Loading timeline…
Loading timeline…
Models · Research · Prices · Benchmarks · Providers · Hardware · Frameworks · Companies. Dots are events sized by importance; drag on the lanes to zoom the list to a range. Everything links to its entity and to the source that stated it.
1,000 events · first 1,000
1,000 events loaded · every dot is one event; hover for its summary
OpenRouter changed pricing for Kimi K2 Thinking: $0.6 in / $2.5 out per 1M tokens → $0.6 in / $2.5 out per 1M tokens
OpenRouter changed pricing for DeepSeek V4 Pro 0423: $0.809274 in / $1.61855 out per 1M tokens → $0.799182 in / $1.59836 out per 1M tokens
OpenRouter changed pricing for Inkling: $1 in / $4.05 out per 1M tokens → $1 in / $4.05 out per 1M tokens
gpt-3.5-turbo: openrouter listed at changed from 2024-01-25 to 2023-05-28
gpt-3.5-turbo: supported parameters changed from ["frequency_penalty", "logit_bias", "logprobs", "max_comp… to ["frequency_penalty", "logit_bias", "logprobs", "max_toke…
gpt-3.5-turbo: max output tokens changed from 3685 to 4096
gpt-3.5-turbo: context length changed from 4095 to 16385
gpt-3.5-turbo: openrouter id changed from openai/gpt-3.5-turbo-0613 to openai/gpt-3.5-turbo
o3-mini: supported parameters changed from ["include_reasoning", "max_tokens", "reasoning", "reasoni… to ["include_reasoning", "max_tokens", "reasoning", "respons…
o3-mini: openrouter id changed from openai/o3-mini-high to openai/o3-mini
o3-mini: openrouter id changed from openai/o3-mini to openai/o3-mini-high
o4-mini: openrouter id changed from openai/o4-mini-high to openai/o4-mini
gpt-5-nano: reasoning changed from false to true
gpt-5-mini: reasoning changed from false to true
Kimi K2 Thinking: max output tokens changed from 100352 to 235929
gpt-5.2: reasoning changed from false to true
gpt-5.4: reasoning changed from false to true
Claude Sonnet 5: reasoning changed from false to true
Inkling: max output tokens changed from 32768 to 471859
Grok Build 0.1: modalities changed from ["document", "image", "text"] to ["image", "text"]
Grok 4.20: modalities changed from ["document", "image", "text"] to ["image", "text"]
Grok 4.20 Multi-Agent: modalities changed from ["document", "image", "text"] to ["image", "text"]
Grok 4.6: modalities changed from ["document", "image", "text"] to ["image", "text"]
Grok 4.3: modalities changed from ["document", "image", "text"] to ["image", "text"]
Grok 4.5: modalities changed from ["document", "image", "text"] to ["image", "text"]
OpenRouter lists gpt-4 at $30 in / $60 out per 1M tokens
OpenRouter lists gpt-3.5-turbo at $0.25 in / $0.75 out per 1M tokens
OpenRouter lists gpt-3.5-turbo at $0.5 in / $1.5 out per 1M tokens
OpenRouter lists gpt-3.5-turbo-16k at $3 in / $4 out per 1M tokens
OpenRouter lists gpt-3.5-turbo-instruct at $1.5 in / $2 out per 1M tokens
OpenRouter lists GPT-4 Turbo Preview at $10 in / $30 out per 1M tokens
OpenRouter lists gpt-3.5-turbo at $1 in / $2 out per 1M tokens
OpenRouter lists Mistral Large at $2 in / $6 out per 1M tokens
OpenRouter lists Claude 3 Haiku at $0.25 in / $1.25 out per 1M tokens
OpenRouter lists gpt-4-turbo at $5 in / $15 out per 1M tokens
OpenRouter lists gpt-4-turbo at $10 in / $30 out per 1M tokens
OpenRouter lists Mixtral 8x22B Instruct at $2 in / $6 out per 1M tokens
OpenRouter lists gpt-4o at $1.25 in / $5 out per 1M tokens
OpenRouter lists GPT-4o (2024-05-13) at $5 in / $15 out per 1M tokens
OpenRouter lists gpt-4o at $2.5 in / $10 out per 1M tokens
OpenRouter lists Gemma 2 27B at $0.65 in / $0.65 out per 1M tokens
OpenRouter lists gpt-4o-mini at $0.075 in / $0.3 out per 1M tokens
OpenRouter lists GPT-4o-mini (2024-07-18) at $0.15 in / $0.6 out per 1M tokens
OpenRouter lists gpt-4o-mini at $0.15 in / $0.6 out per 1M tokens
OpenRouter lists Mistral Nemo at $0.019 in / $0.03 out per 1M tokens
OpenRouter lists GPT-4o (2024-08-06) at $2.5 in / $10 out per 1M tokens
OpenRouter lists command-r-plus-08-2024 at $2.5 in / $10 out per 1M tokens
OpenRouter lists command-r-08-2024 at $0.15 in / $0.6 out per 1M tokens
OpenRouter lists Mistral Large 2.0 at $2 in / $6 out per 1M tokens
OpenRouter lists GPT-4o (2024-11-20) at $2.5 in / $10 out per 1M tokens
OpenRouter lists command-r7b-12-2024 at $0.0375 in / $0.15 out per 1M tokens
OpenRouter lists DeepSeek V3 at $0.2574 in / $1.0287 out per 1M tokens
OpenRouter lists MiniMax-01 at $0.2 in / $1.1 out per 1M tokens
OpenRouter lists R1 Distill Llama 70B at $0.8 in / $0.8 out per 1M tokens
OpenRouter lists Sonar at $1 in / $1 out per 1M tokens
OpenRouter lists Mistral Small 3 at $0.05 in / $0.08 out per 1M tokens
OpenRouter lists o3-mini at $0.55 in / $2.2 out per 1M tokens
OpenRouter lists o3-mini at $1.1 in / $4.4 out per 1M tokens
OpenRouter lists o3-mini at $1.1 in / $4.4 out per 1M tokens
OpenRouter lists Mistral Saba at $0.2 in / $0.6 out per 1M tokens
OpenRouter lists Sonar Deep Research at $2 in / $8 out per 1M tokens
OpenRouter lists Sonar Pro at $3 in / $15 out per 1M tokens
OpenRouter lists Sonar Reasoning Pro at $2 in / $8 out per 1M tokens
OpenRouter lists Gemma 3 27B at $0.08 in / $0.45 out per 1M tokens
OpenRouter lists Command A at $2.5 in / $10 out per 1M tokens
OpenRouter lists Gemma 3 12B at $0.05 in / $0.15 out per 1M tokens
OpenRouter lists Gemma 3 4B at $0.05 in / $0.1 out per 1M tokens
OpenRouter lists Mistral Small 3.1 24B at $0.351 in / $0.555 out per 1M tokens
OpenRouter lists o1-pro at $150 in / $600 out per 1M tokens
OpenRouter lists DeepSeek V3 0324 at $0.25 in / $1 out per 1M tokens
OpenRouter lists gpt-4.1-nano at $0.05 in / $0.2 out per 1M tokens
OpenRouter lists gpt-4.1-nano at $0.1 in / $0.4 out per 1M tokens
OpenRouter lists gpt-4.1-mini at $0.2 in / $0.8 out per 1M tokens
OpenRouter lists gpt-4.1-mini at $0.4 in / $1.6 out per 1M tokens
OpenRouter lists gpt-4.1 at $1 in / $4 out per 1M tokens
OpenRouter lists gpt-4.1 at $2 in / $8 out per 1M tokens
OpenRouter lists o4-mini at $0.55 in / $2.2 out per 1M tokens
OpenRouter lists o4-mini at $1.1 in / $4.4 out per 1M tokens
OpenRouter lists o4-mini at $1.1 in / $4.4 out per 1M tokens
OpenRouter lists Gemini 2.5 Pro Preview 05-06 at $1.25 in / $10 out per 1M tokens
OpenRouter lists Mistral Medium 3 at $0.4 in / $2 out per 1M tokens
OpenRouter lists Claude Sonnet 4 at $3 in / $15 out per 1M tokens
OpenRouter lists Claude Opus 4 at $15 in / $75 out per 1M tokens
OpenRouter lists R1 0528 at $0.5 in / $2.15 out per 1M tokens
OpenRouter lists Gemini 2.5 Pro Preview 06-05 at $1.25 in / $10 out per 1M tokens
OpenRouter lists o3-pro at $20 in / $80 out per 1M tokens
OpenRouter lists Gemini 2.5 Pro at $0.625 in / $5 out per 1M tokens
OpenRouter lists Gemini 2.5 Pro at $1.25 in / $10 out per 1M tokens
OpenRouter lists Gemini 2.5 Flash at $0.15 in / $1.25 out per 1M tokens
OpenRouter lists Gemini 2.5 Flash at $0.3 in / $2.5 out per 1M tokens
OpenRouter lists MiniMax M1 at $0.55 in / $2.2 out per 1M tokens
OpenRouter lists Mistral Small 3.2 24B at $0.075 in / $0.2 out per 1M tokens
OpenRouter lists Kimi K2 0711 at $0.57 in / $2.3 out per 1M tokens
OpenRouter lists Gemini 2.5 Flash-Lite at $0.05 in / $0.2 out per 1M tokens
OpenRouter lists Gemini 2.5 Flash-Lite at $0.1 in / $0.4 out per 1M tokens
OpenRouter lists GLM 4.5 Air at $0.13 in / $0.85 out per 1M tokens
OpenRouter lists GLM 4.5 at $0.6 in / $2.2 out per 1M tokens
OpenRouter lists Codestral 2508 at $0.15 in / $0.45 out per 1M tokens
OpenRouter lists Codestral 2508 at $0.3 in / $0.9 out per 1M tokens
OpenRouter lists Claude Opus 4.1 at $7.5 in / $37.5 out per 1M tokens
OpenRouter lists Claude Opus 4.1 at $15 in / $75 out per 1M tokens
OpenRouter lists gpt-oss-20b at $0.05 in / $0.2 out per 1M tokens
OpenRouter lists gpt-oss-20b at $0.03 in / $0.13 out per 1M tokens
OpenRouter lists gpt-oss-120b at $0.15 in / $0.6 out per 1M tokens
OpenRouter lists gpt-oss-120b at $0.037 in / $0.17 out per 1M tokens
OpenRouter lists gpt-5-nano at $0.025 in / $0.2 out per 1M tokens
OpenRouter lists gpt-5-nano at $0.05 in / $0.4 out per 1M tokens
OpenRouter lists gpt-5-mini at $0.125 in / $1 out per 1M tokens
OpenRouter lists gpt-5-mini at $0.25 in / $2 out per 1M tokens
OpenRouter lists gpt-5 at $0.625 in / $5 out per 1M tokens
OpenRouter lists gpt-5 at $1.25 in / $10 out per 1M tokens
OpenRouter lists GLM 4.5V at $0.6 in / $1.8 out per 1M tokens
OpenRouter lists Mistral Medium 3.1 at $0.2 in / $1 out per 1M tokens
OpenRouter lists Mistral Medium 3.1 at $0.4 in / $2 out per 1M tokens
OpenRouter lists DeepSeek V3.1 at $0.25 in / $0.95 out per 1M tokens
OpenRouter lists Kimi K2 0905 at $0.6 in / $2.5 out per 1M tokens
OpenRouter lists DeepSeek V3.1 Terminus at $0.27 in / $1 out per 1M tokens
OpenRouter lists DeepSeek V3.2 Exp at $0.27 in / $0.41 out per 1M tokens
OpenRouter lists Claude Sonnet 4.5 at $1.5 in / $7.5 out per 1M tokens
OpenRouter lists Claude Sonnet 4.5 at $3 in / $15 out per 1M tokens
OpenRouter lists GLM 4.6 at $0.43 in / $1.75 out per 1M tokens
OpenRouter lists gpt-5-pro at $7.5 in / $60 out per 1M tokens
OpenRouter lists gpt-5-pro at $15 in / $120 out per 1M tokens
OpenRouter lists Gemini 2.5 Flash Image (Nano Banana) at $0.3 in / $2.5 out per 1M tokens
OpenRouter lists GPT-5 Image at $10 in / $10 out per 1M tokens
OpenRouter lists Claude Haiku 4.5 at $0.5 in / $2.5 out per 1M tokens
OpenRouter lists Claude Haiku 4.5 at $1 in / $5 out per 1M tokens
OpenRouter lists GPT-5 Image Mini at $2.5 in / $2 out per 1M tokens
OpenRouter lists MiniMax M2 at $0.255 in / $1.02 out per 1M tokens
OpenRouter lists gpt-oss-safeguard-20b at $0.075 in / $0.3 out per 1M tokens
OpenRouter lists Voxtral Small 24B 2507 at $0.1 in / $0.3 out per 1M tokens
OpenRouter lists Sonar Pro Search at $3 in / $15 out per 1M tokens
OpenRouter lists Kimi K2 Thinking at $0.6 in / $2.5 out per 1M tokens
OpenRouter lists GPT-5.1-Codex Mini at $0.25 in / $2 out per 1M tokens
OpenRouter lists GPT-5.1-Codex at $1.25 in / $10 out per 1M tokens
OpenRouter lists gpt-5.1 at $0.625 in / $5 out per 1M tokens
OpenRouter lists gpt-5.1 at $1.25 in / $10 out per 1M tokens
OpenRouter lists Nano Banana Pro (Gemini 3 Pro Image Preview) at $2 in / $12 out per 1M tokens
OpenRouter lists Claude Opus 4.5 at $2.5 in / $12.5 out per 1M tokens
OpenRouter lists Claude Opus 4.5 at $5 in / $25 out per 1M tokens
OpenRouter lists DeepSeek V3.2 at $0.269 in / $0.4 out per 1M tokens
OpenRouter lists Mistral Large 3 2512 at $0.25 in / $0.75 out per 1M tokens
OpenRouter lists Mistral Large 3 2512 at $0.5 in / $1.5 out per 1M tokens
OpenRouter lists Ministral 3 3B 2512 at $0.1 in / $0.1 out per 1M tokens
OpenRouter lists Ministral 3 8B 2512 at $0.075 in / $0.075 out per 1M tokens
OpenRouter lists Ministral 3 8B 2512 at $0.15 in / $0.15 out per 1M tokens
OpenRouter lists Ministral 3 14B 2512 at $0.2 in / $0.2 out per 1M tokens
OpenRouter lists GPT-5.1-Codex-Max at $1.25 in / $10 out per 1M tokens
OpenRouter lists GLM 4.6V at $0.3 in / $0.9 out per 1M tokens
OpenRouter lists Devstral 2 at $0.4 in / $2 out per 1M tokens
OpenRouter lists gpt-5.2 at $0.875 in / $7 out per 1M tokens
OpenRouter lists gpt-5.2 at $1.75 in / $14 out per 1M tokens
OpenRouter lists gpt-5.2-pro at $10.5 in / $84 out per 1M tokens
OpenRouter lists gpt-5.2-pro at $21 in / $168 out per 1M tokens
OpenRouter lists GPT-5.2 Chat at $1.75 in / $14 out per 1M tokens
OpenRouter lists Nemotron 3 Nano 30B A3B at $0.05 in / $0.2 out per 1M tokens
OpenRouter lists Gemini 3 Flash Preview at $0.25 in / $1.5 out per 1M tokens
OpenRouter lists Gemini 3 Flash Preview at $0.5 in / $3 out per 1M tokens
OpenRouter lists GLM 4.7 at $0.4 in / $1.75 out per 1M tokens
OpenRouter lists MiniMax M2.1 at $0.3 in / $1.2 out per 1M tokens
OpenRouter lists GPT-5.2-Codex at $1.75 in / $14 out per 1M tokens
OpenRouter lists GLM 4.7 Flash at $0.0605 in / $0.4 out per 1M tokens
OpenRouter lists gpt-audio-mini at $0.6 in / $2.4 out per 1M tokens
OpenRouter lists gpt-audio at $2.5 in / $10 out per 1M tokens
OpenRouter lists MiniMax M2-her at $0.3 in / $1.2 out per 1M tokens
OpenRouter lists Kimi K2.5 at $0.45 in / $2.25 out per 1M tokens
OpenRouter lists Claude Opus 4.6 at $2.5 in / $12.5 out per 1M tokens
OpenRouter lists Claude Opus 4.6 at $5 in / $25 out per 1M tokens
OpenRouter lists GLM 5 at $0.6 in / $1.92 out per 1M tokens
OpenRouter lists MiniMax M2.5 at $0.3 in / $1.2 out per 1M tokens
OpenRouter lists Claude Sonnet 4.6 at $1.5 in / $7.5 out per 1M tokens
OpenRouter lists Claude Sonnet 4.6 at $3 in / $15 out per 1M tokens
OpenRouter lists Gemini 3.1 Pro Preview at $1 in / $6 out per 1M tokens
OpenRouter lists Gemini 3.1 Pro Preview at $2 in / $12 out per 1M tokens
OpenRouter lists gpt-5.3-codex at $1.75 in / $14 out per 1M tokens
OpenRouter lists Gemini 3.1 Pro Preview Custom Tools at $2 in / $12 out per 1M tokens
OpenRouter lists Nano Banana 2 (Gemini 3.1 Flash Image Preview) at $0.5 in / $3 out per 1M tokens
OpenRouter lists Gemini 3.1 Flash-Lite Preview at $0.25 in / $1.5 out per 1M tokens
OpenRouter lists gpt-5.4 at $1.25 in / $7.5 out per 1M tokens
OpenRouter lists gpt-5.4 at $2.5 in / $15 out per 1M tokens
OpenRouter lists gpt-5.4-pro at $15 in / $90 out per 1M tokens
OpenRouter lists gpt-5.4-pro at $30 in / $180 out per 1M tokens
OpenRouter lists Nemotron 3 Super at $0 in / $0 out per 1M tokens
OpenRouter lists Nemotron 3 Super at $0.085 in / $0.4 out per 1M tokens
OpenRouter lists GLM 5 Turbo at $1.2 in / $4 out per 1M tokens
OpenRouter lists Mistral Small 4 at $0.075 in / $0.3 out per 1M tokens
OpenRouter lists Mistral Small 4 at $0.15 in / $0.6 out per 1M tokens
OpenRouter lists gpt-5.4-mini at $0.375 in / $2.25 out per 1M tokens
OpenRouter lists gpt-5.4-mini at $0.75 in / $4.5 out per 1M tokens
OpenRouter lists gpt-5.4-nano at $0.1 in / $0.625 out per 1M tokens
OpenRouter lists gpt-5.4-nano at $0.2 in / $1.25 out per 1M tokens
OpenRouter lists MiniMax M2.7 at $0.3 in / $1.2 out per 1M tokens
OpenRouter lists Lyria 3 at $0 in / $0 out per 1M tokens
OpenRouter lists Lyria 3 Pro Preview at $0 in / $0 out per 1M tokens
OpenRouter lists Grok 4.20 at $1.25 in / $2.5 out per 1M tokens
OpenRouter lists Grok 4.20 Multi-Agent at $1.25 in / $2.5 out per 1M tokens
OpenRouter lists GLM 5V Turbo at $1.2 in / $4 out per 1M tokens
OpenRouter lists Gemma 4 31B at $0 in / $0 out per 1M tokens
OpenRouter lists Gemma 4 31B at $0.39 in / $0.97 out per 1M tokens
OpenRouter lists Gemma 4 31B at $0.09 in / $0.34 out per 1M tokens
OpenRouter lists Gemma 4 26B A4B at $0 in / $0 out per 1M tokens
OpenRouter lists Gemma 4 26B A4B at $0.042 in / $0.22 out per 1M tokens
OpenRouter lists GLM 5.1 at $0.966 in / $3.036 out per 1M tokens
OpenRouter lists Claude Opus 4.7 at $2.5 in / $12.5 out per 1M tokens
OpenRouter lists Claude Opus 4.7 at $5 in / $25 out per 1M tokens
OpenRouter lists Kimi K2.6 at $0.95 in / $4 out per 1M tokens
OpenRouter lists GPT-5.4 Image 2 at $8 in / $15 out per 1M tokens
OpenRouter lists DeepSeek V4 Flash 0423 at $0.06678 in / $0.13356 out per 1M tokens
OpenRouter lists DeepSeek V4 Pro 0423 at $0.809274 in / $1.61855 out per 1M tokens
OpenRouter lists gpt-5.5 at $2.5 in / $15 out per 1M tokens
OpenRouter lists gpt-5.5 at $5 in / $30 out per 1M tokens
OpenRouter lists gpt-5.5-pro at $15 in / $90 out per 1M tokens
OpenRouter lists gpt-5.5-pro at $30 in / $180 out per 1M tokens
OpenRouter lists Nemotron 3 Nano Omni (free) at $0 in / $0 out per 1M tokens
OpenRouter lists Mistral Medium 3.5 at $0.75 in / $3.75 out per 1M tokens
OpenRouter lists Mistral Medium 3.5 at $1.5 in / $7.5 out per 1M tokens
OpenRouter lists Grok 4.3 at $1 in / $2 out per 1M tokens
OpenRouter lists Grok 4.3 at $1.25 in / $2.5 out per 1M tokens
OpenRouter lists GPT Chat Latest at $5 in / $30 out per 1M tokens
OpenRouter lists Gemini 3.1 Flash-Lite at $0.125 in / $0.75 out per 1M tokens
OpenRouter lists Gemini 3.1 Flash-Lite at $0.25 in / $1.5 out per 1M tokens
OpenRouter lists Gemini 3.5 Flash at $0.75 in / $4.5 out per 1M tokens
OpenRouter lists Gemini 3.5 Flash at $1.5 in / $9 out per 1M tokens
OpenRouter lists Grok Build 0.1 at $1 in / $2 out per 1M tokens
OpenRouter lists Claude Opus 4.8 at $2.5 in / $12.5 out per 1M tokens
OpenRouter lists Claude Opus 4.8 at $5 in / $25 out per 1M tokens
OpenRouter lists MiniMax-M3 at $0.3 in / $1.2 out per 1M tokens
OpenRouter lists MiniMax-M3 at $0.3 in / $1.2 out per 1M tokens
OpenRouter lists Nemotron 3 Ultra at $0 in / $0 out per 1M tokens
OpenRouter lists Nemotron 3 Ultra at $0.625 in / $3.125 out per 1M tokens
OpenRouter lists Nemotron 3.5 Content Safety at $0 in / $0 out per 1M tokens
OpenRouter lists Nemotron 3.5 Content Safety at $0.2 in / $0.2 out per 1M tokens
OpenRouter lists Claude Fable 5 at $5 in / $25 out per 1M tokens
OpenRouter lists Claude Fable 5 at $10 in / $50 out per 1M tokens
OpenRouter lists Kimi K2.7 Code at $0.71 in / $3.5 out per 1M tokens
OpenRouter lists Z.ai GLM 5.2 at $0.7 in / $2.2 out per 1M tokens
OpenRouter lists Z.ai GLM 5.2 at $0.6 in / $2 out per 1M tokens
OpenRouter lists North Mini Code (free) at $0 in / $0 out per 1M tokens
OpenRouter lists Gemini 3 Pro Image (Nano Banana Pro) at $2 in / $12 out per 1M tokens
OpenRouter lists Gemini 3.1 Flash Image (Nano Banana 2) at $0.5 in / $3 out per 1M tokens
OpenRouter lists Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) at $0.25 in / $1.5 out per 1M tokens
OpenRouter lists Claude Sonnet 5 at $1 in / $5 out per 1M tokens
OpenRouter lists Claude Sonnet 5 at $2 in / $10 out per 1M tokens
OpenRouter lists Grok 4.5 at $2 in / $6 out per 1M tokens
OpenRouter lists gpt-5.6-sol at $1 in / $5 out per 1M tokens
OpenRouter lists gpt-5.6-sol at $2 in / $10 out per 1M tokens
OpenRouter lists GPT-5.6 Sol Pro at $1 in / $5 out per 1M tokens
OpenRouter lists GPT-5.6 Sol Pro at $2 in / $10 out per 1M tokens
OpenRouter lists gpt-5.6-terra at $1 in / $6 out per 1M tokens
OpenRouter lists gpt-5.6-terra at $2 in / $12 out per 1M tokens
OpenRouter lists GPT-5.6 Terra Pro at $1 in / $6 out per 1M tokens
OpenRouter lists GPT-5.6 Terra Pro at $2 in / $12 out per 1M tokens
OpenRouter lists gpt-5.6-luna at $0.1 in / $0.6 out per 1M tokens
OpenRouter lists gpt-5.6-luna at $0.2 in / $1.2 out per 1M tokens
OpenRouter lists GPT-5.6 Luna Pro at $0.1 in / $0.6 out per 1M tokens
OpenRouter lists GPT-5.6 Luna Pro at $0.2 in / $1.2 out per 1M tokens
OpenRouter lists Kimi K3 at $3 in / $15 out per 1M tokens
OpenRouter lists Kimi K3 at $2.30273 in / $11.5502 out per 1M tokens
OpenRouter lists Gemini 3.5 Flash-Lite at $0.15 in / $1.25 out per 1M tokens
OpenRouter lists Gemini 3.5 Flash-Lite at $0.3 in / $2.5 out per 1M tokens
OpenRouter lists Gemini 3.6 Flash at $0.375 in / $1.875 out per 1M tokens
OpenRouter lists Gemini 3.6 Flash at $0.75 in / $3.75 out per 1M tokens
OpenRouter lists Claude Opus 5 at $2.5 in / $12.5 out per 1M tokens
OpenRouter lists Claude Opus 5 at $5 in / $25 out per 1M tokens
OpenRouter lists DeepSeek V4 Flash (0731) at $0.11 in / $0.33 out per 1M tokens
OpenRouter lists DeepSeek V4 Flash (0731) at $0.04 in / $0.08 out per 1M tokens
OpenRouter lists NVIDIA Nemotron 3.5 Lightning 30B A3B at $0 in / $0 out per 1M tokens
OpenRouter lists NVIDIA Nemotron 3.5 Lightning 30B A3B at $0.08 in / $0.2 out per 1M tokens
OpenRouter lists Grok 4.6 at $2 in / $6 out per 1M tokens
OpenRouter lists DeepSeek-V4-Pro-0813 at $0.66 in / $1.98 out per 1M tokens
OpenRouter lists DeepSeek-V4-Pro-0813 at $0.57816 in / $1.73448 out per 1M tokens
OpenRouter lists Gemini 3.7 Flash at $0.375 in / $1.875 out per 1M tokens
OpenRouter lists Gemini 3.7 Flash at $0.75 in / $3.75 out per 1M tokens
OpenRouter lists GLM 5.3 at $0.7 in / $2.2 out per 1M tokens
OpenRouter lists GLM 5.3 at $1.4 in / $4.4 out per 1M tokens
OpenRouter lists DeepSeek V4 Flash Vision Exp at $0.11 in / $0.33 out per 1M tokens
OpenRouter lists DeepSeek V4 Flash Vision Exp at $0.22 in / $0.66 out per 1M tokens
OpenRouter lists GLM 5.3 Flash at $0.075 in / $0.25 out per 1M tokens
OpenRouter lists GLM 5.3 Flash at $0.15 in / $0.5 out per 1M tokens
OpenRouter lists Claude Fable 5.1 at $5 in / $25 out per 1M tokens
OpenRouter lists Claude Fable 5.1 at $10 in / $50 out per 1M tokens
OpenRouter lists Gemini 3.8 Flash at $0.375 in / $1.875 out per 1M tokens
OpenRouter lists Gemini 3.8 Flash at $0.75 in / $3.75 out per 1M tokens
OpenRouter lists GPT-6 Astra Pro at $5 in / $25 out per 1M tokens
OpenRouter lists GPT-6 Astra Pro at $10 in / $50 out per 1M tokens
OpenRouter lists gpt-6-astra at $5 in / $25 out per 1M tokens
OpenRouter lists gpt-6-astra at $10 in / $50 out per 1M tokens
OpenRouter lists DeepSeek-V4.1-Flash at $0.15 in / $0.6 out per 1M tokens
Mistral Large: modalities changed from ["text"] to ["document", "text"]
Mistral Large: modalities input changed from ["text"] to ["document", "text"]
Mixtral 8x22B Instruct: modalities changed from ["text"] to ["document", "text"]
Mixtral 8x22B Instruct: modalities input changed from ["text"] to ["document", "text"]
GPT-4o (2024-05-13): modalities changed from ["image", "text"] to ["document", "image", "text"]
GPT-4o (2024-05-13): modalities input changed from ["image", "text"] to ["document", "image", "text"]
gpt-4o: modalities changed from ["image", "text"] to ["document", "image", "text"]
gpt-4o: modalities input changed from ["image", "text"] to ["document", "image", "text"]
GPT-4o-mini (2024-07-18): modalities changed from ["image", "text"] to ["document", "image", "text"]
GPT-4o-mini (2024-07-18): modalities input changed from ["image", "text"] to ["document", "image", "text"]
gpt-4o-mini: modalities changed from ["image", "text"] to ["document", "image", "text"]
gpt-4o-mini: modalities input changed from ["image", "text"] to ["document", "image", "text"]
Llama 3.1 8B Instruct: hf repo changed from meta-llama/Llama-3.1-8B-Instruct to meta-llama/Meta-Llama-3.1-8B-Instruct
Llama 3.1 70B Instruct: hf repo changed from meta-llama/Llama-3.1-70B-Instruct to meta-llama/Meta-Llama-3.1-70B-Instruct
GPT-4o (2024-08-06): modalities changed from ["image", "text"] to ["document", "image", "text"]
GPT-4o (2024-08-06): modalities input changed from ["image", "text"] to ["document", "image", "text"]
Qwen2.5 72B Instruct: context length changed from 131072 to 32768
Mistral Large 2.0: modalities changed from ["text"] to ["document", "text"]
Mistral Large 2.0: modalities input changed from ["text"] to ["document", "text"]
GPT-4o (2024-11-20): modalities changed from ["image", "text"] to ["document", "image", "text"]
GPT-4o (2024-11-20): modalities input changed from ["image", "text"] to ["document", "image", "text"]
o1: modalities changed from ["image", "text"] to ["document", "image", "text"]
o1: modalities input changed from ["image", "text"] to ["document", "image", "text"]
o3-mini: openrouter listed at changed from 2025-02-12 to 2025-01-31
o3-mini: openrouter listed at changed from 2025-01-31 to 2025-02-12
o3-mini: modalities changed from ["text"] to ["document", "text"]
o3-mini: modalities input changed from ["text"] to ["document", "text"]
Mistral Saba: modalities changed from ["text"] to ["document", "text"]
Mistral Saba: modalities input changed from ["text"] to ["document", "text"]
o1-pro: modalities changed from ["image", "text"] to ["document", "image", "text"]
o1-pro: modalities input changed from ["image", "text"] to ["document", "image", "text"]
gpt-4.1-nano: modalities changed from ["image", "text"] to ["document", "image", "text"]
gpt-4.1-nano: modalities input changed from ["image", "text"] to ["document", "image", "text"]
gpt-4.1-mini: modalities changed from ["image", "text"] to ["document", "image", "text"]
gpt-4.1-mini: modalities input changed from ["image", "text"] to ["document", "image", "text"]
gpt-4.1: modalities changed from ["image", "text"] to ["document", "image", "text"]
gpt-4.1: modalities input changed from ["image", "text"] to ["document", "image", "text"]
o4-mini: supported parameters changed from ["include_reasoning", "max_tokens", "reasoning", "reasoni… to ["include_reasoning", "max_tokens", "reasoning", "respons…
o3: modalities changed from ["image", "text"] to ["document", "image", "text"]
o3: modalities input changed from ["image", "text"] to ["document", "image", "text"]
o4-mini: supported parameters changed from ["include_reasoning", "max_tokens", "reasoning", "respons… to ["include_reasoning", "max_tokens", "reasoning", "reasoni…
o4-mini: modalities changed from ["image", "text"] to ["document", "image", "text"]
o4-mini: modalities input changed from ["image", "text"] to ["document", "image", "text"]
Gemini 2.5 Pro Preview 05-06: modalities changed from ["audio", "image", "text", "video"] to ["audio", "document", "image", "text", "video"]
Gemini 2.5 Pro Preview 05-06: modalities input changed from ["audio", "image", "text", "video"] to ["audio", "document", "image", "text", "video"]
Mistral Medium 3: modalities changed from ["image", "text"] to ["document", "image", "text"]
Mistral Medium 3: modalities input changed from ["image", "text"] to ["document", "image", "text"]
Claude Sonnet 4: modalities changed from ["image", "text"] to ["document", "image", "text"]
Claude Sonnet 4: modalities input changed from ["image", "text"] to ["document", "image", "text"]
Claude Opus 4: modalities changed from ["image", "text"] to ["document", "image", "text"]
Claude Opus 4: modalities input changed from ["image", "text"] to ["document", "image", "text"]
Gemini 2.5 Pro Preview 06-05: modalities changed from ["audio", "image", "text"] to ["audio", "document", "image", "text"]
Gemini 2.5 Pro Preview 06-05: modalities input changed from ["audio", "image", "text"] to ["audio", "document", "image", "text"]
o3-pro: modalities changed from ["image", "text"] to ["document", "image", "text"]
o3-pro: modalities input changed from ["image", "text"] to ["document", "image", "text"]
Codestral 2508: modalities changed from ["text"] to ["document", "text"]
Codestral 2508: modalities input changed from ["text"] to ["document", "text"]
Claude Opus 4.1: modalities changed from ["image", "text"] to ["document", "image", "text"]
Claude Opus 4.1: modalities input changed from ["image", "text"] to ["document", "image", "text"]
gpt-5-nano: modalities changed from ["image", "text"] to ["document", "image", "text"]
gpt-5-nano: modalities input changed from ["image", "text"] to ["document", "image", "text"]
gpt-5-mini: modalities changed from ["image", "text"] to ["document", "image", "text"]
gpt-5-mini: modalities input changed from ["image", "text"] to ["document", "image", "text"]
gpt-5: modalities changed from ["image", "text"] to ["document", "image", "text"]
gpt-5: modalities input changed from ["image", "text"] to ["document", "image", "text"]
GLM 4.5V: reasoning changed from false to true
Mistral Medium 3.1: modalities changed from ["image", "text"] to ["document", "image", "text"]
Mistral Medium 3.1: modalities input changed from ["image", "text"] to ["document", "image", "text"]
Qwen3 Max: openrouter listed at changed from 2026-02-09 to 2025-09-23
Qwen3 Max: supported parameters changed from ["frequency_penalty", "include_reasoning", "logprobs", "m… to ["frequency_penalty", "logprobs", "max_tokens", "presence…
Qwen3 Max: tokenizer changed from Qwen to Qwen3
Qwen3 Max: openrouter id changed from qwen/qwen3-max-thinking to qwen/qwen3-max
Claude Sonnet 4.5: modalities changed from ["image", "text"] to ["document", "image", "text"]
Claude Sonnet 4.5: modalities input changed from ["image", "text"] to ["document", "image", "text"]
gpt-5-pro: modalities changed from ["image", "text"] to ["document", "image", "text"]
gpt-5-pro: modalities input changed from ["image", "text"] to ["document", "image", "text"]
GPT-5 Image: modalities changed from ["image", "text"] to ["document", "image", "text"]
GPT-5 Image: modalities input changed from ["image", "text"] to ["document", "image", "text"]
GPT-5 Image Mini: modalities changed from ["image", "text"] to ["document", "image", "text"]
GPT-5 Image Mini: modalities input changed from ["image", "text"] to ["document", "image", "text"]
Voxtral Small 24B 2507: modalities changed from ["audio", "text"] to ["audio", "document", "text"]
Voxtral Small 24B 2507: modalities input changed from ["audio", "text"] to ["audio", "document", "text"]
gpt-5.1: reasoning changed from false to true
gpt-5.1: modalities changed from ["image", "text"] to ["document", "image", "text"]
gpt-5.1: modalities input changed from ["image", "text"] to ["document", "image", "text"]
Claude Opus 4.5: modalities changed from ["image", "text"] to ["document", "image", "text"]
Claude Opus 4.5: modalities input changed from ["image", "text"] to ["document", "image", "text"]
Mistral Large 3 2512: modalities changed from ["image", "text"] to ["document", "image", "text"]
Mistral Large 3 2512: modalities input changed from ["image", "text"] to ["document", "image", "text"]
Nova 2 Lite: modalities changed from ["image", "text", "video"] to ["document", "image", "text", "video"]
Nova 2 Lite: modalities input changed from ["image", "text", "video"] to ["document", "image", "text", "video"]
GLM 4.6V: reasoning changed from false to true
Devstral 2: modalities changed from ["text"] to ["document", "text"]
Devstral 2: modalities input changed from ["text"] to ["document", "text"]
gpt-5.2: modalities changed from ["image", "text"] to ["document", "image", "text"]
gpt-5.2: modalities input changed from ["image", "text"] to ["document", "image", "text"]
gpt-5.2-pro: modalities changed from ["image", "text"] to ["document", "image", "text"]
gpt-5.2-pro: modalities input changed from ["image", "text"] to ["document", "image", "text"]
GPT-5.2 Chat: modalities changed from ["image", "text"] to ["document", "image", "text"]
GPT-5.2 Chat: modalities input changed from ["image", "text"] to ["document", "image", "text"]
Claude Opus 4.6: modalities changed from ["image", "text"] to ["document", "image", "text"]
Claude Opus 4.6: modalities input changed from ["image", "text"] to ["document", "image", "text"]
Qwen3 Max: openrouter listed at changed from 2025-09-23 to 2026-02-09
Qwen3 Max: supported parameters changed from ["frequency_penalty", "logprobs", "max_tokens", "presence… to ["frequency_penalty", "include_reasoning", "logprobs", "m…
Qwen3 Max: tokenizer changed from Qwen3 to Qwen
Qwen3 Max: openrouter id changed from qwen/qwen3-max to qwen/qwen3-max-thinking
Claude Sonnet 4.6: modalities changed from ["image", "text"] to ["document", "image", "text"]
Claude Sonnet 4.6: modalities input changed from ["image", "text"] to ["document", "image", "text"]
gpt-5.3-codex: modalities changed from ["image", "text"] to ["document", "image", "text"]
gpt-5.3-codex: modalities input changed from ["image", "text"] to ["document", "image", "text"]
Gemini 3.1 Pro Preview Custom Tools: modalities changed from ["audio", "image", "text", "video"] to ["audio", "document", "image", "text", "video"]
Gemini 3.1 Pro Preview Custom Tools: modalities input changed from ["audio", "image", "text", "video"] to ["audio", "document", "image", "text", "video"]
gpt-5.4: modalities changed from ["image", "text"] to ["document", "image", "text"]
gpt-5.4: modalities input changed from ["image", "text"] to ["document", "image", "text"]
gpt-5.4-pro: modalities changed from ["image", "text"] to ["document", "image", "text"]
gpt-5.4-pro: modalities input changed from ["image", "text"] to ["document", "image", "text"]
Mistral Small 4: context length changed from 256000 to 262144
gpt-5.4-mini: reasoning changed from false to true
gpt-5.4-mini: modalities changed from ["image", "text"] to ["document", "image", "text"]
gpt-5.4-mini: modalities input changed from ["image", "text"] to ["document", "image", "text"]
gpt-5.4-nano: reasoning changed from false to true
gpt-5.4-nano: modalities changed from ["image", "text"] to ["document", "image", "text"]
gpt-5.4-nano: modalities input changed from ["image", "text"] to ["document", "image", "text"]
Grok 4.20: modalities changed from ["image", "text"] to ["document", "image", "text"]
Grok 4.20 Multi-Agent: modalities changed from ["image", "text"] to ["document", "image", "text"]
Gemma 4 31B: hf repo changed from google/gemma-4-31B to google/gemma-4-31B-it
Gemma 4 26B A4B: hf repo changed from google/gemma-4-26B-A4B to google/gemma-4-26B-A4B-it
Claude Opus 4.7: reasoning changed from false to true
Claude Opus 4.7: modalities changed from ["image", "text"] to ["document", "image", "text"]
Claude Opus 4.7: modalities input changed from ["image", "text"] to ["document", "image", "text"]
GPT-5.4 Image 2: modalities changed from ["image", "text"] to ["document", "image", "text"]
GPT-5.4 Image 2: modalities input changed from ["image", "text"] to ["document", "image", "text"]
gpt-5.5: modalities changed from ["image", "text"] to ["document", "image", "text"]
gpt-5.5: modalities input changed from ["image", "text"] to ["document", "image", "text"]
gpt-5.5-pro: modalities changed from ["image", "text"] to ["document", "image", "text"]
gpt-5.5-pro: modalities input changed from ["image", "text"] to ["document", "image", "text"]
Mistral Medium 3.5: modalities changed from ["image", "text"] to ["document", "image", "text"]
Mistral Medium 3.5: modalities input changed from ["image", "text"] to ["document", "image", "text"]
Grok 4.3: reasoning changed from false to true
Grok 4.3: modalities changed from ["image", "text"] to ["document", "image", "text"]
GPT Chat Latest: modalities changed from ["image", "text"] to ["document", "image", "text"]
GPT Chat Latest: modalities input changed from ["image", "text"] to ["document", "image", "text"]
Grok Build 0.1: modalities changed from ["image", "text"] to ["document", "image", "text"]
Claude Opus 4.8: modalities changed from ["image", "text"] to ["document", "image", "text"]
Claude Opus 4.8: modalities input changed from ["image", "text"] to ["document", "image", "text"]
MiniMax-M3: hf repo changed from MiniMaxAI/MiniMax-M3 to MiniMaxAI/Minimax-M3
Claude Fable 5: modalities changed from ["image", "text"] to ["document", "image", "text"]
Claude Fable 5: modalities input changed from ["image", "text"] to ["document", "image", "text"]
Z.ai GLM 5.2: reasoning changed from false to true
Z.ai GLM 5.2: context length changed from 1000000 to 1048576
Grok 4.5: modalities changed from ["image", "text"] to ["document", "image", "text"]
gpt-5.6-sol: context length changed from 1000000 to 1050000
GPT-5.6 Sol Pro: modalities changed from ["image", "text"] to ["document", "image", "text"]
GPT-5.6 Sol Pro: modalities input changed from ["image", "text"] to ["document", "image", "text"]
gpt-5.6-terra: context length changed from 1000000 to 1050000
GPT-5.6 Terra Pro: modalities changed from ["image", "text"] to ["document", "image", "text"]
GPT-5.6 Terra Pro: modalities input changed from ["image", "text"] to ["document", "image", "text"]
gpt-5.6-luna: context length changed from 1000000 to 1050000
GPT-5.6 Luna Pro: modalities changed from ["image", "text"] to ["document", "image", "text"]
GPT-5.6 Luna Pro: modalities input changed from ["image", "text"] to ["document", "image", "text"]
Muse Spark 1.1: modalities changed from ["audio", "image", "text", "video"] to ["audio", "document", "image", "text", "video"]
Muse Spark 1.1: modalities input changed from ["audio", "image", "text", "video"] to ["audio", "document", "image", "text", "video"]
Muse Spark 1.2: modalities changed from ["audio", "image", "text", "video"] to ["audio", "document", "image", "text", "video"]
Muse Spark 1.2: modalities input changed from ["audio", "image", "text", "video"] to ["audio", "document", "image", "text", "video"]
Sakana Namazu: modalities changed from ["image", "text"] to ["document", "image", "text"]
Sakana Namazu: modalities input changed from ["image", "text"] to ["document", "image", "text"]
Grok 4.6: modalities changed from ["image", "text"] to ["document", "image", "text"]
Muse Spark 1.2 Contributor: modalities changed from ["audio", "image", "text", "video"] to ["audio", "document", "image", "text", "video"]
Muse Spark 1.2 Contributor: modalities input changed from ["audio", "image", "text", "video"] to ["audio", "document", "image", "text", "video"]
Muse Spark 1.3: modalities changed from ["audio", "image", "text", "video"] to ["audio", "document", "image", "text", "video"]
Muse Spark 1.3: modalities input changed from ["audio", "image", "text", "video"] to ["audio", "document", "image", "text", "video"]
Muse Spark 1.3 Contributor: modalities changed from ["audio", "image", "text", "video"] to ["audio", "document", "image", "text", "video"]
Muse Spark 1.3 Contributor: modalities input changed from ["audio", "image", "text", "video"] to ["audio", "document", "image", "text", "video"]
GPT-6 Astra Pro: modalities changed from ["image", "text"] to ["document", "image", "text"]
GPT-6 Astra Pro: modalities input changed from ["image", "text"] to ["document", "image", "text"]
gpt-6-astra: context length changed from 1000000 to 1050000
Fugu Max: modalities changed from ["image", "text"] to ["document", "image", "text"]
Fugu Max: modalities input changed from ["image", "text"] to ["document", "image", "text"]
Fugu Ultra v2: modalities changed from ["image", "text"] to ["document", "image", "text"]
Fugu Ultra v2: modalities input changed from ["image", "text"] to ["document", "image", "text"]
North Small Translate: openness changed from restricted-weights to open-weights
phoenix: pypi release at changed from 2026-09-11T18:14:10+00:00 to 2026-09-12T04:32:27+00:00
phoenix: pypi version changed from 20.10.0 to 20.11.0
phoenix: kind changed from tool to observability
pydantic-ai: pypi release at changed from 2026-09-09T03:48:41+00:00 to 2026-09-12T01:05:27+00:00
pydantic-ai: pypi version changed from 2.42.0 to 2.43.0
pydantic-ai: kind changed from training-framework to agent-framework
crewAI: kind changed from training-framework to agent-framework
New model family: Mistral (Nous Research)
New model family: Claude 2.0 (Anthropic)
New model family: Claude 4.1 (Anthropic)
GLM 4.5V scores 6.82% on Terminal-Bench
GLM 4.5V scores 3.48% on Humanity's Last Exam
GLM 4.5V scores 57.27% on GPQA Diamond
GLM 4.5V scores 6.7 on Artificial Analysis Intelligence Index
Gemini 3.5 Flash scores 40.91% on Terminal-Bench
Gemini 3.5 Flash scores 78.65% on Terminal-Bench
Gemini 3.5 Flash scores 6.57% on Terminal-Bench
Gemini 3.5 Flash scores 95.32% on τ²-bench
Gemini 3.5 Flash scores 84.28% on MMMU-Pro
Gemini 3.5 Flash scores 76.33% on IFBench
Gemini 3.5 Flash scores 53.94% on SciCode
Gemini 3.5 Flash scores 42.68% on Humanity's Last Exam
Gemini 3.5 Flash scores 92.22% on GPQA Diamond
Gemini 3.5 Flash scores 32.98 on Artificial Analysis Intelligence Index
MiMo-V2.5-Pro scores 43.18% on Terminal-Bench
MiMo-V2.5-Pro scores 65.17% on Terminal-Bench
MiMo-V2.5-Pro scores 0% on Terminal-Bench
MiMo-V2.5-Pro scores 35.68% on Humanity's Last Exam
MiMo-V2.5-Pro scores 86.57% on GPQA Diamond
MiMo-V2.5-Pro scores 26.41 on Artificial Analysis Intelligence Index
jt-35b-flash scores 28.79% on Terminal-Bench
jt-35b-flash scores 99.12% on τ²-bench
jt-35b-flash scores 42.04% on IFBench
jt-35b-flash scores 6.44% on Humanity's Last Exam
jt-35b-flash scores 82.93% on GPQA Diamond
jt-35b-flash scores 18.66 on Artificial Analysis Intelligence Index
Mercury 2 scores 17.15% on Humanity's Last Exam
Mercury 2 scores 11.51 on Artificial Analysis Intelligence Index
qwen3-5-omni-plus scores 21.21% on Terminal-Bench
qwen3-5-omni-plus scores 88.3% on τ²-bench
qwen3-5-omni-plus scores 70.52% on MMMU-Pro
qwen3-5-omni-plus scores 51.16% on IFBench
qwen3-5-omni-plus scores 14.87% on Humanity's Last Exam
qwen3-5-omni-plus scores 82.63% on GPQA Diamond
qwen3-5-omni-plus scores 20.38 on Artificial Analysis Intelligence Index
nova-2-0-omni scores 4.55% on Terminal-Bench
nova-2-0-omni scores 80.41% on τ²-bench
nova-2-0-omni scores 61.91% on MMMU-Pro
nova-2-0-omni scores 66.19% on IFBench
nova-2-0-omni scores 6.95% on Humanity's Last Exam
nova-2-0-omni scores 75.96% on GPQA Diamond
nova-2-0-omni scores 13.65 on Artificial Analysis Intelligence Index
GPT-5.2-Codex scores 37.12% on Terminal-Bench
GPT-5.2-Codex scores 35.73% on Humanity's Last Exam
GPT-5.2-Codex scores 89.9% on GPQA Diamond
GPT-5.2-Codex scores 28.5 on Artificial Analysis Intelligence Index
Qwen3.5-122B-A10B scores 29.55% on Terminal-Bench
Qwen3.5-122B-A10B scores 47.19% on Terminal-Bench
Qwen3.5-122B-A10B scores 84.5% on τ²-bench
Qwen3.5-122B-A10B scores 70.29% on MMMU-Pro
Qwen3.5-122B-A10B scores 50.82% on IFBench
Qwen3.5-122B-A10B scores 15.94% on Humanity's Last Exam
Qwen3.5-122B-A10B scores 82.73% on GPQA Diamond
Qwen3.5-122B-A10B scores 17.75 on Artificial Analysis Intelligence Index
gemma-4-12B scores 11.36% on Terminal-Bench
gemma-4-12B scores 6.35% on Humanity's Last Exam
gemma-4-12B scores 9.38 on Artificial Analysis Intelligence Index
Gemini 3.5 Flash scores 46.21% on Terminal-Bench
Gemini 3.5 Flash scores 58.77% on τ²-bench
Gemini 3.5 Flash scores 80.12% on MMMU-Pro
Gemini 3.5 Flash scores 47.28% on IFBench
Gemini 3.5 Flash scores 24.1% on Humanity's Last Exam
Gemini 3.5 Flash scores 82.83% on GPQA Diamond
Gemini 3.5 Flash scores 23.85 on Artificial Analysis Intelligence Index
Claude Haiku 3.5 scores 2.27% on Terminal-Bench
Claude Haiku 3.5 scores 10.11% on Terminal-Bench
Claude Haiku 3.5 scores 24.56% on τ²-bench
Claude Haiku 3.5 scores 45.61% on MMMU-Pro
Claude Haiku 3.5 scores 42.79% on IFBench
Claude Haiku 3.5 scores 3.63% on Humanity's Last Exam
Claude Haiku 3.5 scores 40.81% on GPQA Diamond
Claude Haiku 3.5 scores 8.94 on Artificial Analysis Intelligence Index
gpt-3.5-turbo scores 29.7% on GPQA Diamond
gpt-3.5-turbo scores 5.49 on Artificial Analysis Intelligence Index
gemini-2.0-flash-thinking-exp-01-21 scores 6.35% on Humanity's Last Exam
gemini-2.0-flash-thinking-exp-01-21 scores 70.1% on GPQA Diamond
gemini-2.0-flash-thinking-exp-01-21 scores 9.42 on Artificial Analysis Intelligence Index
Qwen2.5 Coder 32B Instruct scores 3.51% on Humanity's Last Exam
Qwen2.5 Coder 32B Instruct scores 41.72% on GPQA Diamond
Qwen2.5 Coder 32B Instruct scores 6.74 on Artificial Analysis Intelligence Index
gemma-3-270m scores 3.61% on Humanity's Last Exam
gemma-3-270m scores 22.42% on GPQA Diamond
gemma-3-270m scores 5.12 on Artificial Analysis Intelligence Index
grok-4-20-0309 scores 40.91% on Terminal-Bench
grok-4-20-0309 scores 96.49% on τ²-bench
grok-4-20-0309 scores 73.18% on MMMU-Pro
grok-4-20-0309 scores 82.93% on IFBench
grok-4-20-0309 scores 32.39% on Humanity's Last Exam
grok-4-20-0309 scores 88.48% on GPQA Diamond
grok-4-20-0309 scores 25.22 on Artificial Analysis Intelligence Index
GPT-5.1-Codex scores 34.85% on Terminal-Bench
GPT-5.1-Codex scores 25.72% on Humanity's Last Exam
GPT-5.1-Codex scores 85.96% on GPQA Diamond
GPT-5.1-Codex scores 23.7 on Artificial Analysis Intelligence Index
Muse Spark 1.2 scores 80.15% on Terminal-Bench
Muse Spark 1.2 scores 7.07% on Terminal-Bench
Muse Spark 1.2 scores 57.41% on SciCode
Muse Spark 1.2 scores 45.46% on Humanity's Last Exam
Muse Spark 1.2 scores 90.4% on GPQA Diamond
Muse Spark 1.2 scores 39.8 on Artificial Analysis Intelligence Index
gpt-5.6-luna scores 43.45% on Terminal-Bench
gpt-5.6-luna scores 19.83% on Humanity's Last Exam
gpt-5.6-luna scores 83.54% on GPQA Diamond
gpt-5.6-luna scores 21.55 on Artificial Analysis Intelligence Index
Claude Fable 5.1 scores 85.02% on Terminal-Bench
Claude Fable 5.1 scores 40.4% on Terminal-Bench
Claude Fable 5.1 scores 56.71% on SciCode
Claude Fable 5.1 scores 48.89% on Humanity's Last Exam
Claude Fable 5.1 scores 88.08% on GPQA Diamond
Claude Fable 5.1 scores 47.04 on Artificial Analysis Intelligence Index
Mistral Medium 3.1 scores 10.61% on Terminal-Bench
Mistral Medium 3.1 scores 13.86% on Terminal-Bench
Mistral Medium 3.1 scores 0% on Terminal-Bench
Mistral Medium 3.1 scores 40.64% on τ²-bench
Mistral Medium 3.1 scores 54.16% on MMMU-Pro
Mistral Medium 3.1 scores 39.8% on IFBench
Mistral Medium 3.1 scores 32.41% on SciCode
Mistral Medium 3.1 scores 4.68% on Humanity's Last Exam
Mistral Medium 3.1 scores 58.79% on GPQA Diamond
Mistral Medium 3.1 scores 9.89 on Artificial Analysis Intelligence Index
gpt-5-nano scores 3.99% on Humanity's Last Exam
gpt-5-nano scores 7.09 on Artificial Analysis Intelligence Index
gemini-2-5-pro-05-06 scores 19.93% on Humanity's Last Exam
gemini-2-5-pro-05-06 scores 82.22% on GPQA Diamond
gemini-2-5-pro-05-06 scores 14.52 on Artificial Analysis Intelligence Index
o3-mini scores 10.96 on Artificial Analysis Intelligence Index
o1 Preview scores 11.38 on Artificial Analysis Intelligence Index
DeepSeek V3.2 Exp scores 25% on Terminal-Bench
DeepSeek V3.2 Exp scores 33.92% on τ²-bench
DeepSeek V3.2 Exp scores 43.13% on IFBench
DeepSeek V3.2 Exp scores 9.04% on Humanity's Last Exam
DeepSeek V3.2 Exp scores 73.84% on GPQA Diamond
DeepSeek V3.2 Exp scores 13.88 on Artificial Analysis Intelligence Index
apodex-1-1 scores 34.06% on Humanity's Last Exam
apodex-1-1 scores 30.37 on Artificial Analysis Intelligence Index
gpt-5.6-sol scores 60.61% on Terminal-Bench
gpt-5.6-sol scores 76.78% on Terminal-Bench
gpt-5.6-sol scores 39.39% on Humanity's Last Exam
gpt-5.6-sol scores 33.8 on Artificial Analysis Intelligence Index
qwen3-coder-480b-a35b-instruct scores 18.94% on Terminal-Bench
qwen3-coder-480b-a35b-instruct scores 43.57% on τ²-bench
qwen3-coder-480b-a35b-instruct scores 40.48% on IFBench
qwen3-coder-480b-a35b-instruct scores 4.54% on Humanity's Last Exam
qwen3-coder-480b-a35b-instruct scores 61.82% on GPQA Diamond
qwen3-coder-480b-a35b-instruct scores 11.9 on Artificial Analysis Intelligence Index
Gemini 3.5 Flash-Lite scores 53.56% on Terminal-Bench
Gemini 3.5 Flash-Lite scores 1.01% on Terminal-Bench
Gemini 3.5 Flash-Lite scores 79.02% on MMMU-Pro
Gemini 3.5 Flash-Lite scores 41.32% on SciCode
Gemini 3.5 Flash-Lite scores 18.81% on Humanity's Last Exam
Gemini 3.5 Flash-Lite scores 83.84% on GPQA Diamond
Gemini 3.5 Flash-Lite scores 22.66 on Artificial Analysis Intelligence Index
Qwen3.5-2B scores 4.96% on Humanity's Last Exam
Qwen3.5-2B scores 6.19 on Artificial Analysis Intelligence Index
Devstral 2 scores 18.94% on Terminal-Bench
Devstral 2 scores 30.34% on Terminal-Bench
Devstral 2 scores 3.57% on Humanity's Last Exam
Devstral 2 scores 59.39% on GPQA Diamond
Devstral 2 scores 9.41 on Artificial Analysis Intelligence Index
claude-35-sonnet scores 3.69% on Humanity's Last Exam
claude-35-sonnet scores 59.9% on GPQA Diamond
claude-35-sonnet scores 7.88 on Artificial Analysis Intelligence Index
DeepSeek V3.1 Terminus scores 30.3% on Terminal-Bench
DeepSeek V3.1 Terminus scores 44.94% on Terminal-Bench
DeepSeek V3.1 Terminus scores 0% on Terminal-Bench
DeepSeek V3.1 Terminus scores 37.13% on τ²-bench
DeepSeek V3.1 Terminus scores 57.01% on IFBench
DeepSeek V3.1 Terminus scores 37.96% on SciCode
DeepSeek V3.1 Terminus scores 16.36% on Humanity's Last Exam
DeepSeek V3.1 Terminus scores 79.19% on GPQA Diamond
DeepSeek V3.1 Terminus scores 15.4 on Artificial Analysis Intelligence Index
qwen3-omni-30b-a3b-instruct scores 1.52% on Terminal-Bench
qwen3-omni-30b-a3b-instruct scores 16.37% on τ²-bench
qwen3-omni-30b-a3b-instruct scores 55.49% on MMMU-Pro
qwen3-omni-30b-a3b-instruct scores 31.16% on IFBench
qwen3-omni-30b-a3b-instruct scores 4.63% on Humanity's Last Exam
qwen3-omni-30b-a3b-instruct scores 62.02% on GPQA Diamond
qwen3-omni-30b-a3b-instruct scores 6.01 on Artificial Analysis Intelligence Index
grok-build-0-1-06-16 scores 52.06% on Terminal-Bench
grok-build-0-1-06-16 scores 76.53% on MMMU-Pro
grok-build-0-1-06-16 scores 38.28% on Humanity's Last Exam
grok-build-0-1-06-16 scores 89.49% on GPQA Diamond
grok-build-0-1-06-16 scores 27.17 on Artificial Analysis Intelligence Index
granite-4.2-3b scores 13.86% on Terminal-Bench
granite-4.2-3b scores 6.63% on Humanity's Last Exam
granite-4.2-3b scores 55.86% on GPQA Diamond
granite-4.2-3b scores 9.06 on Artificial Analysis Intelligence Index
nova-2-0-pro scores 24.24% on Terminal-Bench
nova-2-0-pro scores 29.59% on Terminal-Bench
nova-2-0-pro scores 92.69% on τ²-bench
nova-2-0-pro scores 64.51% on MMMU-Pro
nova-2-0-pro scores 79.05% on IFBench
nova-2-0-pro scores 9.41% on Humanity's Last Exam
nova-2-0-pro scores 78.48% on GPQA Diamond
nova-2-0-pro scores 14.16 on Artificial Analysis Intelligence Index
Inkling scores 55.06% on Terminal-Bench
Inkling scores 1.01% on Terminal-Bench
Inkling scores 31.88% on Humanity's Last Exam
Inkling scores 87.17% on GPQA Diamond
Inkling scores 25.54 on Artificial Analysis Intelligence Index
Kimi K2.6 scores 43.94% on Terminal-Bench
Kimi K2.6 scores 65.92% on Terminal-Bench
Kimi K2.6 scores 37.49% on Humanity's Last Exam
Kimi K2.6 scores 31.32 on Artificial Analysis Intelligence Index
deepseek-r1-0120 scores 6.06% on Terminal-Bench
deepseek-r1-0120 scores 19.1% on Terminal-Bench
deepseek-r1-0120 scores 0% on Terminal-Bench
deepseek-r1-0120 scores 11.4% on τ²-bench
deepseek-r1-0120 scores 38.98% on IFBench
deepseek-r1-0120 scores 38.31% on SciCode
deepseek-r1-0120 scores 8.5% on Humanity's Last Exam
deepseek-r1-0120 scores 70.81% on GPQA Diamond
deepseek-r1-0120 scores 11.41 on Artificial Analysis Intelligence Index
deepseek-r1-distill-llama-8b scores 17.55% on IFBench
deepseek-r1-distill-llama-8b scores 30.2% on GPQA Diamond
deepseek-r1-distill-llama-8b scores 6.48 on Artificial Analysis Intelligence Index
qwen3-0.6b-instruct scores 0% on Terminal-Bench
qwen3-0.6b-instruct scores 14.62% on τ²-bench
qwen3-0.6b-instruct scores 21.9% on IFBench
qwen3-0.6b-instruct scores 4.93% on Humanity's Last Exam
qwen3-0.6b-instruct scores 23.13% on GPQA Diamond
qwen3-0.6b-instruct scores 4.83 on Artificial Analysis Intelligence Index
Qwen3.5 397B A17B scores 40.91% on Terminal-Bench
Qwen3.5 397B A17B scores 51.31% on Terminal-Bench
Qwen3.5 397B A17B scores 0% on Terminal-Bench
Qwen3.5 397B A17B scores 95.61% on τ²-bench
Qwen3.5 397B A17B scores 77.28% on MMMU-Pro
Qwen3.5 397B A17B scores 78.78% on IFBench
Qwen3.5 397B A17B scores 44.79% on SciCode
Qwen3.5 397B A17B scores 28.96% on Humanity's Last Exam
Qwen3.5 397B A17B scores 89.29% on GPQA Diamond
Qwen3.5 397B A17B scores 19.11 on Artificial Analysis Intelligence Index
LFM2-1.2B scores 5.56% on Humanity's Last Exam
LFM2-1.2B scores 4.83 on Artificial Analysis Intelligence Index
Kimi K2.6 scores 37.88% on Terminal-Bench
Kimi K2.6 scores 19.56% on Humanity's Last Exam
Kimi K2.6 scores 23.57 on Artificial Analysis Intelligence Index
magistral-small scores 4.55% on Terminal-Bench
magistral-small scores 26.61% on τ²-bench
magistral-small scores 24.76% on IFBench
magistral-small scores 7.55% on Humanity's Last Exam
magistral-small scores 64.14% on GPQA Diamond
magistral-small scores 8.22 on Artificial Analysis Intelligence Index
granite-4.2-30b scores 26.59% on Terminal-Bench
granite-4.2-30b scores 11.17% on Humanity's Last Exam
granite-4.2-30b scores 64.44% on GPQA Diamond
granite-4.2-30b scores 14.83 on Artificial Analysis Intelligence Index
lfm-40b scores 4.93% on Humanity's Last Exam
lfm-40b scores 5.42 on Artificial Analysis Intelligence Index
MiniMax M2.5 scores 34.85% on Terminal-Bench
MiniMax M2.5 scores 20.53% on Humanity's Last Exam
MiniMax M2.5 scores 84.85% on GPQA Diamond
MiniMax M2.5 scores 22.8 on Artificial Analysis Intelligence Index
Mistral Small 4 scores 10.61% on Terminal-Bench
Mistral Small 4 scores 18.42% on τ²-bench
Mistral Small 4 scores 46.47% on MMMU-Pro
Mistral Small 4 scores 32.79% on IFBench
Mistral Small 4 scores 3.8% on Humanity's Last Exam
Mistral Small 4 scores 57.07% on GPQA Diamond
Mistral Small 4 scores 8.99 on Artificial Analysis Intelligence Index
Claude Opus 5 scores 88.01% on Terminal-Bench
Claude Opus 5 scores 46.46% on Terminal-Bench
Claude Opus 5 scores 83.99% on MMMU-Pro
Claude Opus 5 scores 55.67% on SciCode
Claude Opus 5 scores 54.4% on Humanity's Last Exam
Claude Opus 5 scores 93.74% on GPQA Diamond
Claude Opus 5 scores 49.65 on Artificial Analysis Intelligence Index
Claude 3.7 Sonnet scores 21.21% on Terminal-Bench
Claude 3.7 Sonnet scores 54.68% on τ²-bench
Claude 3.7 Sonnet scores 48.3% on IFBench
Claude 3.7 Sonnet scores 9.67% on Humanity's Last Exam
Claude 3.7 Sonnet scores 77.17% on GPQA Diamond
Claude 3.7 Sonnet scores 17.71 on Artificial Analysis Intelligence Index
Claude Sonnet 5 scores 2.53% on Terminal-Bench
Claude Sonnet 5 scores 50.12% on SciCode
Claude Sonnet 5 scores 21.92% on Humanity's Last Exam
Claude Sonnet 5 scores 24.74 on Artificial Analysis Intelligence Index
mimo-v2-0206 scores 31.06% on Terminal-Bench
mimo-v2-0206 scores 22.1% on Humanity's Last Exam
mimo-v2-0206 scores 83.54% on GPQA Diamond
mimo-v2-0206 scores 22.44 on Artificial Analysis Intelligence Index
GLM 5 Turbo scores 33.33% on Terminal-Bench
GLM 5 Turbo scores 98.54% on τ²-bench
GLM 5 Turbo scores 73.2% on IFBench
GLM 5 Turbo scores 27.76% on Humanity's Last Exam
GLM 5 Turbo scores 84.75% on GPQA Diamond
GLM 5 Turbo scores 26.6 on Artificial Analysis Intelligence Index
ling-1t scores 7.32% on Humanity's Last Exam
ling-1t scores 9.17 on Artificial Analysis Intelligence Index
gpt-oss-20b scores 5.28% on Humanity's Last Exam
gpt-oss-20b scores 9.95 on Artificial Analysis Intelligence Index
Qwen3.5-27B scores 23.91% on Humanity's Last Exam
Qwen3.5-27B scores 22.9 on Artificial Analysis Intelligence Index
o3 scores 20.2 on Artificial Analysis Intelligence Index
gemini-1-5-pro-may-2024 scores 3.48% on Humanity's Last Exam
gemini-1-5-pro-may-2024 scores 37.07% on GPQA Diamond
gemini-1-5-pro-may-2024 scores 6.44 on Artificial Analysis Intelligence Index
k-exaone-2-0-0803 scores 40.45% on Terminal-Bench
k-exaone-2-0-0803 scores 42.01% on SciCode
k-exaone-2-0-0803 scores 18.58% on Humanity's Last Exam
k-exaone-2-0-0803 scores 82.93% on GPQA Diamond
k-exaone-2-0-0803 scores 19.69 on Artificial Analysis Intelligence Index
qwen3-4b-instruct scores 19.01% on τ²-bench
qwen3-4b-instruct scores 32.52% on IFBench
qwen3-4b-instruct scores 4.42% on Humanity's Last Exam
qwen3-4b-instruct scores 52.22% on GPQA Diamond
qwen3-4b-instruct scores 7.23 on Artificial Analysis Intelligence Index
GLM 5.3 Flash scores 84.27% on Terminal-Bench
GLM 5.3 Flash scores 32.83% on Terminal-Bench
GLM 5.3 Flash scores 51.62% on SciCode
GLM 5.3 Flash scores 39.85% on Humanity's Last Exam
GLM 5.3 Flash scores 91.21% on GPQA Diamond
GLM 5.3 Flash scores 41.91 on Artificial Analysis Intelligence Index
DeepSeek V3.1 scores 25% on Terminal-Bench
DeepSeek V3.1 scores 37.43% on τ²-bench
DeepSeek V3.1 scores 14.27% on Humanity's Last Exam
DeepSeek V3.1 scores 77.88% on GPQA Diamond
DeepSeek V3.1 scores 13.48 on Artificial Analysis Intelligence Index
llama-3-3-nemotron-super-49b scores 0% on Terminal-Bench
llama-3-3-nemotron-super-49b scores 26.9% on τ²-bench
llama-3-3-nemotron-super-49b scores 38.1% on IFBench
llama-3-3-nemotron-super-49b scores 5.62% on Humanity's Last Exam
llama-3-3-nemotron-super-49b scores 64.34% on GPQA Diamond
llama-3-3-nemotron-super-49b scores 8.93 on Artificial Analysis Intelligence Index
Step 3.5 Flash scores 32.58% on Terminal-Bench
Step 3.5 Flash scores 87.43% on τ²-bench
Step 3.5 Flash scores 66.53% on IFBench
Step 3.5 Flash scores 24.47% on Humanity's Last Exam
Step 3.5 Flash scores 82.63% on GPQA Diamond
Step 3.5 Flash scores 16.96 on Artificial Analysis Intelligence Index
Mistral Large 2.0 scores 33.04% on τ²-bench
Mistral Large 2.0 scores 31.63% on IFBench
Mistral Large 2.0 scores 2.95% on Humanity's Last Exam
Mistral Large 2.0 scores 47.17% on GPQA Diamond
Mistral Large 2.0 scores 6.8 on Artificial Analysis Intelligence Index
Solar Pro 4 scores 57.3% on Terminal-Bench
Solar Pro 4 scores 0.51% on Terminal-Bench
Solar Pro 4 scores 29.24% on Humanity's Last Exam
Solar Pro 4 scores 28.15 on Artificial Analysis Intelligence Index
dbrx scores 5.29 on Artificial Analysis Intelligence Index
GLM 4.5 scores 21.97% on Terminal-Bench
GLM 4.5 scores 12.97% on Humanity's Last Exam
GLM 4.5 scores 12.77 on Artificial Analysis Intelligence Index
qwen2.5-32b-instruct scores 3.99% on Humanity's Last Exam
qwen2.5-32b-instruct scores 46.57% on GPQA Diamond
qwen2.5-32b-instruct scores 6.87 on Artificial Analysis Intelligence Index
Gemini 2.5 Flash-Lite scores 2.27% on Terminal-Bench
Gemini 2.5 Flash-Lite scores 19.01% on τ²-bench
Gemini 2.5 Flash-Lite scores 53.99% on MMMU-Pro
Gemini 2.5 Flash-Lite scores 31.5% on IFBench
Gemini 2.5 Flash-Lite scores 3.66% on Humanity's Last Exam
Gemini 2.5 Flash-Lite scores 47.37% on GPQA Diamond
Gemini 2.5 Flash-Lite scores 6.67 on Artificial Analysis Intelligence Index
Hermes 3 70B Instruct scores 3.99% on Humanity's Last Exam
Hermes 3 70B Instruct scores 40.1% on GPQA Diamond
Hermes 3 70B Instruct scores 6 on Artificial Analysis Intelligence Index
North Mini Code (free) scores 31.06% on Terminal-Bench
North Mini Code (free) scores 35.58% on Terminal-Bench
North Mini Code (free) scores 0.51% on Terminal-Bench
North Mini Code (free) scores 37.43% on τ²-bench
North Mini Code (free) scores 57.55% on IFBench
North Mini Code (free) scores 38.77% on SciCode
North Mini Code (free) scores 11.08% on Humanity's Last Exam
North Mini Code (free) scores 75.66% on GPQA Diamond
North Mini Code (free) scores 12.84 on Artificial Analysis Intelligence Index
Sonar Reasoning Pro scores 11.82 on Artificial Analysis Intelligence Index
gpt-5.5 scores 38.63 on Artificial Analysis Intelligence Index
mistral-medium scores 3.51% on Humanity's Last Exam
mistral-medium scores 34.95% on GPQA Diamond
mistral-medium scores 5.49 on Artificial Analysis Intelligence Index
gpt-6-astra scores 89.14% on Terminal-Bench
gpt-6-astra scores 54.59% on Humanity's Last Exam
gpt-6-astra scores 52.51 on Artificial Analysis Intelligence Index
nova-2-0-omni scores 6.82% on Terminal-Bench
nova-2-0-omni scores 44.74% on τ²-bench
nova-2-0-omni scores 49.88% on MMMU-Pro
nova-2-0-omni scores 41.09% on IFBench
nova-2-0-omni scores 3.85% on Humanity's Last Exam
nova-2-0-omni scores 55.45% on GPQA Diamond
nova-2-0-omni scores 8.15 on Artificial Analysis Intelligence Index
Showing up to 1,000 events — the API cap; narrow by year, lane or scope to see everything. Dates are occurred_at (effective date when a source states one, else observation) — hover a date for the observation time. Cursor-paged history: changes feed.
Earliest loaded event: 2026-09-12T07:08:16.635021Z