Catalog Directory

AI Models Catalog

431 tracked models with dated benchmark snapshots, pairwise comparison hubs, and Stack Engine scoring.

Frontier Models Only Open Weights Only Interactive Compare Hub

Showing 431 of 431 catalog models

Provider list prices are USD

1Claude Opus 5AnthropicFrontier

Anthropic current default flagship. Official API $5/$25 per 1M tokens and a 1M context window (Anthropic, Jul 24 2026).

Elo (Votes)1,624

SWE-bench (Code)79.2%

Input /1M$10

Output /1M$50

View Claude Opus 5 Specs & Benchmarks Compare vs All

2Claude Fable 5AnthropicFrontier

Anthropic top-tier long-horizon model. Official API $10/$50 per 1M tokens (Claude Platform pricing, Aug 2026).

Elo (Votes)1,616

SWE-bench (Code)80%

Input /1M$10

Output /1M$50

View Claude Fable 5 Specs & Benchmarks Compare vs All

3GPT-5.6 SolOpenAIFrontier

OpenAI 5.6 flagship tier. Official API $5/$30 per 1M tokens (OpenAI pricing, Jul 30 2026 update left Sol unchanged).

Elo (Votes)1,608

SWE-bench (Code)77.6%

Input /1M$5.0

Output /1M$30

View GPT-5.6 Sol Specs & Benchmarks Compare vs All

4Claude Opus 4.8AnthropicFrontier

Prior Opus generation still billed at $5/$25. Kept as a compare baseline against Opus 5.

Elo (Votes)1,598

SWE-bench (Code)78.4%

Input /1M$5.0

Output /1M$25

View Claude Opus 4.8 Specs & Benchmarks Compare vs All

5Grok 4.6xAIFrontier

xAI Aug 12 2026 post-training refresh of Grok 4.5. Same $2/$6 API price, 500k context, stronger agentic traces.

Elo (Votes)1,592

SWE-bench (Code)69.1%

Input /1M$2.0

Output /1M$6.0

View Grok 4.6 Specs & Benchmarks Compare vs All

6Claude Opus 4.6AnthropicFrontier

Follow-on Opus release. Slightly behind 4.5 on official SWE-bench bash-only in the last published sweep; stronger long-horizon agent traces.

Elo (Votes)1,574

SWE-bench (Code)75.9%

Input /1M$5.0

Output /1M$25

View Claude Opus 4.6 Specs & Benchmarks Compare vs All

7Gemini 3.6 ProGoogleFrontier

Current Google Pro-class multimodal model. Long context, strong coding, billed like the 3.x Pro tier.

Elo (Votes)1,570

SWE-bench (Code)74.6%

Input /1M$1.3

Output /1M$5.0

View Gemini 3.6 Pro Specs & Benchmarks Compare vs All

8Claude Opus 4.5AnthropicFrontier

Anthropic frontier coding and computer-use model. SWE-bench leader on the official mini-SWE-agent harness in the Feb 2026 refresh.

Elo (Votes)1,568

SWE-bench (Code)76.8%

Input /1M$5.0

Output /1M$25

View Claude Opus 4.5 Specs & Benchmarks Compare vs All

9OpenAI: o3 MiniOpenAI

Auto-discovered from OpenRouter (openai/o3-mini). Preview until a second source matches.

Elo (Votes)1,560

SWE-bench (Code)78.5%

Input /1M$1.1

Output /1M$4.4

View OpenAI: o3 Mini Specs & Benchmarks Compare vs All

10GPT-5OpenAIFrontier

OpenAI flagship reasoning model for 2025–26. Strong general preference Elo and multimodal coverage.

Elo (Votes)1,558

SWE-bench (Code)68.4%

Input /1M$1.3

Output /1M$10

View GPT-5 Specs & Benchmarks Compare vs All

11GLM-5.3Zhipu🇨🇳 CNFrontier

Z.ai Aug 14 2026 post-train of the GLM-5.2 744B base. Coding-plan live; open weights promised after a two-week safety review (z.ai/blog/glm-5.3).

Elo (Votes)1,558

SWE-bench (Code)76.4%

Input /1M$0.50

Output /1M$1.8

View GLM-5.3 Specs & Benchmarks Compare vs All

12Claude Sonnet 5AnthropicFrontier

Anthropic workhorse. Official $2/$10 per 1M tokens made permanent on Aug 10 2026.

Elo (Votes)1,556

SWE-bench (Code)73.8%

Input /1M$2.0

Output /1M$10

View Claude Sonnet 5 Specs & Benchmarks Compare vs All

13Gemini 3 ProGoogleFrontier

Google frontier multimodal model with a multi-million-token context window.

Elo (Votes)1,552

SWE-bench (Code)72.4%

Input /1M$1.3

Output /1M$5.0

View Gemini 3 Pro Specs & Benchmarks Compare vs All

14GPT-5.6 TerraOpenAIFrontier

OpenAI 5.6 mid tier. Official API $2/$12 per 1M after the Jul 30 2026 price cut.

Elo (Votes)1,548

SWE-bench (Code)70.4%

Input /1M$1.0

Output /1M$6.0

View GPT-5.6 Terra Specs & Benchmarks Compare vs All

15GPT-4.5 OrionOpenAIFrontier

OpenAI largest dense non-reasoning model with expansive world knowledge and reduced hallucinations.

Elo (Votes)1,540

SWE-bench (Code)71%

Input /1M$75

Output /1M$150

View GPT-4.5 Orion Specs & Benchmarks Compare vs All

16DeepSeek V4 ProDeepSeek🇨🇳 CNOpen WeightsFrontier

Open-weight-adjacent DeepSeek flagship. High reasoning density per dollar.

Elo (Votes)1,536

SWE-bench (Code)71.6%

Input /1M$0.43

Output /1M$0.87

View DeepSeek V4 Pro Specs & Benchmarks Compare vs All

17Gemini 3.7 FlashGoogleFrontier

Google Aug 13 2026 workhorse. Official intro price $0.75/$3.75 per 1M through Dec 31 2026; 1,048,576-token context (Google blog).

Elo (Votes)1,530

SWE-bench (Code)72.4%

Input /1M$0.38

Output /1M$1.9

View Gemini 3.7 Flash Specs & Benchmarks Compare vs All

18Kimi K3Moonshot🇨🇳 CNFrontier

Moonshot AI frontier flagship reasoning and agent swarm model with 256k context and top-tier SWE-bench coding capability.

Elo (Votes)1,528

SWE-bench (Code)73.8%

Input /1M$3.0

Output /1M$15

View Kimi K3 Specs & Benchmarks Compare vs All

19Claude Sonnet 4.5AnthropicFrontier

Workhorse Anthropic model: most of Opus coding quality at a mid-tier price.

Elo (Votes)1,524

SWE-bench (Code)70.1%

Input /1M$3.0

Output /1M$15

View Claude Sonnet 4.5 Specs & Benchmarks Compare vs All

20Qwen 3 MaxAlibaba🇨🇳 CNFrontier

Alibaba flagship. Strong math and multilingual code.

Elo (Votes)1,518

SWE-bench (Code)67.8%

Input /1M$0.78

Output /1M$3.9

View Qwen 3 Max Specs & Benchmarks Compare vs All

21MoonshotAI: Kimi K2.5Moonshot🇨🇳 CN

Auto-discovered from OpenRouter (moonshotai/kimi-k2.5). Preview until a second source matches.

Elo (Votes)1,515

SWE-bench (Code)71.3%

Input /1M$0.57

Output /1M$2.8

View MoonshotAI: Kimi K2.5 Specs & Benchmarks Compare vs All

22OpenAI: o1OpenAI

Auto-discovered from OpenRouter (openai/o1). Preview until a second source matches.

Elo (Votes)1,512

SWE-bench (Code)48.9%

Input /1M$15

Output /1M$60

View OpenAI: o1 Specs & Benchmarks Compare vs All

23Gemini 3.6 FlashGoogleFrontier

Google Jul 21 workhorse. Now shares the 3.7 Flash introductory $0.75/$3.75 rate through Dec 31 2026.

Elo (Votes)1,506

SWE-bench (Code)70.8%

Input /1M$0.75

Output /1M$3.8

View Gemini 3.6 Flash Specs & Benchmarks Compare vs All

24Gemini 3 FlashGoogleFrontier

Fast Google frontier-adjacent model. Near-top official SWE-bench at a fraction of Opus price.

Elo (Votes)1,495

SWE-bench (Code)75.8%

Input /1M$0.50

Output /1M$3.0

View Gemini 3 Flash Specs & Benchmarks Compare vs All

25Qwen QwQ 32BAlibaba🇨🇳 CNOpen WeightsFrontier

Alibaba specialized open reasoning model competing with frontier closed reasoning models.

Elo (Votes)1,495

SWE-bench (Code)67.5%

Input /1M$0.30

Output /1M$1.2

View Qwen QwQ 32B Specs & Benchmarks Compare vs All

26GLM-5.2Zhipu🇨🇳 CNOpen WeightsFrontier

Zhipu flagship. Strong Chinese/English coding and agents.

Elo (Votes)1,492

SWE-bench (Code)69.3%

Input /1M$0.31

Output /1M$0.97

View GLM-5.2 Specs & Benchmarks Compare vs All

27Gemini 2.0 Flash ThinkingGoogleFrontier

Google experimental reasoning model that visualizes thoughts in real-time.

Elo (Votes)1,490

SWE-bench (Code)66.8%

Input /1M$0.10

Output /1M$0.40

View Gemini 2.0 Flash Thinking Specs & Benchmarks Compare vs All

28DeepSeek V4 FlashDeepSeek🇨🇳 CNOpen WeightsFrontier

DeepSeek Jul 31 2026 price-performance SKU. Public listings put it near $0.14/$0.28 per 1M tokens.

Elo (Votes)1,490

SWE-bench (Code)71.2%

Input /1M$0.14

Output /1M$0.28

View DeepSeek V4 Flash Specs & Benchmarks Compare vs All

29Claude Opus 4Anthropic

First Claude 4 Opus generation. Baseline for opus 4 vs opus 5.

Elo (Votes)1,490

SWE-bench (Code)72.5%

Input /1M$15

Output /1M$75

View Claude Opus 4 Specs & Benchmarks Compare vs All

30Grok 4xAI

Previous xAI flagship.

Elo (Votes)1,488

SWE-bench (Code)58.6%

Input /1M$3.0

Output /1M$15

View Grok 4 Specs & Benchmarks Compare vs All

31MiniMax M2.5MiniMax🇨🇳 CNOpen WeightsFrontier

MiniMax coding model. Tied near the top of official SWE-bench bash-only in Feb 2026.

Elo (Votes)1,478

SWE-bench (Code)75.8%

Input /1M$0.22

Output /1M$0.90

View MiniMax M2.5 Specs & Benchmarks Compare vs All

32Yi-Lightning01.AI🇨🇳 CNFrontier

01.AI ultra-fast reasoning model delivering top LiveBench efficiency.

Elo (Votes)1,475

SWE-bench (Code)63.4%

Input /1M$0.14

Output /1M$0.14

View Yi-Lightning Specs & Benchmarks Compare vs All

33Seed 2.1 TurboByteDance🇨🇳 CN

ByteDance Seed 2.1 Turbo, listed on public model timelines as an Aug 10 2026 API drop.

Elo (Votes)1,472

SWE-bench (Code)63.2%

Input /1M$0.50

Output /1M$2.5

View Seed 2.1 Turbo Specs & Benchmarks Compare vs All

34Doubao Pro 1.5ByteDance🇨🇳 CNFrontier

ByteDance flagship enterprise model with ultra-low token cost and 128k context.

Elo (Votes)1,470

SWE-bench (Code)62.1%

Input /1M$0.11

Output /1M$0.28

View Doubao Pro 1.5 Specs & Benchmarks Compare vs All

35Llama 4 MaverickMetaOpen WeightsFrontier

Meta natively multimodal open-weight flagship.

Elo (Votes)1,468

SWE-bench (Code)57.1%

Input /1M$0.20

Output /1M$0.80

View Llama 4 Maverick Specs & Benchmarks Compare vs All

36GPT-5.6 LunaOpenAI

OpenAI 5.6 fast/cheap tier. Official API $0.20/$1.20 per 1M after the Jul 30 80% Luna cut.

Elo (Votes)1,466

SWE-bench (Code)61.8%

Input /1M$0.10

Output /1M$0.60

View GPT-5.6 Luna Specs & Benchmarks Compare vs All

37MoonshotAI: Kimi K2 0711Moonshot🇨🇳 CN

Auto-discovered from OpenRouter (moonshotai/kimi-k2). Preview until a second source matches.

Elo (Votes)1,465

SWE-bench (Code)65.8%

Input /1M$0.57

Output /1M$2.3

View MoonshotAI: Kimi K2 0711 Specs & Benchmarks Compare vs All

38Mistral Large 3MistralFrontier

Mistral European flagship with strong function calling.

Elo (Votes)1,456

SWE-bench (Code)55.4%

Input /1M$2.0

Output /1M$6.0

View Mistral Large 3 Specs & Benchmarks Compare vs All

39Claude Sonnet 4Anthropic

First Sonnet 4 generation. Bridge between 3.5/3.7 and Sonnet 5.

Elo (Votes)1,455

SWE-bench (Code)62.8%

Input /1M$3.0

Output /1M$15

View Claude Sonnet 4 Specs & Benchmarks Compare vs All

40Ernie 4.5 TurboBaidu🇨🇳 CN

Baidu current multimodal enterprise foundation model with broad Chinese knowledge.

Elo (Votes)1,450

SWE-bench (Code)57%

Input /1M$0.30

Output /1M$1.2

View Ernie 4.5 Turbo Specs & Benchmarks Compare vs All

41Qwen 2.5 PlusAlibaba🇨🇳 CN

Alibaba balanced flagship API model with high-throughput general reasoning.

Elo (Votes)1,445

SWE-bench (Code)59.2%

Input /1M$0.25

Output /1M$1.0

View Qwen 2.5 Plus Specs & Benchmarks Compare vs All

42OpenAI o1-miniOpenAI

OpenAI high-speed, cost-effective reasoning model optimized for STEM, math, and code generation.

Elo (Votes)1,445

SWE-bench (Code)56.4%

Input /1M$1.1

Output /1M$4.4

View OpenAI o1-mini Specs & Benchmarks Compare vs All

43Qwen3 235BAlibaba🇨🇳 CNOpen Weights

Open-weight Qwen3 mixture-of-experts.

Elo (Votes)1,440

SWE-bench (Code)59.4%

Input /1M$0.45

Output /1M$1.8

View Qwen3 235B Specs & Benchmarks Compare vs All

44Claude Haiku 4.5Anthropic

Anthropic cheap/fast Claude SKU. Official Claude Platform list price $1/$5 per 1M tokens (Anthropic Haiku page).

Elo (Votes)1,438

SWE-bench (Code)58.2%

Input /1M$1.0

Output /1M$5.0

View Claude Haiku 4.5 Specs & Benchmarks Compare vs All

45Yi-Large01.AI🇨🇳 CN

01.AI full-scale dense model for complex instruction following.

Elo (Votes)1,430

SWE-bench (Code)53.8%

Input /1M$0.30

Output /1M$0.30

View Yi-Large Specs & Benchmarks Compare vs All

46Qwen 2.5 Coder 32BAlibaba🇨🇳 CNOpen Weights

Alibaba dedicated open-weight code generation model with near-frontier SWE-bench Verified coding capability.

Elo (Votes)1,425

SWE-bench (Code)65.2%

Input /1M$0.18

Output /1M$0.72

View Qwen 2.5 Coder 32B Specs & Benchmarks Compare vs All

47Kimi Chat 1.5Moonshot🇨🇳 CN

Moonshot ultra-long context model supporting up to 2 million tokens per request.

Elo (Votes)1,420

SWE-bench (Code)51%

Input /1M$0.20

Output /1M$0.80

View Kimi Chat 1.5 Specs & Benchmarks Compare vs All

48Llama 4 ScoutMetaOpen Weights

Meta open-weight Llama 4 long-context sibling of Maverick. Common public API lists sit near $0.08–$0.30 / $0.30–$0.70 per 1M; we store a conservative hosted list until OpenRouter overwrites.

Elo (Votes)1,412

SWE-bench (Code)52.4%

Input /1M$0.10

Output /1M$0.30

View Llama 4 Scout Specs & Benchmarks Compare vs All

49GPT-5 miniOpenAI

Cost-efficient GPT-5 distill for high-volume agents.

Elo (Votes)1,410

SWE-bench (Code)52.4%

Input /1M$0.25

Output /1M$2.0

View GPT-5 mini Specs & Benchmarks Compare vs All

50Grok 3xAI

Previous xAI generation before Grok 4. Kept for grok 3 vs grok 4.

Elo (Votes)1,405

SWE-bench (Code)51.4%

Input /1M$3.0

Output /1M$15

View Grok 3 Specs & Benchmarks Compare vs All

51Qwen3.8 27BAlibaba🇨🇳 CNOpen Weights

Alibaba open-weight 27B drop dated Aug 14 2026. Dense enough to self-host; not a frontier MoE.

Elo (Votes)1,398

SWE-bench (Code)58.8%

Input /1M$0.45

Output /1M$3.2

View Qwen3.8 27B Specs & Benchmarks Compare vs All

52Llama 3.1 405BMetaOpen Weights

Meta flagship open-weight 405B dense foundation model with 128k context window.

Elo (Votes)1,370

SWE-bench (Code)58.4%

Input /1M$1.3

Output /1M$3.5

View Llama 3.1 405B Specs & Benchmarks Compare vs All

53DeepSeek Coder V2DeepSeek🇨🇳 CNOpen Weights

DeepSeek open-weight Mixture-of-Experts coding model supporting 338 programming languages and 128k context.

Elo (Votes)1,365

SWE-bench (Code)60.5%

Input /1M$0.14

Output /1M$0.28

View DeepSeek Coder V2 Specs & Benchmarks Compare vs All

54Claude 3.7 SonnetAnthropic

Hybrid-reasoning Sonnet from 2025. Kept for historical compare pages.

Elo (Votes)1,362

SWE-bench (Code)70.3%

Input /1M$3.0

Output /1M$15

View Claude 3.7 Sonnet Specs & Benchmarks Compare vs All

55Doubao Lite 1.5ByteDance🇨🇳 CN

ByteDance high-speed lightweight model priced at sub-cent levels.

Elo (Votes)1,360

SWE-bench (Code)46%

Input /1M$0.040

Output /1M$0.10

View Doubao Lite 1.5 Specs & Benchmarks Compare vs All

56DeepSeek R1DeepSeek🇨🇳 CNOpen Weights

Open-weights reasoning model trained with large-scale RL.

Elo (Votes)1,358

SWE-bench (Code)65.2%

Input /1M$0.70

Output /1M$2.5

View DeepSeek R1 Specs & Benchmarks Compare vs All

57Gemini 2.5 ProGoogle

Previous Google long-context flagship.

Elo (Votes)1,350

SWE-bench (Code)63.8%

Input /1M$1.3

Output /1M$10

View Gemini 2.5 Pro Specs & Benchmarks Compare vs All

58Command ACohere

Cohere enterprise RAG and tool-use model.

Elo (Votes)1,344

SWE-bench (Code)42.6%

Input /1M$2.5

Output /1M$10

View Command A Specs & Benchmarks Compare vs All

59GPT-4oOpenAI

Previous OpenAI flagship. Still a common compare baseline on legacy pages.

Elo (Votes)1,335

SWE-bench (Code)54.8%

Input /1M$2.5

Output /1M$10

View GPT-4o Specs & Benchmarks Compare vs All

60Codestral 25.01Mistral

Mistral code-specialist model.

Elo (Votes)1,320

SWE-bench (Code)51.8%

Input /1M$0.30

Output /1M$0.90

View Codestral 25.01 Specs & Benchmarks Compare vs All

61DeepSeek V3DeepSeek🇨🇳 CNOpen Weights

Prior DeepSeek flagship. Baseline for v3 vs v4.

Elo (Votes)1,310

SWE-bench (Code)48.6%

Input /1M$0.26

Output /1M$1.0

View DeepSeek V3 Specs & Benchmarks Compare vs All

62Gemini 2.5 FlashGoogle

Previous Google speed workhorse.

Elo (Votes)1,295

SWE-bench (Code)48%

Input /1M$0.30

Output /1M$2.5

View Gemini 2.5 Flash Specs & Benchmarks Compare vs All

63Llama 3.3 70BMetaOpen Weights

Previous Meta 70B open-weight workhorse.

Elo (Votes)1,285

SWE-bench (Code)45.1%

Input /1M$0.10

Output /1M$0.32

View Llama 3.3 70B Specs & Benchmarks Compare vs All

64Claude 3.5 SonnetAnthropic

2024 workhorse. Still a high-intent compare against GPT-4o.

Elo (Votes)1,280

SWE-bench (Code)49%

Input /1M$3.0

Output /1M$15

View Claude 3.5 Sonnet Specs & Benchmarks Compare vs All

65GPT-4o miniOpenAI

Legacy small OpenAI model. Useful as a cheap baseline.

Elo (Votes)1,272

SWE-bench (Code)41.2%

Input /1M$0.15

Output /1M$0.60

View GPT-4o mini Specs & Benchmarks Compare vs All

66Gemini 1.5 ProGoogle

First million-token Gemini Pro. Baseline for 1.5 vs 2.5 vs 3.x Pro.

Elo (Votes)1,260

SWE-bench (Code)38%

Input /1M$1.3

Output /1M$5.0

View Gemini 1.5 Pro Specs & Benchmarks Compare vs All

67GPT-4 TurboOpenAI

GPT-4 Turbo 128k. Historical flagship for gpt-4 turbo vs gpt-4o / gpt-5.

Elo (Votes)1,255

SWE-bench (Code)33.2%

Input /1M$10

Output /1M$30

View GPT-4 Turbo Specs & Benchmarks Compare vs All

68Claude 3 OpusAnthropic

Original Claude 3 flagship. Kept so opus 3 vs later Opus and vs GPT-4o still resolve.

Elo (Votes)1,248

SWE-bench (Code)38.4%

Input /1M$15

Output /1M$75

View Claude 3 Opus Specs & Benchmarks Compare vs All

69Llama 3.1 70BMetaOpen Weights

Llama 3.1 70B instruct. Predecessor to 3.3 70B and Llama 4.

Elo (Votes)1,240

SWE-bench (Code)40.2%

Input /1M$0.40

Output /1M$0.40

View Llama 3.1 70B Specs & Benchmarks Compare vs All

70Claude 3.5 HaikuAnthropic

Previous cheap Claude. Haiku 4.5 is the current $1/$5 SKU.

Elo (Votes)1,224

SWE-bench (Code)36.2%

Input /1M$0.80

Output /1M$4.0

View Claude 3.5 Haiku Specs & Benchmarks Compare vs All

71Dots Studio: Dots3-Note Preview (free)dots-studio

Auto-discovered from OpenRouter (dots-studio/dots-3-note-preview:free). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1MFree

Output /1MFree

View Dots Studio: Dots3-Note Preview (free) Specs & Benchmarks Compare vs All

72Qwen: Qwen3.8 2.4T A95BAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3.8-2.4t-a95b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.0

Output /1M$6.0

View Qwen: Qwen3.8 2.4T A95B Specs & Benchmarks Compare vs All

73ByteDance Seed: Seed-2.0-Codebytedance-seed🇨🇳 CN

Auto-discovered from OpenRouter (bytedance-seed/seed-2.0-code). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.50

Output /1M$3.0

View ByteDance Seed: Seed-2.0-Code Specs & Benchmarks Compare vs All

74LiquidAI: LFM2.5-2.6B (free)liquid

Auto-discovered from OpenRouter (liquid/lfm-2.5-2.6b:free). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1MFree

Output /1MFree

View LiquidAI: LFM2.5-2.6B (free) Specs & Benchmarks Compare vs All

75NVIDIA: Nemotron 3.5 Lightningnvidia

Auto-discovered from OpenRouter (nvidia/nemotron-3.5-lightning). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.10

Output /1M$0.25

View NVIDIA: Nemotron 3.5 Lightning Specs & Benchmarks Compare vs All

76NVIDIA: Nemotron 3.5 Lightning (free)nvidia

Auto-discovered from OpenRouter (nvidia/nemotron-3.5-lightning:free). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1MFree

Output /1MFree

View NVIDIA: Nemotron 3.5 Lightning (free) Specs & Benchmarks Compare vs All

77Sakana: Sakana Namazusakana

Auto-discovered from OpenRouter (sakana/sakana-namazu). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.95

Output /1M$4.0

View Sakana: Sakana Namazu Specs & Benchmarks Compare vs All

78Upstage: Solar Pro 4upstage

Auto-discovered from OpenRouter (upstage/solar-pro4). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.030

Output /1M$0.12

View Upstage: Solar Pro 4 Specs & Benchmarks Compare vs All

79Meta: Muse Glimmer 30BMeta

Auto-discovered from OpenRouter (meta/muse-glimmer-30b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.35

Output /1M$1.5

View Meta: Muse Glimmer 30B Specs & Benchmarks Compare vs All

80Meta: Muse Spark 1.2Meta

Auto-discovered from OpenRouter (meta/muse-spark-1.2). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.3

Output /1M$4.3

View Meta: Muse Spark 1.2 Specs & Benchmarks Compare vs All

81Qwen: Qwen3.8 MaxAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3.8-max). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.0

Output /1M$6.0

View Qwen: Qwen3.8 Max Specs & Benchmarks Compare vs All

82DeepSeek V4 Flash Latest~deepseek🇨🇳 CN

Auto-discovered from OpenRouter (~deepseek/deepseek-v4-flash-latest). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.067

Output /1M$0.13

View DeepSeek V4 Flash Latest Specs & Benchmarks Compare vs All

83Thinking Machines: Inkling Smallthinkingmachines

Auto-discovered from OpenRouter (thinkingmachines/inkling-small). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.45

Output /1M$1.2

View Thinking Machines: Inkling Small Specs & Benchmarks Compare vs All

84Qwen: Qwen3.7 FlashAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3.7-flash). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.030

Output /1M$0.13

View Qwen: Qwen3.7 Flash Specs & Benchmarks Compare vs All

85Claude Opus 5 (batch)Anthropic

Auto-discovered from OpenRouter (anthropic/claude-opus-5:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.5

Output /1M$13

View Claude Opus 5 (batch) Specs & Benchmarks Compare vs All

86Ling-3.0-flashinclusionai

Auto-discovered from OpenRouter (inclusionai/ling-3.0-flash). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.021

Output /1M$0.063

View Ling-3.0-flash Specs & Benchmarks Compare vs All

87Poolside: Laguna S 2.1poolside

Auto-discovered from OpenRouter (poolside/laguna-s-2.1). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.090

Output /1M$0.18

View Poolside: Laguna S 2.1 Specs & Benchmarks Compare vs All

88Poolside: Laguna S 2.1 (free)poolside

Auto-discovered from OpenRouter (poolside/laguna-s-2.1:free). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1MFree

Output /1MFree

View Poolside: Laguna S 2.1 (free) Specs & Benchmarks Compare vs All

89Google: Gemini 3.6 Flash (batch)Google

Auto-discovered from OpenRouter (google/gemini-3.6-flash:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.38

Output /1M$1.9

View Google: Gemini 3.6 Flash (batch) Specs & Benchmarks Compare vs All

90Google: Gemini 3.5 Flash LiteGoogle

Auto-discovered from OpenRouter (google/gemini-3.5-flash-lite). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.30

Output /1M$2.5

View Google: Gemini 3.5 Flash Lite Specs & Benchmarks Compare vs All

91Google: Gemini 3.5 Flash Lite (batch)Google

Auto-discovered from OpenRouter (google/gemini-3.5-flash-lite:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.15

Output /1M$1.3

View Google: Gemini 3.5 Flash Lite (batch) Specs & Benchmarks Compare vs All

92Meituan: LongCat 2.0meituan

Auto-discovered from OpenRouter (meituan/longcat-2.0). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.30

Output /1M$1.2

View Meituan: LongCat 2.0 Specs & Benchmarks Compare vs All

93Thinking Machines: Inklingthinkingmachines

Auto-discovered from OpenRouter (thinkingmachines/inkling). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.95

Output /1M$4.0

View Thinking Machines: Inkling Specs & Benchmarks Compare vs All

94Thinking Machines: Inkling (batch)thinkingmachines

Auto-discovered from OpenRouter (thinkingmachines/inkling:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.50

Output /1M$2.0

View Thinking Machines: Inkling (batch) Specs & Benchmarks Compare vs All

95Auto Router (Beta)openrouter

Auto-discovered from OpenRouter (openrouter/auto-beta). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M-$1.0M

Output /1M-$1.0M

View Auto Router (Beta) Specs & Benchmarks Compare vs All

96Meta: Muse Spark 1.1Meta

Auto-discovered from OpenRouter (meta/muse-spark-1.1). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.3

Output /1M$4.3

View Meta: Muse Spark 1.1 Specs & Benchmarks Compare vs All

97Kwaipilot: KAT-Coder-Air V2.5kwaipilot

Auto-discovered from OpenRouter (kwaipilot/kat-coder-air-v2.5). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.15

Output /1M$0.60

View Kwaipilot: KAT-Coder-Air V2.5 Specs & Benchmarks Compare vs All

98Kwaipilot: KAT-Coder-Pro V2.5kwaipilot

Auto-discovered from OpenRouter (kwaipilot/kat-coder-pro-v2.5). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.74

Output /1M$3.0

View Kwaipilot: KAT-Coder-Pro V2.5 Specs & Benchmarks Compare vs All

99OpenAI: GPT-5.6 Luna ProOpenAI

Auto-discovered from OpenRouter (openai/gpt-5.6-luna-pro). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.10

Output /1M$0.60

View OpenAI: GPT-5.6 Luna Pro Specs & Benchmarks Compare vs All

100OpenAI: GPT-5.6 Luna Pro (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-5.6-luna-pro:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.10

Output /1M$0.60

View OpenAI: GPT-5.6 Luna Pro (batch) Specs & Benchmarks Compare vs All

101OpenAI: GPT-5.6 Luna (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-5.6-luna:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.10

Output /1M$0.60

View OpenAI: GPT-5.6 Luna (batch) Specs & Benchmarks Compare vs All

102OpenAI: GPT-5.6 Terra ProOpenAI

Auto-discovered from OpenRouter (openai/gpt-5.6-terra-pro). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.0

Output /1M$6.0

View OpenAI: GPT-5.6 Terra Pro Specs & Benchmarks Compare vs All

103OpenAI: GPT-5.6 Terra Pro (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-5.6-terra-pro:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.0

Output /1M$6.0

View OpenAI: GPT-5.6 Terra Pro (batch) Specs & Benchmarks Compare vs All

104OpenAI: GPT-5.6 Terra (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-5.6-terra:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.0

Output /1M$6.0

View OpenAI: GPT-5.6 Terra (batch) Specs & Benchmarks Compare vs All

105OpenAI: GPT-5.6 Sol ProOpenAI

Auto-discovered from OpenRouter (openai/gpt-5.6-sol-pro). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$5.0

Output /1M$30

View OpenAI: GPT-5.6 Sol Pro Specs & Benchmarks Compare vs All

106OpenAI: GPT-5.6 Sol Pro (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-5.6-sol-pro:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.5

Output /1M$15

View OpenAI: GPT-5.6 Sol Pro (batch) Specs & Benchmarks Compare vs All

107OpenAI: GPT-5.6 Sol (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-5.6-sol:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.5

Output /1M$15

View OpenAI: GPT-5.6 Sol (batch) Specs & Benchmarks Compare vs All

108xAI: Grok Latest~x-ai

Auto-discovered from OpenRouter (~x-ai/grok-latest). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.0

Output /1M$6.0

View xAI: Grok Latest Specs & Benchmarks Compare vs All

109AionLabs: Aion-3.0-Miniaion-labs

Auto-discovered from OpenRouter (aion-labs/aion-3.0-mini). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.70

Output /1M$1.4

View AionLabs: Aion-3.0-Mini Specs & Benchmarks Compare vs All

110AionLabs: Aion-3.0aion-labs

Auto-discovered from OpenRouter (aion-labs/aion-3.0). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$3.0

Output /1M$6.0

View AionLabs: Aion-3.0 Specs & Benchmarks Compare vs All

111Tencent: Hy3tencent

Auto-discovered from OpenRouter (tencent/hy3). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.13

Output /1M$0.53

View Tencent: Hy3 Specs & Benchmarks Compare vs All

112Poolside: Laguna XS 2.1poolside

Auto-discovered from OpenRouter (poolside/laguna-xs-2.1). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.060

Output /1M$0.12

View Poolside: Laguna XS 2.1 Specs & Benchmarks Compare vs All

113Poolside: Laguna XS 2.1 (free)poolside

Auto-discovered from OpenRouter (poolside/laguna-xs-2.1:free). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1MFree

Output /1MFree

View Poolside: Laguna XS 2.1 (free) Specs & Benchmarks Compare vs All

114Anthropic: Claude Sonnet 5 (batch)Anthropic

Auto-discovered from OpenRouter (anthropic/claude-sonnet-5:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.0

Output /1M$5.0

View Anthropic: Claude Sonnet 5 (batch) Specs & Benchmarks Compare vs All

115Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google

Auto-discovered from OpenRouter (google/gemini-3.1-flash-lite-image). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.25

Output /1M$1.5

View Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) Specs & Benchmarks Compare vs All

116Nex AGI: Nex-N2-Mininex-agi

Auto-discovered from OpenRouter (nex-agi/nex-n2-mini). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.025

Output /1M$0.10

View Nex AGI: Nex-N2-Mini Specs & Benchmarks Compare vs All

117Sakana: Fugu Ultrasakana

Auto-discovered from OpenRouter (sakana/fugu-ultra). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$5.0

Output /1M$30

View Sakana: Fugu Ultra Specs & Benchmarks Compare vs All

118Google: Nano Banana 2 (Gemini 3.1 Flash Image)Google

Auto-discovered from OpenRouter (google/gemini-3.1-flash-image). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.50

Output /1M$3.0

View Google: Nano Banana 2 (Gemini 3.1 Flash Image) Specs & Benchmarks Compare vs All

119Google: Nano Banana Pro (Gemini 3 Pro Image)Google

Auto-discovered from OpenRouter (google/gemini-3-pro-image). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.0

Output /1M$12

View Google: Nano Banana Pro (Gemini 3 Pro Image) Specs & Benchmarks Compare vs All

120Cohere: North Mini Code (free)Cohere

Auto-discovered from OpenRouter (cohere/north-mini-code:free). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1MFree

Output /1MFree

View Cohere: North Mini Code (free) Specs & Benchmarks Compare vs All

121Z.ai: GLM 5.2 (batch)Zhipu🇨🇳 CN

Auto-discovered from OpenRouter (z-ai/glm-5.2:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.70

Output /1M$2.2

View Z.ai: GLM 5.2 (batch) Specs & Benchmarks Compare vs All

122OpenRouter: Fusionopenrouter

Auto-discovered from OpenRouter (openrouter/fusion). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M-$1.0M

Output /1M-$1.0M

View OpenRouter: Fusion Specs & Benchmarks Compare vs All

123MoonshotAI: Kimi K2.7 CodeMoonshot🇨🇳 CN

Auto-discovered from OpenRouter (moonshotai/kimi-k2.7-code). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.71

Output /1M$3.5

View MoonshotAI: Kimi K2.7 Code Specs & Benchmarks Compare vs All

124MoonshotAI: Kimi K2.7 Code (batch)Moonshot🇨🇳 CN

Auto-discovered from OpenRouter (moonshotai/kimi-k2.7-code:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.47

Output /1M$2.0

View MoonshotAI: Kimi K2.7 Code (batch) Specs & Benchmarks Compare vs All

125Anthropic: Claude Fable Latest~anthropic

Auto-discovered from OpenRouter (~anthropic/claude-fable-latest). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$10

Output /1M$50

View Anthropic: Claude Fable Latest Specs & Benchmarks Compare vs All

126Anthropic: Claude Fable 5 (batch)Anthropic

Auto-discovered from OpenRouter (anthropic/claude-fable-5:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$5.0

Output /1M$25

View Anthropic: Claude Fable 5 (batch) Specs & Benchmarks Compare vs All

127Nex AGI: Nex-N2-Pronex-agi

Auto-discovered from OpenRouter (nex-agi/nex-n2-pro). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.25

Output /1M$1.0

View Nex AGI: Nex-N2-Pro Specs & Benchmarks Compare vs All

128NVIDIA: Nemotron 3.5 Content Safety (free)nvidia

Auto-discovered from OpenRouter (nvidia/nemotron-3.5-content-safety:free). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1MFree

Output /1MFree

View NVIDIA: Nemotron 3.5 Content Safety (free) Specs & Benchmarks Compare vs All

129NVIDIA: Nemotron 3 Ultranvidia

Auto-discovered from OpenRouter (nvidia/nemotron-3-ultra-550b-a55b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.60

Output /1M$3.6

View NVIDIA: Nemotron 3 Ultra Specs & Benchmarks Compare vs All

130NVIDIA: Nemotron 3 Ultra (batch)nvidia

Auto-discovered from OpenRouter (nvidia/nemotron-3-ultra-550b-a55b:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.30

Output /1M$1.8

View NVIDIA: Nemotron 3 Ultra (batch) Specs & Benchmarks Compare vs All

131NVIDIA: Nemotron 3 Ultra (free)nvidia

Auto-discovered from OpenRouter (nvidia/nemotron-3-ultra-550b-a55b:free). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1MFree

Output /1MFree

View NVIDIA: Nemotron 3 Ultra (free) Specs & Benchmarks Compare vs All

132Qwen: Qwen3.7 PlusAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3.7-plus). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.32

Output /1M$1.3

View Qwen: Qwen3.7 Plus Specs & Benchmarks Compare vs All

133MiniMax: MiniMax M3MiniMax🇨🇳 CN

Auto-discovered from OpenRouter (minimax/minimax-m3). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.30

Output /1M$1.2

View MiniMax: MiniMax M3 Specs & Benchmarks Compare vs All

134MiniMax: MiniMax M3 (batch)MiniMax🇨🇳 CN

Auto-discovered from OpenRouter (minimax/minimax-m3:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.15

Output /1M$0.60

View MiniMax: MiniMax M3 (batch) Specs & Benchmarks Compare vs All

135StepFun: Step 3.7 Flashstepfun🇨🇳 CN

Auto-discovered from OpenRouter (stepfun/step-3.7-flash). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.20

Output /1M$1.1

View StepFun: Step 3.7 Flash Specs & Benchmarks Compare vs All

136Anthropic: Claude Opus 4.8 (Fast)Anthropic

Auto-discovered from OpenRouter (anthropic/claude-opus-4.8-fast). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$10

Output /1M$50

View Anthropic: Claude Opus 4.8 (Fast) Specs & Benchmarks Compare vs All

137Anthropic: Claude Opus 4.8 (batch)Anthropic

Auto-discovered from OpenRouter (anthropic/claude-opus-4.8:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.5

Output /1M$13

View Anthropic: Claude Opus 4.8 (batch) Specs & Benchmarks Compare vs All

138Qwen: Qwen3.7 MaxAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3.7-max). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.5

Output /1M$4.4

View Qwen: Qwen3.7 Max Specs & Benchmarks Compare vs All

139SpaceXAI: Grok Build 0.1xAI

Auto-discovered from OpenRouter (x-ai/grok-build-0.1). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.0

Output /1M$2.0

View SpaceXAI: Grok Build 0.1 Specs & Benchmarks Compare vs All

140Google: Gemini 3.5 FlashGoogle

Auto-discovered from OpenRouter (google/gemini-3.5-flash). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.5

Output /1M$9.0

View Google: Gemini 3.5 Flash Specs & Benchmarks Compare vs All

141Google: Gemini 3.5 Flash (batch)Google

Auto-discovered from OpenRouter (google/gemini-3.5-flash:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.75

Output /1M$4.5

View Google: Gemini 3.5 Flash (batch) Specs & Benchmarks Compare vs All

142Anthropic: Claude Opus 4.7 (Fast)Anthropic

Auto-discovered from OpenRouter (anthropic/claude-opus-4.7-fast). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$30

Output /1M$150

View Anthropic: Claude Opus 4.7 (Fast) Specs & Benchmarks Compare vs All

143Perceptron: Perceptron Mk1perceptron

Auto-discovered from OpenRouter (perceptron/perceptron-mk1). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.15

Output /1M$1.5

View Perceptron: Perceptron Mk1 Specs & Benchmarks Compare vs All

144inclusionAI: Ring-2.6-1Tinclusionai

Auto-discovered from OpenRouter (inclusionai/ring-2.6-1t). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.075

Output /1M$0.63

View inclusionAI: Ring-2.6-1T Specs & Benchmarks Compare vs All

145Google: Gemini 3.1 Flash LiteGoogle

Auto-discovered from OpenRouter (google/gemini-3.1-flash-lite). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.25

Output /1M$1.5

View Google: Gemini 3.1 Flash Lite Specs & Benchmarks Compare vs All

146Google: Gemini 3.1 Flash Lite (batch)Google

Auto-discovered from OpenRouter (google/gemini-3.1-flash-lite:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.13

Output /1M$0.75

View Google: Gemini 3.1 Flash Lite (batch) Specs & Benchmarks Compare vs All

147OpenAI: GPT Chat LatestOpenAI

Auto-discovered from OpenRouter (openai/gpt-chat-latest). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$5.0

Output /1M$30

View OpenAI: GPT Chat Latest Specs & Benchmarks Compare vs All

148SpaceXAI: Grok 4.3xAI

Auto-discovered from OpenRouter (x-ai/grok-4.3). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.3

Output /1M$2.5

View SpaceXAI: Grok 4.3 Specs & Benchmarks Compare vs All

149IBM: Granite 4.1 8Bibm-granite

Auto-discovered from OpenRouter (ibm-granite/granite-4.1-8b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.050

Output /1M$0.10

View IBM: Granite 4.1 8B Specs & Benchmarks Compare vs All

150Mistral: Mistral Medium 3.5Mistral

Auto-discovered from OpenRouter (mistralai/mistral-medium-3-5). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.5

Output /1M$7.5

View Mistral: Mistral Medium 3.5 Specs & Benchmarks Compare vs All

151NVIDIA: Nemotron 3 Nano Omni (free)nvidia

Auto-discovered from OpenRouter (nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1MFree

Output /1MFree

View NVIDIA: Nemotron 3 Nano Omni (free) Specs & Benchmarks Compare vs All

152Anthropic Claude Haiku Latest~anthropic

Auto-discovered from OpenRouter (~anthropic/claude-haiku-latest). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.0

Output /1M$5.0

View Anthropic Claude Haiku Latest Specs & Benchmarks Compare vs All

153OpenAI GPT Mini Latest~openai

Auto-discovered from OpenRouter (~openai/gpt-mini-latest). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.75

Output /1M$4.5

View OpenAI GPT Mini Latest Specs & Benchmarks Compare vs All

154Google Gemini Pro Latest~google

Auto-discovered from OpenRouter (~google/gemini-pro-latest). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.0

Output /1M$12

View Google Gemini Pro Latest Specs & Benchmarks Compare vs All

155MoonshotAI Kimi Latest~moonshotai🇨🇳 CN

Auto-discovered from OpenRouter (~moonshotai/kimi-latest). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.8

Output /1M$14

View MoonshotAI Kimi Latest Specs & Benchmarks Compare vs All

156Google Gemini Flash Latest~google

Auto-discovered from OpenRouter (~google/gemini-flash-latest). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.38

Output /1M$1.9

View Google Gemini Flash Latest Specs & Benchmarks Compare vs All

157Anthropic Claude Sonnet Latest~anthropic

Auto-discovered from OpenRouter (~anthropic/claude-sonnet-latest). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.0

Output /1M$10

View Anthropic Claude Sonnet Latest Specs & Benchmarks Compare vs All

158OpenAI GPT Latest~openai

Auto-discovered from OpenRouter (~openai/gpt-latest). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$5.0

Output /1M$30

View OpenAI GPT Latest Specs & Benchmarks Compare vs All

159Qwen: Qwen3.5 Plus 2026-04-20Alibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3.5-plus-20260420). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.30

Output /1M$1.8

View Qwen: Qwen3.5 Plus 2026-04-20 Specs & Benchmarks Compare vs All

160Qwen: Qwen3.6 FlashAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3.6-flash). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.19

Output /1M$1.1

View Qwen: Qwen3.6 Flash Specs & Benchmarks Compare vs All

161Qwen: Qwen3.6 35B A3BAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3.6-35b-a3b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.15

Output /1M$1.0

View Qwen: Qwen3.6 35B A3B Specs & Benchmarks Compare vs All

162Qwen: Qwen3.6 Max PreviewAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3.6-max-preview). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.0

Output /1M$6.2

View Qwen: Qwen3.6 Max Preview Specs & Benchmarks Compare vs All

163Qwen: Qwen3.6 27BAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3.6-27b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.30

Output /1M$2.0

View Qwen: Qwen3.6 27B Specs & Benchmarks Compare vs All

164OpenAI: GPT-5.5 ProOpenAI

Auto-discovered from OpenRouter (openai/gpt-5.5-pro). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$30

Output /1M$180

View OpenAI: GPT-5.5 Pro Specs & Benchmarks Compare vs All

165OpenAI: GPT-5.5 Pro (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-5.5-pro:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$15

Output /1M$90

View OpenAI: GPT-5.5 Pro (batch) Specs & Benchmarks Compare vs All

166OpenAI: GPT-5.5OpenAI

Auto-discovered from OpenRouter (openai/gpt-5.5). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$5.0

Output /1M$30

View OpenAI: GPT-5.5 Specs & Benchmarks Compare vs All

167OpenAI: GPT-5.5 (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-5.5:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.5

Output /1M$15

View OpenAI: GPT-5.5 (batch) Specs & Benchmarks Compare vs All

168inclusionAI: Ling-2.6-1Tinclusionai

Auto-discovered from OpenRouter (inclusionai/ling-2.6-1t). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.075

Output /1M$0.63

View inclusionAI: Ling-2.6-1T Specs & Benchmarks Compare vs All

169Tencent: Hy3 previewtencent

Auto-discovered from OpenRouter (tencent/hy3-preview). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.18

Output /1M$0.60

View Tencent: Hy3 preview Specs & Benchmarks Compare vs All

170Xiaomi: MiMo-V2.5-Proxiaomi

Auto-discovered from OpenRouter (xiaomi/mimo-v2.5-pro). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.43

Output /1M$0.87

View Xiaomi: MiMo-V2.5-Pro Specs & Benchmarks Compare vs All

171Xiaomi: MiMo-V2.5xiaomi

Auto-discovered from OpenRouter (xiaomi/mimo-v2.5). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.14

Output /1M$0.28

View Xiaomi: MiMo-V2.5 Specs & Benchmarks Compare vs All

172OpenAI: GPT-5.4 Image 2OpenAI

Auto-discovered from OpenRouter (openai/gpt-5.4-image-2). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$8.0

Output /1M$15

View OpenAI: GPT-5.4 Image 2 Specs & Benchmarks Compare vs All

173inclusionAI: Ling-2.6-flashinclusionai

Auto-discovered from OpenRouter (inclusionai/ling-2.6-flash). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.010

Output /1M$0.030

View inclusionAI: Ling-2.6-flash Specs & Benchmarks Compare vs All

174Anthropic: Claude Opus Latest~anthropic

Auto-discovered from OpenRouter (~anthropic/claude-opus-latest). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$5.0

Output /1M$25

View Anthropic: Claude Opus Latest Specs & Benchmarks Compare vs All

175Pareto Code Routeropenrouter

Auto-discovered from OpenRouter (openrouter/pareto-code). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M-$1.0M

Output /1M-$1.0M

View Pareto Code Router Specs & Benchmarks Compare vs All

176MoonshotAI: Kimi K2.6Moonshot🇨🇳 CN

Auto-discovered from OpenRouter (moonshotai/kimi-k2.6). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.54

Output /1M$2.3

View MoonshotAI: Kimi K2.6 Specs & Benchmarks Compare vs All

177Anthropic: Claude Opus 4.7Anthropic

Auto-discovered from OpenRouter (anthropic/claude-opus-4.7). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$5.0

Output /1M$25

View Anthropic: Claude Opus 4.7 Specs & Benchmarks Compare vs All

178Anthropic: Claude Opus 4.7 (batch)Anthropic

Auto-discovered from OpenRouter (anthropic/claude-opus-4.7:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.5

Output /1M$13

View Anthropic: Claude Opus 4.7 (batch) Specs & Benchmarks Compare vs All

179Z.ai: GLM 5.1Zhipu🇨🇳 CN

Auto-discovered from OpenRouter (z-ai/glm-5.1). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.97

Output /1M$3.0

View Z.ai: GLM 5.1 Specs & Benchmarks Compare vs All

180Google: Gemma 4 26B A4B Google

Auto-discovered from OpenRouter (google/gemma-4-26b-a4b-it). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.12

Output /1M$0.40

View Google: Gemma 4 26B A4B Specs & Benchmarks Compare vs All

181Google: Gemma 4 26B A4B (free)Google

Auto-discovered from OpenRouter (google/gemma-4-26b-a4b-it:free). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1MFree

Output /1MFree

View Google: Gemma 4 26B A4B (free) Specs & Benchmarks Compare vs All

182Google: Gemma 4 31BGoogle

Auto-discovered from OpenRouter (google/gemma-4-31b-it). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.10

Output /1M$0.34

View Google: Gemma 4 31B Specs & Benchmarks Compare vs All

183Google: Gemma 4 31B (free)Google

Auto-discovered from OpenRouter (google/gemma-4-31b-it:free). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1MFree

Output /1MFree

View Google: Gemma 4 31B (free) Specs & Benchmarks Compare vs All

184Qwen: Qwen3.6 PlusAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3.6-plus). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.33

Output /1M$1.9

View Qwen: Qwen3.6 Plus Specs & Benchmarks Compare vs All

185Z.ai: GLM 5V TurboZhipu🇨🇳 CN

Auto-discovered from OpenRouter (z-ai/glm-5v-turbo). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.2

Output /1M$4.0

View Z.ai: GLM 5V Turbo Specs & Benchmarks Compare vs All

186Arcee AI: Trinity Large Thinkingarcee-ai

Auto-discovered from OpenRouter (arcee-ai/trinity-large-thinking). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.22

Output /1M$0.85

View Arcee AI: Trinity Large Thinking Specs & Benchmarks Compare vs All

187SpaceXAI: Grok 4.20 Multi-AgentxAI

Auto-discovered from OpenRouter (x-ai/grok-4.20-multi-agent). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.3

Output /1M$2.5

View SpaceXAI: Grok 4.20 Multi-Agent Specs & Benchmarks Compare vs All

188SpaceXAI: Grok 4.20xAI

Auto-discovered from OpenRouter (x-ai/grok-4.20). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.3

Output /1M$2.5

View SpaceXAI: Grok 4.20 Specs & Benchmarks Compare vs All

189Google: Lyria 3 Pro PreviewGoogle

Auto-discovered from OpenRouter (google/lyria-3-pro-preview). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1MFree

Output /1MFree

View Google: Lyria 3 Pro Preview Specs & Benchmarks Compare vs All

190Google: Lyria 3 Clip PreviewGoogle

Auto-discovered from OpenRouter (google/lyria-3-clip-preview). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1MFree

Output /1MFree

View Google: Lyria 3 Clip Preview Specs & Benchmarks Compare vs All

191Kwaipilot: KAT-Coder-Pro V2kwaipilot

Auto-discovered from OpenRouter (kwaipilot/kat-coder-pro-v2). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.30

Output /1M$1.2

View Kwaipilot: KAT-Coder-Pro V2 Specs & Benchmarks Compare vs All

192Reka Edgerekaai

Auto-discovered from OpenRouter (rekaai/reka-edge). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.10

Output /1M$0.10

View Reka Edge Specs & Benchmarks Compare vs All

193MiniMax: MiniMax M2.7MiniMax🇨🇳 CN

Auto-discovered from OpenRouter (minimax/minimax-m2.7). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.30

Output /1M$1.2

View MiniMax: MiniMax M2.7 Specs & Benchmarks Compare vs All

194OpenAI: GPT-5.4 NanoOpenAI

Auto-discovered from OpenRouter (openai/gpt-5.4-nano). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.20

Output /1M$1.3

View OpenAI: GPT-5.4 Nano Specs & Benchmarks Compare vs All

195OpenAI: GPT-5.4 Nano (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-5.4-nano:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.10

Output /1M$0.63

View OpenAI: GPT-5.4 Nano (batch) Specs & Benchmarks Compare vs All

196OpenAI: GPT-5.4 MiniOpenAI

Auto-discovered from OpenRouter (openai/gpt-5.4-mini). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.75

Output /1M$4.5

View OpenAI: GPT-5.4 Mini Specs & Benchmarks Compare vs All

197OpenAI: GPT-5.4 Mini (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-5.4-mini:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.38

Output /1M$2.3

View OpenAI: GPT-5.4 Mini (batch) Specs & Benchmarks Compare vs All

198Mistral: Mistral Small 4Mistral

Auto-discovered from OpenRouter (mistralai/mistral-small-2603). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.15

Output /1M$0.60

View Mistral: Mistral Small 4 Specs & Benchmarks Compare vs All

199Z.ai: GLM 5 TurboZhipu🇨🇳 CN

Auto-discovered from OpenRouter (z-ai/glm-5-turbo). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.2

Output /1M$4.0

View Z.ai: GLM 5 Turbo Specs & Benchmarks Compare vs All

200NVIDIA: Nemotron 3 Supernvidia

Auto-discovered from OpenRouter (nvidia/nemotron-3-super-120b-a12b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.085

Output /1M$0.40

View NVIDIA: Nemotron 3 Super Specs & Benchmarks Compare vs All

201NVIDIA: Nemotron 3 Super (free)nvidia

Auto-discovered from OpenRouter (nvidia/nemotron-3-super-120b-a12b:free). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1MFree

Output /1MFree

View NVIDIA: Nemotron 3 Super (free) Specs & Benchmarks Compare vs All

202ByteDance Seed: Seed-2.0-Litebytedance-seed🇨🇳 CN

Auto-discovered from OpenRouter (bytedance-seed/seed-2.0-lite). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.25

Output /1M$2.0

View ByteDance Seed: Seed-2.0-Lite Specs & Benchmarks Compare vs All

203Qwen: Qwen3.5-9BAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3.5-9b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.10

Output /1M$0.15

View Qwen: Qwen3.5-9B Specs & Benchmarks Compare vs All

204OpenAI: GPT-5.4 ProOpenAI

Auto-discovered from OpenRouter (openai/gpt-5.4-pro). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$30

Output /1M$180

View OpenAI: GPT-5.4 Pro Specs & Benchmarks Compare vs All

205OpenAI: GPT-5.4 Pro (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-5.4-pro:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$15

Output /1M$90

View OpenAI: GPT-5.4 Pro (batch) Specs & Benchmarks Compare vs All

206OpenAI: GPT-5.4OpenAI

Auto-discovered from OpenRouter (openai/gpt-5.4). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.5

Output /1M$15

View OpenAI: GPT-5.4 Specs & Benchmarks Compare vs All

207OpenAI: GPT-5.4 (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-5.4:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.3

Output /1M$7.5

View OpenAI: GPT-5.4 (batch) Specs & Benchmarks Compare vs All

208Inception: Mercury 2inception

Auto-discovered from OpenRouter (inception/mercury-2). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.25

Output /1M$0.75

View Inception: Mercury 2 Specs & Benchmarks Compare vs All

209Google: Gemini 3.1 Flash Lite PreviewGoogle

Auto-discovered from OpenRouter (google/gemini-3.1-flash-lite-preview). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.25

Output /1M$1.5

View Google: Gemini 3.1 Flash Lite Preview Specs & Benchmarks Compare vs All

210ByteDance Seed: Seed-2.0-Minibytedance-seed🇨🇳 CN

Auto-discovered from OpenRouter (bytedance-seed/seed-2.0-mini). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.10

Output /1M$0.40

View ByteDance Seed: Seed-2.0-Mini Specs & Benchmarks Compare vs All

211Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)Google

Auto-discovered from OpenRouter (google/gemini-3.1-flash-image-preview). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.50

Output /1M$3.0

View Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) Specs & Benchmarks Compare vs All

212Qwen: Qwen3.5-35B-A3BAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3.5-35b-a3b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.22

Output /1M$1.8

View Qwen: Qwen3.5-35B-A3B Specs & Benchmarks Compare vs All

213Qwen: Qwen3.5-27BAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3.5-27b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.20

Output /1M$1.6

View Qwen: Qwen3.5-27B Specs & Benchmarks Compare vs All

214Qwen: Qwen3.5-122B-A10BAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3.5-122b-a10b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.29

Output /1M$2.4

View Qwen: Qwen3.5-122B-A10B Specs & Benchmarks Compare vs All

215Qwen: Qwen3.5-FlashAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3.5-flash-02-23). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.065

Output /1M$0.26

View Qwen: Qwen3.5-Flash Specs & Benchmarks Compare vs All

216Google: Gemini 3.1 Pro Preview Custom ToolsGoogle

Auto-discovered from OpenRouter (google/gemini-3.1-pro-preview-customtools). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.0

Output /1M$12

View Google: Gemini 3.1 Pro Preview Custom Tools Specs & Benchmarks Compare vs All

217OpenAI: GPT-5.3-CodexOpenAI

Auto-discovered from OpenRouter (openai/gpt-5.3-codex). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.8

Output /1M$14

View OpenAI: GPT-5.3-Codex Specs & Benchmarks Compare vs All

218AionLabs: Aion-2.0aion-labs

Auto-discovered from OpenRouter (aion-labs/aion-2.0). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.80

Output /1M$1.6

View AionLabs: Aion-2.0 Specs & Benchmarks Compare vs All

219Google: Gemini 3.1 Pro PreviewGoogle

Auto-discovered from OpenRouter (google/gemini-3.1-pro-preview). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.0

Output /1M$12

View Google: Gemini 3.1 Pro Preview Specs & Benchmarks Compare vs All

220Google: Gemini 3.1 Pro Preview (batch)Google

Auto-discovered from OpenRouter (google/gemini-3.1-pro-preview:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.0

Output /1M$6.0

View Google: Gemini 3.1 Pro Preview (batch) Specs & Benchmarks Compare vs All

221Anthropic: Claude Sonnet 4.6Anthropic

Auto-discovered from OpenRouter (anthropic/claude-sonnet-4.6). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$3.0

Output /1M$15

View Anthropic: Claude Sonnet 4.6 Specs & Benchmarks Compare vs All

222Anthropic: Claude Sonnet 4.6 (batch)Anthropic

Auto-discovered from OpenRouter (anthropic/claude-sonnet-4.6:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.5

Output /1M$7.5

View Anthropic: Claude Sonnet 4.6 (batch) Specs & Benchmarks Compare vs All

223Qwen: Qwen3.5 Plus 2026-02-15Alibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3.5-plus-02-15). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.26

Output /1M$1.6

View Qwen: Qwen3.5 Plus 2026-02-15 Specs & Benchmarks Compare vs All

224Qwen: Qwen3.5 397B A17BAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3.5-397b-a17b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.39

Output /1M$2.3

View Qwen: Qwen3.5 397B A17B Specs & Benchmarks Compare vs All

225Qwen: Qwen3 Max ThinkingAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3-max-thinking). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.78

Output /1M$3.9

View Qwen: Qwen3 Max Thinking Specs & Benchmarks Compare vs All

226Anthropic: Claude Opus 4.6 (batch)Anthropic

Auto-discovered from OpenRouter (anthropic/claude-opus-4.6:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.5

Output /1M$13

View Anthropic: Claude Opus 4.6 (batch) Specs & Benchmarks Compare vs All

227Qwen: Qwen3 Coder NextAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3-coder-next). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.12

Output /1M$0.80

View Qwen: Qwen3 Coder Next Specs & Benchmarks Compare vs All

228Free Models Routeropenrouter

Auto-discovered from OpenRouter (openrouter/free). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1MFree

Output /1MFree

View Free Models Router Specs & Benchmarks Compare vs All

229StepFun: Step 3.5 Flashstepfun🇨🇳 CN

Auto-discovered from OpenRouter (stepfun/step-3.5-flash). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.10

Output /1M$0.30

View StepFun: Step 3.5 Flash Specs & Benchmarks Compare vs All

230Upstage: Solar Pro 3upstage

Auto-discovered from OpenRouter (upstage/solar-pro-3). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.15

Output /1M$0.60

View Upstage: Solar Pro 3 Specs & Benchmarks Compare vs All

231MiniMax: MiniMax M2-herMiniMax🇨🇳 CN

Auto-discovered from OpenRouter (minimax/minimax-m2-her). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.30

Output /1M$1.2

View MiniMax: MiniMax M2-her Specs & Benchmarks Compare vs All

232Writer: Palmyra X5writer

Auto-discovered from OpenRouter (writer/palmyra-x5). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.60

Output /1M$6.0

View Writer: Palmyra X5 Specs & Benchmarks Compare vs All

233OpenAI: GPT AudioOpenAI

Auto-discovered from OpenRouter (openai/gpt-audio). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.5

Output /1M$10

View OpenAI: GPT Audio Specs & Benchmarks Compare vs All

234OpenAI: GPT Audio MiniOpenAI

Auto-discovered from OpenRouter (openai/gpt-audio-mini). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.60

Output /1M$2.4

View OpenAI: GPT Audio Mini Specs & Benchmarks Compare vs All

235Z.ai: GLM 4.7 FlashZhipu🇨🇳 CN

Auto-discovered from OpenRouter (z-ai/glm-4.7-flash). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.060

Output /1M$0.40

View Z.ai: GLM 4.7 Flash Specs & Benchmarks Compare vs All

236OpenAI: GPT-5.2-CodexOpenAI

Auto-discovered from OpenRouter (openai/gpt-5.2-codex). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.8

Output /1M$14

View OpenAI: GPT-5.2-Codex Specs & Benchmarks Compare vs All

237ByteDance Seed: Seed 1.6 Flashbytedance-seed🇨🇳 CN

Auto-discovered from OpenRouter (bytedance-seed/seed-1.6-flash). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.075

Output /1M$0.30

View ByteDance Seed: Seed 1.6 Flash Specs & Benchmarks Compare vs All

238ByteDance Seed: Seed 1.6bytedance-seed🇨🇳 CN

Auto-discovered from OpenRouter (bytedance-seed/seed-1.6). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.25

Output /1M$2.0

View ByteDance Seed: Seed 1.6 Specs & Benchmarks Compare vs All

239MiniMax: MiniMax M2.1MiniMax🇨🇳 CN

Auto-discovered from OpenRouter (minimax/minimax-m2.1). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.30

Output /1M$1.2

View MiniMax: MiniMax M2.1 Specs & Benchmarks Compare vs All

240Z.ai: GLM 4.7Zhipu🇨🇳 CN

Auto-discovered from OpenRouter (z-ai/glm-4.7). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.40

Output /1M$1.8

View Z.ai: GLM 4.7 Specs & Benchmarks Compare vs All

241Google: Gemini 3 Flash Preview (batch)Google

Auto-discovered from OpenRouter (google/gemini-3-flash-preview:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.25

Output /1M$1.5

View Google: Gemini 3 Flash Preview (batch) Specs & Benchmarks Compare vs All

242NVIDIA: Nemotron 3 Nano 30B A3Bnvidia

Auto-discovered from OpenRouter (nvidia/nemotron-3-nano-30b-a3b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.050

Output /1M$0.20

View NVIDIA: Nemotron 3 Nano 30B A3B Specs & Benchmarks Compare vs All

243NVIDIA: Nemotron 3 Nano 30B A3B (free)nvidia

Auto-discovered from OpenRouter (nvidia/nemotron-3-nano-30b-a3b:free). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1MFree

Output /1MFree

View NVIDIA: Nemotron 3 Nano 30B A3B (free) Specs & Benchmarks Compare vs All

244OpenAI: GPT-5.2 ChatOpenAI

Auto-discovered from OpenRouter (openai/gpt-5.2-chat). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.8

Output /1M$14

View OpenAI: GPT-5.2 Chat Specs & Benchmarks Compare vs All

245OpenAI: GPT-5.2 ProOpenAI

Auto-discovered from OpenRouter (openai/gpt-5.2-pro). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$21

Output /1M$168

View OpenAI: GPT-5.2 Pro Specs & Benchmarks Compare vs All

246OpenAI: GPT-5.2 Pro (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-5.2-pro:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$11

Output /1M$84

View OpenAI: GPT-5.2 Pro (batch) Specs & Benchmarks Compare vs All

247OpenAI: GPT-5.2OpenAI

Auto-discovered from OpenRouter (openai/gpt-5.2). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.8

Output /1M$14

View OpenAI: GPT-5.2 Specs & Benchmarks Compare vs All

248OpenAI: GPT-5.2 (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-5.2:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.88

Output /1M$7.0

View OpenAI: GPT-5.2 (batch) Specs & Benchmarks Compare vs All

249Relace: Relace Searchrelace

Auto-discovered from OpenRouter (relace/relace-search). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.0

Output /1M$3.0

View Relace: Relace Search Specs & Benchmarks Compare vs All

250Z.ai: GLM 4.6VZhipu🇨🇳 CN

Auto-discovered from OpenRouter (z-ai/glm-4.6v). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.30

Output /1M$0.90

View Z.ai: GLM 4.6V Specs & Benchmarks Compare vs All

251Body Builder (beta)openrouter

Auto-discovered from OpenRouter (openrouter/bodybuilder). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M-$1.0M

Output /1M-$1.0M

View Body Builder (beta) Specs & Benchmarks Compare vs All

252OpenAI: GPT-5.1-Codex-MaxOpenAI

Auto-discovered from OpenRouter (openai/gpt-5.1-codex-max). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.3

Output /1M$10

View OpenAI: GPT-5.1-Codex-Max Specs & Benchmarks Compare vs All

253Amazon: Nova 2 Liteamazon

Auto-discovered from OpenRouter (amazon/nova-2-lite-v1). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.30

Output /1M$2.5

View Amazon: Nova 2 Lite Specs & Benchmarks Compare vs All

254Mistral: Ministral 3 14B 2512Mistral

Auto-discovered from OpenRouter (mistralai/ministral-14b-2512). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.20

Output /1M$0.20

View Mistral: Ministral 3 14B 2512 Specs & Benchmarks Compare vs All

255Mistral: Ministral 3 8B 2512Mistral

Auto-discovered from OpenRouter (mistralai/ministral-8b-2512). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.15

Output /1M$0.15

View Mistral: Ministral 3 8B 2512 Specs & Benchmarks Compare vs All

256Mistral: Ministral 3 3B 2512Mistral

Auto-discovered from OpenRouter (mistralai/ministral-3b-2512). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.10

Output /1M$0.10

View Mistral: Ministral 3 3B 2512 Specs & Benchmarks Compare vs All

257Mistral: Mistral Large 3 2512Mistral

Auto-discovered from OpenRouter (mistralai/mistral-large-2512). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.50

Output /1M$1.5

View Mistral: Mistral Large 3 2512 Specs & Benchmarks Compare vs All

258DeepSeek: DeepSeek V3.2DeepSeek🇨🇳 CN

Auto-discovered from OpenRouter (deepseek/deepseek-v3.2). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.27

Output /1M$0.40

View DeepSeek: DeepSeek V3.2 Specs & Benchmarks Compare vs All

259Anthropic: Claude Opus 4.5 (batch)Anthropic

Auto-discovered from OpenRouter (anthropic/claude-opus-4.5:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.5

Output /1M$13

View Anthropic: Claude Opus 4.5 (batch) Specs & Benchmarks Compare vs All

260AllenAI: Olmo 3 32B Thinkallenai

Auto-discovered from OpenRouter (allenai/olmo-3-32b-think). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.15

Output /1M$0.50

View AllenAI: Olmo 3 32B Think Specs & Benchmarks Compare vs All

261Google: Nano Banana Pro (Gemini 3 Pro Image Preview)Google

Auto-discovered from OpenRouter (google/gemini-3-pro-image-preview). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.0

Output /1M$12

View Google: Nano Banana Pro (Gemini 3 Pro Image Preview) Specs & Benchmarks Compare vs All

262Deep Cogito: Cogito v2.1 671Bdeepcogito

Auto-discovered from OpenRouter (deepcogito/cogito-v2.1-671b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.3

Output /1M$1.3

View Deep Cogito: Cogito v2.1 671B Specs & Benchmarks Compare vs All

263OpenAI: GPT-5.1OpenAI

Auto-discovered from OpenRouter (openai/gpt-5.1). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.3

Output /1M$10

View OpenAI: GPT-5.1 Specs & Benchmarks Compare vs All

264OpenAI: GPT-5.1 (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-5.1:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.63

Output /1M$5.0

View OpenAI: GPT-5.1 (batch) Specs & Benchmarks Compare vs All

265OpenAI: GPT-5.1-CodexOpenAI

Auto-discovered from OpenRouter (openai/gpt-5.1-codex). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.3

Output /1M$10

View OpenAI: GPT-5.1-Codex Specs & Benchmarks Compare vs All

266OpenAI: GPT-5.1-Codex-MiniOpenAI

Auto-discovered from OpenRouter (openai/gpt-5.1-codex-mini). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.25

Output /1M$2.0

View OpenAI: GPT-5.1-Codex-Mini Specs & Benchmarks Compare vs All

267MoonshotAI: Kimi K2 ThinkingMoonshot🇨🇳 CN

Auto-discovered from OpenRouter (moonshotai/kimi-k2-thinking). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.60

Output /1M$2.5

View MoonshotAI: Kimi K2 Thinking Specs & Benchmarks Compare vs All

268Amazon: Nova Premier 1.0amazon

Auto-discovered from OpenRouter (amazon/nova-premier-v1). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.5

Output /1M$13

View Amazon: Nova Premier 1.0 Specs & Benchmarks Compare vs All

269Perplexity: Sonar Pro Searchperplexity

Auto-discovered from OpenRouter (perplexity/sonar-pro-search). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$3.0

Output /1M$15

View Perplexity: Sonar Pro Search Specs & Benchmarks Compare vs All

270Mistral: Voxtral Small 24B 2507Mistral

Auto-discovered from OpenRouter (mistralai/voxtral-small-24b-2507). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.10

Output /1M$0.30

View Mistral: Voxtral Small 24B 2507 Specs & Benchmarks Compare vs All

271OpenAI: gpt-oss-safeguard-20bOpenAI

Auto-discovered from OpenRouter (openai/gpt-oss-safeguard-20b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.075

Output /1M$0.30

View OpenAI: gpt-oss-safeguard-20b Specs & Benchmarks Compare vs All

272NVIDIA: Nemotron Nano 12B 2 VL (free)nvidia

Auto-discovered from OpenRouter (nvidia/nemotron-nano-12b-v2-vl:free). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1MFree

Output /1MFree

View NVIDIA: Nemotron Nano 12B 2 VL (free) Specs & Benchmarks Compare vs All

273MiniMax: MiniMax M2MiniMax🇨🇳 CN

Auto-discovered from OpenRouter (minimax/minimax-m2). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.26

Output /1M$1.0

View MiniMax: MiniMax M2 Specs & Benchmarks Compare vs All

274Qwen: Qwen3 VL 32B InstructAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3-vl-32b-instruct). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.10

Output /1M$0.42

View Qwen: Qwen3 VL 32B Instruct Specs & Benchmarks Compare vs All

275IBM: Granite 4.0 Microibm-granite

Auto-discovered from OpenRouter (ibm-granite/granite-4.0-h-micro). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.017

Output /1M$0.11

View IBM: Granite 4.0 Micro Specs & Benchmarks Compare vs All

276OpenAI: GPT-5 Image MiniOpenAI

Auto-discovered from OpenRouter (openai/gpt-5-image-mini). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.5

Output /1M$2.0

View OpenAI: GPT-5 Image Mini Specs & Benchmarks Compare vs All

277Anthropic: Claude Haiku 4.5 (batch)Anthropic

Auto-discovered from OpenRouter (anthropic/claude-haiku-4.5:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.50

Output /1M$2.5

View Anthropic: Claude Haiku 4.5 (batch) Specs & Benchmarks Compare vs All

278Qwen: Qwen3 VL 8B ThinkingAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3-vl-8b-thinking). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.18

Output /1M$2.1

View Qwen: Qwen3 VL 8B Thinking Specs & Benchmarks Compare vs All

279Qwen: Qwen3 VL 8B InstructAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3-vl-8b-instruct). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.12

Output /1M$0.45

View Qwen: Qwen3 VL 8B Instruct Specs & Benchmarks Compare vs All

280OpenAI: GPT-5 ImageOpenAI

Auto-discovered from OpenRouter (openai/gpt-5-image). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$10

Output /1M$10

View OpenAI: GPT-5 Image Specs & Benchmarks Compare vs All

281Google: Nano Banana (Gemini 2.5 Flash Image)Google

Auto-discovered from OpenRouter (google/gemini-2.5-flash-image). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.30

Output /1M$2.5

View Google: Nano Banana (Gemini 2.5 Flash Image) Specs & Benchmarks Compare vs All

282Qwen: Qwen3 VL 30B A3B ThinkingAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3-vl-30b-a3b-thinking). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.20

Output /1M$2.4

View Qwen: Qwen3 VL 30B A3B Thinking Specs & Benchmarks Compare vs All

283Qwen: Qwen3 VL 30B A3B InstructAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3-vl-30b-a3b-instruct). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.13

Output /1M$0.52

View Qwen: Qwen3 VL 30B A3B Instruct Specs & Benchmarks Compare vs All

284OpenAI: GPT-5 ProOpenAI

Auto-discovered from OpenRouter (openai/gpt-5-pro). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$15

Output /1M$120

View OpenAI: GPT-5 Pro Specs & Benchmarks Compare vs All

285OpenAI: GPT-5 Pro (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-5-pro:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$7.5

Output /1M$60

View OpenAI: GPT-5 Pro (batch) Specs & Benchmarks Compare vs All

286Z.ai: GLM 4.6Zhipu🇨🇳 CN

Auto-discovered from OpenRouter (z-ai/glm-4.6). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.55

Output /1M$2.2

View Z.ai: GLM 4.6 Specs & Benchmarks Compare vs All

287Anthropic: Claude Sonnet 4.5 (batch)Anthropic

Auto-discovered from OpenRouter (anthropic/claude-sonnet-4.5:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.5

Output /1M$7.5

View Anthropic: Claude Sonnet 4.5 (batch) Specs & Benchmarks Compare vs All

288DeepSeek: DeepSeek V3.2 ExpDeepSeek🇨🇳 CN

Auto-discovered from OpenRouter (deepseek/deepseek-v3.2-exp). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.27

Output /1M$0.41

View DeepSeek: DeepSeek V3.2 Exp Specs & Benchmarks Compare vs All

289TheDrummer: Cydonia 24B V4.1thedrummer

Auto-discovered from OpenRouter (thedrummer/cydonia-24b-v4.1). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.30

Output /1M$0.50

View TheDrummer: Cydonia 24B V4.1 Specs & Benchmarks Compare vs All

290Relace: Relace Apply 3relace

Auto-discovered from OpenRouter (relace/relace-apply-3). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.85

Output /1M$1.3

View Relace: Relace Apply 3 Specs & Benchmarks Compare vs All

291Qwen: Qwen3 VL 235B A22B ThinkingAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3-vl-235b-a22b-thinking). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.40

Output /1M$4.0

View Qwen: Qwen3 VL 235B A22B Thinking Specs & Benchmarks Compare vs All

292Qwen: Qwen3 VL 235B A22B InstructAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3-vl-235b-a22b-instruct). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.26

Output /1M$1.0

View Qwen: Qwen3 VL 235B A22B Instruct Specs & Benchmarks Compare vs All

293Qwen: Qwen3 Coder PlusAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3-coder-plus). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.65

Output /1M$3.3

View Qwen: Qwen3 Coder Plus Specs & Benchmarks Compare vs All

294OpenAI: GPT-5 Codex (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-5-codex:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.63

Output /1M$5.0

View OpenAI: GPT-5 Codex (batch) Specs & Benchmarks Compare vs All

295DeepSeek: DeepSeek V3.1 TerminusDeepSeek🇨🇳 CN

Auto-discovered from OpenRouter (deepseek/deepseek-v3.1-terminus). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.27

Output /1M$0.95

View DeepSeek: DeepSeek V3.1 Terminus Specs & Benchmarks Compare vs All

296Qwen: Qwen3 Coder FlashAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3-coder-flash). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.20

Output /1M$0.97

View Qwen: Qwen3 Coder Flash Specs & Benchmarks Compare vs All

297Qwen: Qwen3 Next 80B A3B ThinkingAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3-next-80b-a3b-thinking). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.15

Output /1M$1.2

View Qwen: Qwen3 Next 80B A3B Thinking Specs & Benchmarks Compare vs All

298Qwen: Qwen3 Next 80B A3B InstructAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3-next-80b-a3b-instruct). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.10

Output /1M$1.1

View Qwen: Qwen3 Next 80B A3B Instruct Specs & Benchmarks Compare vs All

299Qwen: Qwen Plus 0728Alibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen-plus-2025-07-28). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.26

Output /1M$0.78

View Qwen: Qwen Plus 0728 Specs & Benchmarks Compare vs All

300Qwen: Qwen Plus 0728 (thinking)Alibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen-plus-2025-07-28:thinking). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.26

Output /1M$0.78

View Qwen: Qwen Plus 0728 (thinking) Specs & Benchmarks Compare vs All

301NVIDIA: Nemotron Nano 9B V2 (free)nvidia

Auto-discovered from OpenRouter (nvidia/nemotron-nano-9b-v2:free). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1MFree

Output /1MFree

View NVIDIA: Nemotron Nano 9B V2 (free) Specs & Benchmarks Compare vs All

302MoonshotAI: Kimi K2 0905Moonshot🇨🇳 CN

Auto-discovered from OpenRouter (moonshotai/kimi-k2-0905). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.60

Output /1M$2.5

View MoonshotAI: Kimi K2 0905 Specs & Benchmarks Compare vs All

303Qwen: Qwen3 30B A3B Thinking 2507Alibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3-30b-a3b-thinking-2507). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.20

Output /1M$2.4

View Qwen: Qwen3 30B A3B Thinking 2507 Specs & Benchmarks Compare vs All

304Nous: Hermes 4 70Bnousresearch

Auto-discovered from OpenRouter (nousresearch/hermes-4-70b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.13

Output /1M$0.40

View Nous: Hermes 4 70B Specs & Benchmarks Compare vs All

305Nous: Hermes 4 405Bnousresearch

Auto-discovered from OpenRouter (nousresearch/hermes-4-405b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.0

Output /1M$3.0

View Nous: Hermes 4 405B Specs & Benchmarks Compare vs All

306DeepSeek: DeepSeek V3.1DeepSeek🇨🇳 CN

Auto-discovered from OpenRouter (deepseek/deepseek-chat-v3.1). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.25

Output /1M$0.95

View DeepSeek: DeepSeek V3.1 Specs & Benchmarks Compare vs All

307Mistral: Mistral Medium 3.1Mistral

Auto-discovered from OpenRouter (mistralai/mistral-medium-3.1). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.40

Output /1M$2.0

View Mistral: Mistral Medium 3.1 Specs & Benchmarks Compare vs All

308Z.ai: GLM 4.5VZhipu🇨🇳 CN

Auto-discovered from OpenRouter (z-ai/glm-4.5v). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.60

Output /1M$1.8

View Z.ai: GLM 4.5V Specs & Benchmarks Compare vs All

309AI21: Jamba Large 1.7ai21

Auto-discovered from OpenRouter (ai21/jamba-large-1.7). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.0

Output /1M$8.0

View AI21: Jamba Large 1.7 Specs & Benchmarks Compare vs All

310OpenAI: GPT-5 (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-5:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.63

Output /1M$5.0

View OpenAI: GPT-5 (batch) Specs & Benchmarks Compare vs All

311OpenAI: GPT-5 Mini (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-5-mini:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.13

Output /1M$1.0

View OpenAI: GPT-5 Mini (batch) Specs & Benchmarks Compare vs All

312OpenAI: GPT-5 NanoOpenAI

Auto-discovered from OpenRouter (openai/gpt-5-nano). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.050

Output /1M$0.40

View OpenAI: GPT-5 Nano Specs & Benchmarks Compare vs All

313OpenAI: GPT-5 Nano (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-5-nano:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.025

Output /1M$0.20

View OpenAI: GPT-5 Nano (batch) Specs & Benchmarks Compare vs All

314OpenAI: gpt-oss-120bOpenAI

Auto-discovered from OpenRouter (openai/gpt-oss-120b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.030

Output /1M$0.17

View OpenAI: gpt-oss-120b Specs & Benchmarks Compare vs All

315OpenAI: gpt-oss-20bOpenAI

Auto-discovered from OpenRouter (openai/gpt-oss-20b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.030

Output /1M$0.13

View OpenAI: gpt-oss-20b Specs & Benchmarks Compare vs All

316OpenAI: gpt-oss-20b (free)OpenAI

Auto-discovered from OpenRouter (openai/gpt-oss-20b:free). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1MFree

Output /1MFree

View OpenAI: gpt-oss-20b (free) Specs & Benchmarks Compare vs All

317Anthropic: Claude Opus 4.1Anthropic

Auto-discovered from OpenRouter (anthropic/claude-opus-4.1). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$15

Output /1M$75

View Anthropic: Claude Opus 4.1 Specs & Benchmarks Compare vs All

318Anthropic: Claude Opus 4.1 (batch)Anthropic

Auto-discovered from OpenRouter (anthropic/claude-opus-4.1:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$7.5

Output /1M$38

View Anthropic: Claude Opus 4.1 (batch) Specs & Benchmarks Compare vs All

319Mistral: Codestral 2508Mistral

Auto-discovered from OpenRouter (mistralai/codestral-2508). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.30

Output /1M$0.90

View Mistral: Codestral 2508 Specs & Benchmarks Compare vs All

320Qwen: Qwen3 Coder 30B A3B InstructAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3-coder-30b-a3b-instruct). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.070

Output /1M$0.28

View Qwen: Qwen3 Coder 30B A3B Instruct Specs & Benchmarks Compare vs All

321Qwen: Qwen3 30B A3B Instruct 2507Alibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3-30b-a3b-instruct-2507). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.048

Output /1M$0.19

View Qwen: Qwen3 30B A3B Instruct 2507 Specs & Benchmarks Compare vs All

322Z.ai: GLM 4.5Zhipu🇨🇳 CN

Auto-discovered from OpenRouter (z-ai/glm-4.5). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.60

Output /1M$2.2

View Z.ai: GLM 4.5 Specs & Benchmarks Compare vs All

323Z.ai: GLM 4.5 AirZhipu🇨🇳 CN

Auto-discovered from OpenRouter (z-ai/glm-4.5-air). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.13

Output /1M$0.85

View Z.ai: GLM 4.5 Air Specs & Benchmarks Compare vs All

324Qwen: Qwen3 235B A22B Thinking 2507Alibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3-235b-a22b-thinking-2507). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.23

Output /1M$2.3

View Qwen: Qwen3 235B A22B Thinking 2507 Specs & Benchmarks Compare vs All

325Qwen: Qwen3 Coder 480B A35BAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3-coder). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.30

Output /1M$1.0

View Qwen: Qwen3 Coder 480B A35B Specs & Benchmarks Compare vs All

326ByteDance: UI-TARS 7B ByteDance🇨🇳 CN

Auto-discovered from OpenRouter (bytedance/ui-tars-1.5-7b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.10

Output /1M$0.20

View ByteDance: UI-TARS 7B Specs & Benchmarks Compare vs All

327Google: Gemini 2.5 Flash LiteGoogle

Auto-discovered from OpenRouter (google/gemini-2.5-flash-lite). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.10

Output /1M$0.40

View Google: Gemini 2.5 Flash Lite Specs & Benchmarks Compare vs All

328Google: Gemini 2.5 Flash Lite (batch)Google

Auto-discovered from OpenRouter (google/gemini-2.5-flash-lite:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.050

Output /1M$0.20

View Google: Gemini 2.5 Flash Lite (batch) Specs & Benchmarks Compare vs All

329Qwen: Qwen3 235B A22B Instruct 2507Alibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3-235b-a22b-2507). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.090

Output /1M$0.55

View Qwen: Qwen3 235B A22B Instruct 2507 Specs & Benchmarks Compare vs All

330Venice: Uncensoredcognitivecomputations

Auto-discovered from OpenRouter (cognitivecomputations/dolphin-mistral-24b-venice-edition). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.20

Output /1M$0.90

View Venice: Uncensored Specs & Benchmarks Compare vs All

331Tencent: Hunyuan A13B Instructtencent

Auto-discovered from OpenRouter (tencent/hunyuan-a13b-instruct). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.14

Output /1M$0.57

View Tencent: Hunyuan A13B Instruct Specs & Benchmarks Compare vs All

332Morph: Morph V3 Largemorph

Auto-discovered from OpenRouter (morph/morph-v3-large). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.90

Output /1M$1.9

View Morph: Morph V3 Large Specs & Benchmarks Compare vs All

333Morph: Morph V3 Fastmorph

Auto-discovered from OpenRouter (morph/morph-v3-fast). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.80

Output /1M$1.2

View Morph: Morph V3 Fast Specs & Benchmarks Compare vs All

334Baidu: ERNIE 4.5 VL 424B A47B Baidu🇨🇳 CN

Auto-discovered from OpenRouter (baidu/ernie-4.5-vl-424b-a47b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.42

Output /1M$1.3

View Baidu: ERNIE 4.5 VL 424B A47B Specs & Benchmarks Compare vs All

335Mistral: Mistral Small 3.2 24BMistral

Auto-discovered from OpenRouter (mistralai/mistral-small-3.2-24b-instruct). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.094

Output /1M$0.25

View Mistral: Mistral Small 3.2 24B Specs & Benchmarks Compare vs All

336MiniMax: MiniMax M1MiniMax🇨🇳 CN

Auto-discovered from OpenRouter (minimax/minimax-m1). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.40

Output /1M$2.2

View MiniMax: MiniMax M1 Specs & Benchmarks Compare vs All

337Google: Gemini 2.5 Flash (batch)Google

Auto-discovered from OpenRouter (google/gemini-2.5-flash:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.15

Output /1M$1.3

View Google: Gemini 2.5 Flash (batch) Specs & Benchmarks Compare vs All

338Google: Gemini 2.5 Pro (batch)Google

Auto-discovered from OpenRouter (google/gemini-2.5-pro:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.63

Output /1M$5.0

View Google: Gemini 2.5 Pro (batch) Specs & Benchmarks Compare vs All

339OpenAI: o3 ProOpenAI

Auto-discovered from OpenRouter (openai/o3-pro). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$20

Output /1M$80

View OpenAI: o3 Pro Specs & Benchmarks Compare vs All

340OpenAI: o3 Pro (batch)OpenAI

Auto-discovered from OpenRouter (openai/o3-pro:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$10

Output /1M$40

View OpenAI: o3 Pro (batch) Specs & Benchmarks Compare vs All

341Google: Gemini 2.5 Pro Preview 06-05Google

Auto-discovered from OpenRouter (google/gemini-2.5-pro-preview). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.3

Output /1M$10

View Google: Gemini 2.5 Pro Preview 06-05 Specs & Benchmarks Compare vs All

342DeepSeek: R1 0528DeepSeek🇨🇳 CN

Auto-discovered from OpenRouter (deepseek/deepseek-r1-0528). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.50

Output /1M$2.2

View DeepSeek: R1 0528 Specs & Benchmarks Compare vs All

343Google: Gemma 3n 4BGoogle

Auto-discovered from OpenRouter (google/gemma-3n-e4b-it). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.060

Output /1M$0.12

View Google: Gemma 3n 4B Specs & Benchmarks Compare vs All

344Mistral: Mistral Medium 3Mistral

Auto-discovered from OpenRouter (mistralai/mistral-medium-3). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.40

Output /1M$2.0

View Mistral: Mistral Medium 3 Specs & Benchmarks Compare vs All

345Google: Gemini 2.5 Pro Preview 05-06Google

Auto-discovered from OpenRouter (google/gemini-2.5-pro-preview-05-06). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.3

Output /1M$10

View Google: Gemini 2.5 Pro Preview 05-06 Specs & Benchmarks Compare vs All

346Arcee AI: Virtuoso Largearcee-ai

Auto-discovered from OpenRouter (arcee-ai/virtuoso-large). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.75

Output /1M$1.2

View Arcee AI: Virtuoso Large Specs & Benchmarks Compare vs All

347Meta: Llama Guard 4 12BMeta

Auto-discovered from OpenRouter (meta-llama/llama-guard-4-12b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.18

Output /1M$0.18

View Meta: Llama Guard 4 12B Specs & Benchmarks Compare vs All

348Qwen: Qwen3 30B A3BAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3-30b-a3b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.13

Output /1M$0.52

View Qwen: Qwen3 30B A3B Specs & Benchmarks Compare vs All

349Qwen: Qwen3 8BAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3-8b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.12

Output /1M$0.45

View Qwen: Qwen3 8B Specs & Benchmarks Compare vs All

350Qwen: Qwen3 14BAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3-14b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.12

Output /1M$0.24

View Qwen: Qwen3 14B Specs & Benchmarks Compare vs All

351Qwen: Qwen3 32BAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen3-32b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.080

Output /1M$0.28

View Qwen: Qwen3 32B Specs & Benchmarks Compare vs All

352OpenAI: o4 Mini HighOpenAI

Auto-discovered from OpenRouter (openai/o4-mini-high). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.1

Output /1M$4.4

View OpenAI: o4 Mini High Specs & Benchmarks Compare vs All

353OpenAI: o4 Mini High (batch)OpenAI

Auto-discovered from OpenRouter (openai/o4-mini-high:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.55

Output /1M$2.2

View OpenAI: o4 Mini High (batch) Specs & Benchmarks Compare vs All

354OpenAI: o3OpenAI

Auto-discovered from OpenRouter (openai/o3). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.0

Output /1M$8.0

View OpenAI: o3 Specs & Benchmarks Compare vs All

355OpenAI: o3 (batch)OpenAI

Auto-discovered from OpenRouter (openai/o3:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.0

Output /1M$4.0

View OpenAI: o3 (batch) Specs & Benchmarks Compare vs All

356OpenAI: o4 MiniOpenAI

Auto-discovered from OpenRouter (openai/o4-mini). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.1

Output /1M$4.4

View OpenAI: o4 Mini Specs & Benchmarks Compare vs All

357OpenAI: o4 Mini (batch)OpenAI

Auto-discovered from OpenRouter (openai/o4-mini:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.55

Output /1M$2.2

View OpenAI: o4 Mini (batch) Specs & Benchmarks Compare vs All

358OpenAI: GPT-4.1OpenAI

Auto-discovered from OpenRouter (openai/gpt-4.1). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.0

Output /1M$8.0

View OpenAI: GPT-4.1 Specs & Benchmarks Compare vs All

359OpenAI: GPT-4.1 (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-4.1:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.0

Output /1M$4.0

View OpenAI: GPT-4.1 (batch) Specs & Benchmarks Compare vs All

360OpenAI: GPT-4.1 MiniOpenAI

Auto-discovered from OpenRouter (openai/gpt-4.1-mini). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.40

Output /1M$1.6

View OpenAI: GPT-4.1 Mini Specs & Benchmarks Compare vs All

361OpenAI: GPT-4.1 Mini (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-4.1-mini:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.20

Output /1M$0.80

View OpenAI: GPT-4.1 Mini (batch) Specs & Benchmarks Compare vs All

362OpenAI: GPT-4.1 NanoOpenAI

Auto-discovered from OpenRouter (openai/gpt-4.1-nano). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.10

Output /1M$0.40

View OpenAI: GPT-4.1 Nano Specs & Benchmarks Compare vs All

363OpenAI: GPT-4.1 Nano (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-4.1-nano:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.050

Output /1M$0.20

View OpenAI: GPT-4.1 Nano (batch) Specs & Benchmarks Compare vs All

364DeepSeek: DeepSeek V3 0324DeepSeek🇨🇳 CN

Auto-discovered from OpenRouter (deepseek/deepseek-chat-v3-0324). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.27

Output /1M$1.1

View DeepSeek: DeepSeek V3 0324 Specs & Benchmarks Compare vs All

365OpenAI: o1-proOpenAI

Auto-discovered from OpenRouter (openai/o1-pro). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$150

Output /1M$600

View OpenAI: o1-pro Specs & Benchmarks Compare vs All

366OpenAI: o1-pro (batch)OpenAI

Auto-discovered from OpenRouter (openai/o1-pro:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$75

Output /1M$300

View OpenAI: o1-pro (batch) Specs & Benchmarks Compare vs All

367Mistral: Mistral Small 3.1 24BMistral

Auto-discovered from OpenRouter (mistralai/mistral-small-3.1-24b-instruct). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.35

Output /1M$0.55

View Mistral: Mistral Small 3.1 24B Specs & Benchmarks Compare vs All

368Google: Gemma 3 4BGoogle

Auto-discovered from OpenRouter (google/gemma-3-4b-it). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.050

Output /1M$0.10

View Google: Gemma 3 4B Specs & Benchmarks Compare vs All

369Google: Gemma 3 12BGoogle

Auto-discovered from OpenRouter (google/gemma-3-12b-it). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.050

Output /1M$0.15

View Google: Gemma 3 12B Specs & Benchmarks Compare vs All

370Reka Flash 3rekaai

Auto-discovered from OpenRouter (rekaai/reka-flash-3). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.10

Output /1M$0.20

View Reka Flash 3 Specs & Benchmarks Compare vs All

371Google: Gemma 3 27BGoogle

Auto-discovered from OpenRouter (google/gemma-3-27b-it). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.080

Output /1M$0.45

View Google: Gemma 3 27B Specs & Benchmarks Compare vs All

372TheDrummer: Skyfall 36B V2thedrummer

Auto-discovered from OpenRouter (thedrummer/skyfall-36b-v2). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.55

Output /1M$0.80

View TheDrummer: Skyfall 36B V2 Specs & Benchmarks Compare vs All

373Perplexity: Sonar Reasoning Properplexity

Auto-discovered from OpenRouter (perplexity/sonar-reasoning-pro). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.0

Output /1M$8.0

View Perplexity: Sonar Reasoning Pro Specs & Benchmarks Compare vs All

374Perplexity: Sonar Properplexity

Auto-discovered from OpenRouter (perplexity/sonar-pro). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$3.0

Output /1M$15

View Perplexity: Sonar Pro Specs & Benchmarks Compare vs All

375Perplexity: Sonar Deep Researchperplexity

Auto-discovered from OpenRouter (perplexity/sonar-deep-research). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.0

Output /1M$8.0

View Perplexity: Sonar Deep Research Specs & Benchmarks Compare vs All

376Mistral: SabaMistral

Auto-discovered from OpenRouter (mistralai/mistral-saba). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.20

Output /1M$0.60

View Mistral: Saba Specs & Benchmarks Compare vs All

377OpenAI: o3 Mini HighOpenAI

Auto-discovered from OpenRouter (openai/o3-mini-high). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.1

Output /1M$4.4

View OpenAI: o3 Mini High Specs & Benchmarks Compare vs All

378OpenAI: o3 Mini High (batch)OpenAI

Auto-discovered from OpenRouter (openai/o3-mini-high:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.55

Output /1M$2.2

View OpenAI: o3 Mini High (batch) Specs & Benchmarks Compare vs All

379AionLabs: Aion-RP 1.0 (8B)aion-labs

Auto-discovered from OpenRouter (aion-labs/aion-rp-llama-3.1-8b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.80

Output /1M$1.6

View AionLabs: Aion-RP 1.0 (8B) Specs & Benchmarks Compare vs All

380Qwen: Qwen2.5 VL 72B InstructAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen2.5-vl-72b-instruct). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.25

Output /1M$0.75

View Qwen: Qwen2.5 VL 72B Instruct Specs & Benchmarks Compare vs All

381Qwen: Qwen-PlusAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen-plus). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.26

Output /1M$0.78

View Qwen: Qwen-Plus Specs & Benchmarks Compare vs All

382OpenAI: o3 Mini (batch)OpenAI

Auto-discovered from OpenRouter (openai/o3-mini:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.55

Output /1M$2.2

View OpenAI: o3 Mini (batch) Specs & Benchmarks Compare vs All

383Mistral: Mistral Small 3Mistral

Auto-discovered from OpenRouter (mistralai/mistral-small-24b-instruct-2501). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.050

Output /1M$0.080

View Mistral: Mistral Small 3 Specs & Benchmarks Compare vs All

384Perplexity: Sonarperplexity

Auto-discovered from OpenRouter (perplexity/sonar). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.0

Output /1M$1.0

View Perplexity: Sonar Specs & Benchmarks Compare vs All

385DeepSeek: R1 Distill Llama 70BDeepSeek🇨🇳 CN

Auto-discovered from OpenRouter (deepseek/deepseek-r1-distill-llama-70b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.80

Output /1M$0.80

View DeepSeek: R1 Distill Llama 70B Specs & Benchmarks Compare vs All

386MiniMax: MiniMax-01MiniMax🇨🇳 CN

Auto-discovered from OpenRouter (minimax/minimax-01). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.20

Output /1M$1.1

View MiniMax: MiniMax-01 Specs & Benchmarks Compare vs All

387Microsoft: Phi 4microsoft

Auto-discovered from OpenRouter (microsoft/phi-4). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.070

Output /1M$0.14

View Microsoft: Phi 4 Specs & Benchmarks Compare vs All

388Sao10K: Llama 3.3 Euryale 70Bsao10k

Auto-discovered from OpenRouter (sao10k/l3.3-euryale-70b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.65

Output /1M$0.75

View Sao10K: Llama 3.3 Euryale 70B Specs & Benchmarks Compare vs All

389OpenAI: o1 (batch)OpenAI

Auto-discovered from OpenRouter (openai/o1:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$7.5

Output /1M$30

View OpenAI: o1 (batch) Specs & Benchmarks Compare vs All

390Cohere: Command R7B (12-2024)Cohere

Auto-discovered from OpenRouter (cohere/command-r7b-12-2024). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.037

Output /1M$0.15

View Cohere: Command R7B (12-2024) Specs & Benchmarks Compare vs All

391Amazon: Nova Lite 1.0amazon

Auto-discovered from OpenRouter (amazon/nova-lite-v1). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.060

Output /1M$0.24

View Amazon: Nova Lite 1.0 Specs & Benchmarks Compare vs All

392Amazon: Nova Micro 1.0amazon

Auto-discovered from OpenRouter (amazon/nova-micro-v1). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.035

Output /1M$0.14

View Amazon: Nova Micro 1.0 Specs & Benchmarks Compare vs All

393Amazon: Nova Pro 1.0amazon

Auto-discovered from OpenRouter (amazon/nova-pro-v1). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.80

Output /1M$3.2

View Amazon: Nova Pro 1.0 Specs & Benchmarks Compare vs All

394OpenAI: GPT-4o (2024-11-20)OpenAI

Auto-discovered from OpenRouter (openai/gpt-4o-2024-11-20). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.5

Output /1M$10

View OpenAI: GPT-4o (2024-11-20) Specs & Benchmarks Compare vs All

395Mistral Large 2407Mistral

Auto-discovered from OpenRouter (mistralai/mistral-large-2407). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.0

Output /1M$6.0

View Mistral Large 2407 Specs & Benchmarks Compare vs All

396Qwen2.5 Coder 32B InstructAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen-2.5-coder-32b-instruct). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.66

Output /1M$1.0

View Qwen2.5 Coder 32B Instruct Specs & Benchmarks Compare vs All

397TheDrummer: UnslopNemo 12Bthedrummer

Auto-discovered from OpenRouter (thedrummer/unslopnemo-12b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.40

Output /1M$0.40

View TheDrummer: UnslopNemo 12B Specs & Benchmarks Compare vs All

398Magnum v4 72Banthracite-org

Auto-discovered from OpenRouter (anthracite-org/magnum-v4-72b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$3.0

Output /1M$5.0

View Magnum v4 72B Specs & Benchmarks Compare vs All

399Qwen: Qwen2.5 7B InstructAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen-2.5-7b-instruct). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.10

Output /1M$0.20

View Qwen: Qwen2.5 7B Instruct Specs & Benchmarks Compare vs All

400TheDrummer: Rocinante 12Bthedrummer

Auto-discovered from OpenRouter (thedrummer/rocinante-12b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.25

Output /1M$0.50

View TheDrummer: Rocinante 12B Specs & Benchmarks Compare vs All

401Meta: Llama 3.2 1B InstructMeta

Auto-discovered from OpenRouter (meta-llama/llama-3.2-1b-instruct). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.027

Output /1M$0.20

View Meta: Llama 3.2 1B Instruct Specs & Benchmarks Compare vs All

402Meta: Llama 3.2 3B InstructMeta

Auto-discovered from OpenRouter (meta-llama/llama-3.2-3b-instruct). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.050

Output /1M$0.33

View Meta: Llama 3.2 3B Instruct Specs & Benchmarks Compare vs All

403Qwen2.5 72B InstructAlibaba🇨🇳 CN

Auto-discovered from OpenRouter (qwen/qwen-2.5-72b-instruct). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.36

Output /1M$0.40

View Qwen2.5 72B Instruct Specs & Benchmarks Compare vs All

404Cohere: Command R (08-2024)Cohere

Auto-discovered from OpenRouter (cohere/command-r-08-2024). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.15

Output /1M$0.60

View Cohere: Command R (08-2024) Specs & Benchmarks Compare vs All

405Sao10K: Llama 3.1 Euryale 70B v2.2sao10k

Auto-discovered from OpenRouter (sao10k/l3.1-euryale-70b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.85

Output /1M$0.85

View Sao10K: Llama 3.1 Euryale 70B v2.2 Specs & Benchmarks Compare vs All

406Nous: Hermes 3 70B Instructnousresearch

Auto-discovered from OpenRouter (nousresearch/hermes-3-llama-3.1-70b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.70

Output /1M$0.70

View Nous: Hermes 3 70B Instruct Specs & Benchmarks Compare vs All

407Nous: Hermes 3 405B Instructnousresearch

Auto-discovered from OpenRouter (nousresearch/hermes-3-llama-3.1-405b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.0

Output /1M$1.0

View Nous: Hermes 3 405B Instruct Specs & Benchmarks Compare vs All

408Sao10K: Llama 3 8B Lunarissao10k

Auto-discovered from OpenRouter (sao10k/l3-lunaris-8b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.040

Output /1M$0.050

View Sao10K: Llama 3 8B Lunaris Specs & Benchmarks Compare vs All

409OpenAI: GPT-4o (2024-08-06)OpenAI

Auto-discovered from OpenRouter (openai/gpt-4o-2024-08-06). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.5

Output /1M$10

View OpenAI: GPT-4o (2024-08-06) Specs & Benchmarks Compare vs All

410Meta: Llama 3.1 8B InstructMeta

Auto-discovered from OpenRouter (meta-llama/llama-3.1-8b-instruct). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.050

Output /1M$0.080

View Meta: Llama 3.1 8B Instruct Specs & Benchmarks Compare vs All

411Mistral: Mistral NemoMistral

Auto-discovered from OpenRouter (mistralai/mistral-nemo). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.019

Output /1M$0.030

View Mistral: Mistral Nemo Specs & Benchmarks Compare vs All

412OpenAI: GPT-4o-mini (2024-07-18)OpenAI

Auto-discovered from OpenRouter (openai/gpt-4o-mini-2024-07-18). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.15

Output /1M$0.60

View OpenAI: GPT-4o-mini (2024-07-18) Specs & Benchmarks Compare vs All

413OpenAI: GPT-4o-mini (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-4o-mini:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.075

Output /1M$0.30

View OpenAI: GPT-4o-mini (batch) Specs & Benchmarks Compare vs All

414Google: Gemma 2 27BGoogle

Auto-discovered from OpenRouter (google/gemma-2-27b-it). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.65

Output /1M$0.65

View Google: Gemma 2 27B Specs & Benchmarks Compare vs All

415OpenAI: GPT-4o (2024-05-13)OpenAI

Auto-discovered from OpenRouter (openai/gpt-4o-2024-05-13). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$5.0

Output /1M$15

View OpenAI: GPT-4o (2024-05-13) Specs & Benchmarks Compare vs All

416OpenAI: GPT-4o (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-4o:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.3

Output /1M$5.0

View OpenAI: GPT-4o (batch) Specs & Benchmarks Compare vs All

417Mistral: Mixtral 8x22B InstructMistral

Auto-discovered from OpenRouter (mistralai/mixtral-8x22b-instruct). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$2.0

Output /1M$6.0

View Mistral: Mixtral 8x22B Instruct Specs & Benchmarks Compare vs All

418WizardLM-2 8x22Bmicrosoft

Auto-discovered from OpenRouter (microsoft/wizardlm-2-8x22b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.62

Output /1M$0.62

View WizardLM-2 8x22B Specs & Benchmarks Compare vs All

419OpenAI: GPT-4 Turbo (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-4-turbo:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$5.0

Output /1M$15

View OpenAI: GPT-4 Turbo (batch) Specs & Benchmarks Compare vs All

420Anthropic: Claude 3 HaikuAnthropic

Auto-discovered from OpenRouter (anthropic/claude-3-haiku). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.25

Output /1M$1.3

View Anthropic: Claude 3 Haiku Specs & Benchmarks Compare vs All

421OpenAI: GPT-3.5 Turbo (older v0613)OpenAI

Auto-discovered from OpenRouter (openai/gpt-3.5-turbo-0613). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.0

Output /1M$2.0

View OpenAI: GPT-3.5 Turbo (older v0613) Specs & Benchmarks Compare vs All

422OpenAI: GPT-4 Turbo PreviewOpenAI

Auto-discovered from OpenRouter (openai/gpt-4-turbo-preview). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$10

Output /1M$30

View OpenAI: GPT-4 Turbo Preview Specs & Benchmarks Compare vs All

423Auto Routeropenrouter

Auto-discovered from OpenRouter (openrouter/auto). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M-$1.0M

Output /1M-$1.0M

View Auto Router Specs & Benchmarks Compare vs All

424OpenAI: GPT-3.5 Turbo InstructOpenAI

Auto-discovered from OpenRouter (openai/gpt-3.5-turbo-instruct). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$1.5

Output /1M$2.0

View OpenAI: GPT-3.5 Turbo Instruct Specs & Benchmarks Compare vs All

425OpenAI: GPT-3.5 Turbo 16kOpenAI

Auto-discovered from OpenRouter (openai/gpt-3.5-turbo-16k). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$3.0

Output /1M$4.0

View OpenAI: GPT-3.5 Turbo 16k Specs & Benchmarks Compare vs All

426Mancer: Weaver (alpha)mancer

Auto-discovered from OpenRouter (mancer/weaver). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.50

Output /1M$0.75

View Mancer: Weaver (alpha) Specs & Benchmarks Compare vs All

427ReMM SLERP 13Bundi95

Auto-discovered from OpenRouter (undi95/remm-slerp-l2-13b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.45

Output /1M$0.65

View ReMM SLERP 13B Specs & Benchmarks Compare vs All

428MythoMax 13Bgryphe

Auto-discovered from OpenRouter (gryphe/mythomax-l2-13b). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.060

Output /1M$0.060

View MythoMax 13B Specs & Benchmarks Compare vs All

429OpenAI: GPT-3.5 TurboOpenAI

Auto-discovered from OpenRouter (openai/gpt-3.5-turbo). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.50

Output /1M$1.5

View OpenAI: GPT-3.5 Turbo Specs & Benchmarks Compare vs All

430OpenAI: GPT-3.5 Turbo (batch)OpenAI

Auto-discovered from OpenRouter (openai/gpt-3.5-turbo:batch). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$0.25

Output /1M$0.75

View OpenAI: GPT-3.5 Turbo (batch) Specs & Benchmarks Compare vs All

431OpenAI: GPT-4OpenAI

Auto-discovered from OpenRouter (openai/gpt-4). Preview until a second source matches.

Elo (Votes)—

SWE-bench (Code)—

Input /1M$30

Output /1M$60

View OpenAI: GPT-4 Specs & Benchmarks Compare vs All