Compare AI inference models for coding tools, agents, and API usage
Read this as a triage board: start with a ranking, check the data confidence badges, then open a row before choosing a model. Scores are source-backed when available and explicitly marked when stale, estimated, or missing.
Default shortlist when you have price and benchmark coverage.
Missing fields stay visible so you can avoid false precision.
Move the slider when your workload is prompt-heavy or output-heavy.
Ranking shortlist
Default shortlist when you have price and benchmark coverage.
Price vs quality
Best value usually lives high and left: better public quality with lower blended price.
Click a dot to inspect that model.
Axes are scaled because a few outliers would otherwise compress the useful cluster. Legend values remain the original public values.
Context window vs price
Look for models far right and low: more context without a large price jump.
Click a dot to inspect that model.
Axes are scaled because a few outliers would otherwise compress the useful cluster. Legend values remain the original public values.
Output price comparison
Selected table rows. Use this before choosing chatty coding or agent models.
Click a bar to open model details.
Value score ranking
Overall value: quality divided by your current blended price.
Click a bar to open model details.
Model table
Sorted by value score descending. Click a row for source values and score math; select up to 8 rows for charts.
| Pick | Features | Sources | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Nemotron 3 Ultra (free) nvidia/nemotron-3-ultra-550b-a55b:free 3 gapsBenchmark: live | nvidia | $0.00 | $0.00 | $0.00 | 1M | 65.5K | Reason: YesTools: YesVision: NoCache: Unknown | 37.6 | 47.7 | No public latency | 4,750 | OpenRouter | |
Nemotron 3 Super (free) nvidia/nemotron-3-super-120b-a12b:free 3 gapsBenchmark: live | nvidia | $0.00 | $0.00 | $0.00 | 1M | 262.1K | Reason: YesTools: YesVision: NoCache: Unknown | 31.2 | 36 | No public latency | 3,580 | OpenRouter | |
Nemotron 3 Nano 30B A3B (free) openrouter/openrouter/free 2 gapsBenchmark: live | nousresearch | $0.00 | $0.00 | $0.00 | 1M | 262.1K | Reason: YesTools: YesVision: YesCache: Unknown | 22.4 | 31.2 | No public latency | 3,040 | LiteLLMOpenRouter | |
Nemotron 3 Nano Omni (free) nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free 3 gapsBenchmark: live | nvidia | $0.00 | $0.00 | $0.00 | 256K | 65.5K | Reason: YesTools: YesVision: YesCache: Unknown | 14.8 | 21.4 | No public latency | 2,000 | OpenRouter | |
Qwen3 Next 80B A3B Instruct (free) qwen/qwen3-next-80b-a3b-instruct:free 4 gapsBenchmark: live | qwen | $0.00 | $0.00 | $0.00 | 262.1K | No public limit | Reason: NoTools: YesVision: NoCache: Unknown | 15.3 | 20.1 | No public latency | 1,650 | OpenRouter | |
Ling-2.6-flash inclusionai/ling-2.6-flash 2 gapsBenchmark: live | inclusionai | $0.01 | $0.03 | $0.026 | 262.1K | 32.8K | Reason: NoTools: YesVision: NoCache: Yes | 23.2 | 26.2 | No public latency | 1,123.1 | OpenRouter | |
Olmo 3 32B Think publicai/allenai/Olmo-3-32B-Think 3 gapsBenchmark: live | publicai | $0.00 | $0.00 | $0.00 | 65.5K | 65.5K | Reason: YesTools: YesVision: NoCache: Unknown | 10.5 | 12.1 | No public latency | 750 | LiteLLMOpenRouter | |
Qwen3 235B A22B Instruct 2507 openrouter/qwen/qwen3-235b-a22b-2507 2 gapsBenchmark: live | openrouter | $0.071 | $0.10 | $0.0942 | 262.1K | 262.1K | Reason: NoTools: YesVision: NoCache: Unknown | 22.1 | 25 | No public latency | 296.2 | LiteLLMOpenRouter | |
DeepSeek V4 Flash deepseek/deepseek-v4-flash 2 gapsBenchmark: live | deepseek | $0.098 | $0.196 | $0.1764 | 1M | No public limit | Reason: YesTools: YesVision: NoCache: Yes | 38.7 | 46.5 | No public latency | 278.3 | OpenRouter | |
Hy3 preview tencent/hy3-preview 3 gapsBenchmark: live | tencent | $0.063 | $0.21 | $0.1806 | 262.1K | No public limit | Reason: YesTools: YesVision: NoCache: Yes | 36.5 | 41.9 | No public latency | 247.5 | OpenRouter | |
Qwen3.5-9B qwen/qwen3.5-9b 3 gapsBenchmark: live | qwen | $0.10 | $0.15 | $0.14 | 262.1K | 262.1K | Reason: YesTools: YesVision: YesCache: Unknown | 25.3 | 32.4 | No public latency | 226.4 | OpenRouter | |
GPT Oss 20b deepinfra/openai/gpt-oss-20b 1 gapsBenchmark: live | together_ai | $0.04 | $0.15 | $0.128 | 131.1K | 131.1K | Reason: YesTools: YesVision: YesCache: Yes | 18.5 | 24.5 | No public latency | 203.9 | LiteLLMOpenRouter | |
Llama 3.1 8B Instruct lambda_ai/llama3.1-8b-instruct 3 gapsBenchmark: live | perplexity | $0.025 | $0.04 | $0.037 | 131.1K | 131.1K | Reason: NoTools: YesVision: NoCache: Unknown | 4.9 | 11.8 | No public latency | 200 | LiteLLMOpenRouter | |
Mimo V2 Flash openrouter/xiaomi/mimo-v2-flash 1 gapsBenchmark: live | openrouter | $0.10 | $0.30 | $0.26 | 262.1K | 65.5K | Reason: YesTools: YesVision: NoCache: Yes | 33.5 | 41.5 | No public latency | 163.1 | LiteLLMOpenRouter | |
Ministral 3 3B 2512 openrouter/mistralai/ministral-3b-2512 1 gapsBenchmark: live | openrouter | $0.10 | $0.10 | $0.10 | 131.1K | 131.1K | Reason: NoTools: YesVision: YesCache: Yes | 4.8 | 11.2 | No public latency | 159 | LiteLLMOpenRouter | |
Step 3.5 Flash stepfun/step-3.5-flash 2 gapsBenchmark: live | stepfun | $0.09 | $0.30 | $0.258 | 262.1K | 16.4K | Reason: YesTools: YesVision: NoCache: Yes | 34.6 | 38.5 | No public latency | 156.6 | OpenRouter | |
Mistral Small 3.2 24b Instruct openrouter/mistralai/mistral-small-3.2-24b-instruct 5 gapsBenchmark: live | openrouter | $0.10 | $0.30 | $0.26 | 128K | 128K | Reason: NoTools: YesVision: YesCache: Unknown | No score | No score | No public latency | 155 | LiteLLMOpenRouter | |
Ministral 3 8B 2512 mistral/ministral-8b-2512 1 gapsBenchmark: live | openrouter | $0.15 | $0.15 | $0.15 | 262.1K | 262.1K | Reason: NoTools: YesVision: YesCache: Yes | 10 | 14.8 | No public latency | 140.7 | LiteLLMOpenRouter | |
Gemma 4 31B google/gemma-4-31b-it 2 gapsBenchmark: live | $0.12 | $0.35 | $0.304 | 262.1K | 262.1K | Reason: YesTools: YesVision: YesCache: Yes | 38.7 | 39.2 | No public latency | 130.3 | OpenRouter | ||
Qwen3 Coder 30b A3b Instruct novita/qwen/qwen3-coder-30b-a3b-instruct 2 gapsBenchmark: live | novita | $0.07 | $0.27 | $0.23 | 160K | 32.8K | Reason: NoTools: YesVision: NoCache: Unknown | 19.4 | 20 | No public latency | 126.1 | LiteLLMOpenRouter | |
Codestral 2501 vertex_ai/codestral-2501 5 gapsBenchmark: stale estimate | mistral | $0.20 | $0.60 | $0.52 | 128K | 128K | Reason: UnknownTools: YesVision: UnknownCache: Unknown | 70 | 61 | No public latency | 125.6 | LiteLLMBenchmark Seed | |
GPT 4o Mini azure/gpt-4o-mini 1 gapsBenchmark: stale estimate | openai | $0.165 | $0.66 | $0.561 | 131.1K | 16.4K | Reason: NoTools: YesVision: YesCache: Yes | 68 | 63 | No public latency | 122.6 | LiteLLMOpenRouterBenchmark Seed | |
Nemotron 3 Nano 30B A3B nvidia/nemotron-3-nano-30b-a3b 3 gapsBenchmark: live | nvidia | $0.05 | $0.20 | $0.17 | 262.1K | 228K | Reason: YesTools: YesVision: NoCache: Unknown | 19 | 24.3 | No public latency | 122.4 | OpenRouter | |
Deepseek Chat deepseek-chat 4 gapsBenchmark: live | openrouter | $0.28 | $0.42 | $0.392 | 131.1K | 16K | Reason: NoTools: YesVision: NoCache: Yes | No score | No score | No public latency | 121.9 | LiteLLMOpenRouter | |
Zai.Glm 4.7 Flash openrouter/z-ai/glm-4.7-flash 1 gapsBenchmark: live | bedrock_converse | $0.07 | $0.40 | $0.334 | 202.8K | 128K | Reason: YesTools: YesVision: YesCache: Yes | 25.9 | 30.1 | No public latency | 114.4 | LiteLLMOpenRouter | |
Granite 4.1 8B ibm-granite/granite-4.1-8b 2 gapsBenchmark: live | ibm-granite | $0.05 | $0.10 | $0.09 | 131.1K | 131.1K | Reason: NoTools: YesVision: NoCache: Yes | 7.3 | 12.4 | No public latency | 112.2 | OpenRouter | |
Ministral 3 14B 2512 openrouter/mistralai/ministral-14b-2512 1 gapsBenchmark: live | openrouter | $0.20 | $0.20 | $0.20 | 262.1K | 262.1K | Reason: NoTools: YesVision: YesCache: Yes | 10.9 | 16 | No public latency | 109 | LiteLLMOpenRouter | |
Gemma 4 26B A4B google/gemma-4-26b-a4b-it 4 gapsBenchmark: live | $0.06 | $0.33 | $0.276 | 262.1K | No public limit | Reason: YesTools: YesVision: YesCache: Unknown | 22.4 | 31.2 | No public latency | 103.6 | OpenRouter | ||
Deepseek V3.2 Exp openrouter/deepseek/deepseek-v3.2-exp 1 gapsBenchmark: live | openrouter | $0.20 | $0.40 | $0.36 | 163.8K | 163.8K | Reason: YesTools: YesVision: NoCache: Yes | 33.3 | 32.9 | No public latency | 101.9 | LiteLLMOpenRouter | |
Qwen3 8b llamagate/qwen3-8b 2 gapsBenchmark: live | llamagate | $0.04 | $0.14 | $0.12 | 131.1K | 8.2K | Reason: YesTools: YesVision: NoCache: Yes | 9 | 13.2 | No public latency | 96.7 | LiteLLMOpenRouter | |
Nemotron 3 Super nvidia/nemotron-3-super-120b-a12b 4 gapsBenchmark: live | nvidia | $0.09 | $0.45 | $0.378 | 1M | No public limit | Reason: YesTools: YesVision: NoCache: Unknown | 31.2 | 36 | No public latency | 94.7 | OpenRouter | |
GPT 5 Nano azure/gpt-5-nano 1 gapsBenchmark: live | openrouter | $0.05 | $0.40 | $0.33 | 400K | 128K | Reason: YesTools: YesVision: YesCache: Yes | 20.3 | 26.8 | No public latency | 88.5 | LiteLLMOpenRouter | |
Deepseek Chat V3 0324 openrouter/deepseek/deepseek-chat-v3-0324 2 gapsBenchmark: live | openrouter | $0.14 | $0.28 | $0.252 | 131.1K | 16.4K | Reason: NoTools: YesVision: NoCache: Yes | 22 | 22.3 | No public latency | 80.2 | LiteLLMOpenRouter | |
Ring-2.6-1T inclusionai/ring-2.6-1t 2 gapsBenchmark: live | inclusionai | $0.075 | $0.625 | $0.515 | 262.1K | 65.5K | Reason: YesTools: YesVision: NoCache: Yes | 33.3 | 38.5 | No public latency | 79.8 | OpenRouter | |
Qwen3 30b A3b dashscope/qwen3-30b-a3b 2 gapsBenchmark: live | dashscope | $0.08 | $0.29 | $0.248 | 131.1K | 41K | Reason: YesTools: YesVision: NoCache: Unknown | 11 | 15.3 | No public latency | 77 | LiteLLMOpenRouter | |
Ling-2.6-1T inclusionai/ling-2.6-1t 2 gapsBenchmark: live | inclusionai | $0.075 | $0.625 | $0.515 | 262.1K | 32.8K | Reason: NoTools: YesVision: NoCache: Yes | 33.1 | 33.6 | No public latency | 74.4 | OpenRouter | |
Qwen3 30B A3B Instruct 2507 qwen/qwen3-30b-a3b-instruct-2507 3 gapsBenchmark: live | qwen | $0.0482 | $0.1931 | $0.1641 | 131.1K | 32K | Reason: NoTools: YesVision: NoCache: Unknown | 14.2 | 15 | No public latency | 73.8 | OpenRouter | |
Qwen3 14B deepinfra/Qwen/Qwen3-14B 3 gapsBenchmark: live | deepinfra | $0.06 | $0.24 | $0.204 | 131.7K | 41K | Reason: YesTools: YesVision: NoCache: Unknown | 13.1 | 16.2 | No public latency | 71.6 | LiteLLMOpenRouter | |
Gemini 2.5 Flash Lite Preview 09 2025 gemini-2.5-flash-lite-preview-09-2025 1 gapsBenchmark: live | vertex_ai-language-models | $0.10 | $0.40 | $0.34 | 1M | 65.5K | Reason: YesTools: YesVision: YesCache: Yes | 18.2 | 21.6 | No public latency | 70.3 | LiteLLMOpenRouter | |
Gemma 3 12b It deepinfra/google/gemma-3-12b-it 3 gapsBenchmark: live | deepinfra | $0.05 | $0.10 | $0.09 | 131.1K | 131.1K | Reason: NoTools: YesVision: YesCache: Unknown | 6.3 | 8.8 | No public latency | 68.9 | LiteLLMOpenRouter | |
DeepSeek V4 Pro deepseek/deepseek-v4-pro 1 gapsBenchmark: live | deepseek | $0.435 | $0.87 | $0.783 | 1M | 384K | Reason: YesTools: YesVision: NoCache: Yes | 47.5 | 51.5 | No public latency | 68.2 | OpenRouter | |
GPT Oss 120b azure_ai/gpt-oss-120b 1 gapsBenchmark: live | together_ai | $0.15 | $0.60 | $0.51 | 131.1K | 131.1K | Reason: YesTools: YesVision: YesCache: Yes | 28.6 | 33.3 | No public latency | 66.7 | LiteLLMOpenRouter | |
Qwen3 30B A3B Thinking 2507 qwen/qwen3-30b-a3b-thinking-2507 1 gapsBenchmark: live | qwen | $0.08 | $0.40 | $0.336 | 131.1K | 131.1K | Reason: YesTools: YesVision: NoCache: Yes | 14.6 | 22.4 | No public latency | 66.4 | OpenRouter | |
Granite 4.0 Micro ibm-granite/granite-4.0-h-micro 3 gapsBenchmark: live | ibm-granite | $0.017 | $0.112 | $0.093 | 131K | 131K | Reason: NoTools: NoVision: NoCache: Unknown | 5 | 7.7 | No public latency | 60.2 | OpenRouter | |
Deepseek R1 0528 lambda_ai/deepseek-r1-0528 1 gapsBenchmark: live | openrouter | $0.20 | $0.60 | $0.52 | 163.8K | 131.1K | Reason: YesTools: YesVision: NoCache: Yes | 24 | 27.1 | No public latency | 60.2 | LiteLLMOpenRouter | |
LFM2-24B-A2B liquid/lfm-2-24b-a2b 4 gapsBenchmark: live | liquid | $0.03 | $0.12 | $0.102 | 128K | No public limit | Reason: NoTools: NoVision: NoCache: Unknown | 3.6 | 10.5 | No public latency | 57.8 | OpenRouter | |
Phi 4 deepinfra/microsoft/phi-4 3 gapsBenchmark: live | deepinfra | $0.07 | $0.14 | $0.126 | 16.4K | 16.4K | Reason: NoTools: YesVision: NoCache: Unknown | 11.2 | 10.4 | No public latency | 57.1 | LiteLLMOpenRouter | |
GPT 4.1 Nano azure/gpt-4.1-nano 1 gapsBenchmark: live | vercel_ai_gateway | $0.10 | $0.40 | $0.34 | 1M | 32.8K | Reason: NoTools: YesVision: YesCache: Yes | 11.2 | 13 | No public latency | 55.9 | LiteLLMOpenRouter | |
Qwen3.6 35B A3B qwen/qwen3.6-35b-a3b 2 gapsBenchmark: live | qwen | $0.15 | $1.00 | $0.83 | 262.1K | 262.1K | Reason: YesTools: YesVision: YesCache: Yes | 35.2 | 43.5 | No public latency | 55.1 | OpenRouter | |
Nova Micro 1.0 amazon-nova/nova-micro-v1 2 gapsBenchmark: live | amazon_nova | $0.035 | $0.14 | $0.119 | 128K | 10K | Reason: NoTools: YesVision: NoCache: Yes | 4.1 | 10.3 | No public latency | 53.8 | LiteLLMOpenRouter | |
Gemma 3 27b It deepinfra/google/gemma-3-27b-it 3 gapsBenchmark: live | deepinfra | $0.09 | $0.16 | $0.146 | 131.1K | 131.1K | Reason: NoTools: YesVision: YesCache: Unknown | 9.6 | 10.3 | No public latency | 53.4 | LiteLLMOpenRouter | |
Mercury 2 inception/mercury-2 2 gapsBenchmark: live | inception | $0.25 | $0.75 | $0.65 | 128K | 50K | Reason: YesTools: YesVision: NoCache: Yes | 30.6 | 32.8 | No public latency | 52.9 | LiteLLMOpenRouter | |
Codestral 2508 mistral/codestral-2508 4 gapsBenchmark: live | mistralai | $0.30 | $0.90 | $0.78 | 256K | 256K | Reason: NoTools: YesVision: NoCache: Yes | No score | No score | No public latency | 52.7 | LiteLLMOpenRouter | |
Llama 4 Scout meta-llama/llama-4-scout 2 gapsBenchmark: live | meta-llama | $0.10 | $0.30 | $0.26 | 10M | 16.4K | Reason: NoTools: YesVision: YesCache: Unknown | 6.7 | 13.5 | No public latency | 51.5 | OpenRouter | |
Mistral Small 4 mistralai/mistral-small-2603 3 gapsBenchmark: live | mistralai | $0.15 | $0.60 | $0.51 | 262.1K | No public limit | Reason: YesTools: YesVision: YesCache: Yes | 24.3 | 27.8 | No public latency | 51 | OpenRouter | |
Qwen3.7 Plus qwen/qwen3.7-plus 2 gapsBenchmark: live | qwen | $0.32 | $1.28 | $1.088 | 1M | 65.5K | Reason: YesTools: YesVision: YesCache: Yes | 46.5 | 53.3 | No public latency | 50.6 | OpenRouter | |
MiniMax M2.7 sambanova/MiniMax-M2.7 1 gapsBenchmark: live | sambanova | $0.30 | $1.20 | $1.02 | 204.8K | 131.1K | Reason: YesTools: YesVision: NoCache: Yes | 41.9 | 49.6 | No public latency | 50.2 | LiteLLMOpenRouter | |
Gemma 3 4b It deepinfra/google/gemma-3-4b-it 3 gapsBenchmark: live | deepinfra | $0.04 | $0.08 | $0.072 | 131.1K | 131.1K | Reason: NoTools: YesVision: YesCache: Unknown | 2.9 | 6.3 | No public latency | 50 | LiteLLMOpenRouter | |
Deepseek Chat V3.1 openrouter/deepseek/deepseek-chat-v3.1 1 gapsBenchmark: live | openrouter | $0.20 | $0.80 | $0.68 | 163.8K | 163.8K | Reason: YesTools: YesVision: NoCache: Yes | 28.4 | 28.1 | No public latency | 49.6 | LiteLLMOpenRouter | |
Qwen3 235B A22B deepinfra/Qwen/Qwen3-235B-A22B 2 gapsBenchmark: live | hyperbolic | $0.18 | $0.54 | $0.468 | 262.1K | 262.1K | Reason: YesTools: YesVision: NoCache: Unknown | 17.4 | 19.8 | No public latency | 48.9 | LiteLLMOpenRouter | |
Solar Pro 3 upstage/solar-pro-3 3 gapsBenchmark: live | upstage | $0.15 | $0.60 | $0.51 | 128K | No public limit | Reason: YesTools: YesVision: NoCache: Yes | 13.3 | 25.9 | No public latency | 48.4 | OpenRouter | |
Trinity Large Thinking arcee-ai/trinity-large-thinking 1 gapsBenchmark: live | arcee-ai | $0.22 | $0.85 | $0.724 | 262.1K | 262.1K | Reason: YesTools: YesVision: NoCache: Yes | 27.2 | 31.9 | No public latency | 48.3 | OpenRouter | |
Step 3.7 Flash stepfun/step-3.7-flash 1 gapsBenchmark: live | stepfun | $0.20 | $1.15 | $0.96 | 256K | 256K | Reason: YesTools: YesVision: YesCache: Yes | 37.1 | 42.6 | No public latency | 48.1 | OpenRouter | |
Qwen3 Coder Next qwen/qwen3-coder-next 2 gapsBenchmark: live | qwen | $0.11 | $0.80 | $0.662 | 262.1K | 262.1K | Reason: NoTools: YesVision: NoCache: Yes | 22.9 | 28.3 | No public latency | 47 | OpenRouter | |
Minimax.Minimax M2.5 minimax.minimax-m2.5 1 gapsBenchmark: live | bedrock_converse | $0.30 | $1.20 | $1.02 | 1M | 196.6K | Reason: YesTools: YesVision: NoCache: Yes | 37.4 | 41.9 | No public latency | 46.6 | LiteLLMOpenRouter | |
KAT-Coder-Pro V2 kwaipilot/kat-coder-pro-v2 2 gapsBenchmark: live | kwaipilot | $0.30 | $1.20 | $1.02 | 256K | 80K | Reason: NoTools: YesVision: NoCache: Yes | 45.6 | 43.8 | No public latency | 45.8 | OpenRouter | |
Deepseek V3.1 Terminus novita/deepseek/deepseek-v3.1-terminus 1 gapsBenchmark: live | deepseek | $0.27 | $1.00 | $0.854 | 163.8K | 32.8K | Reason: YesTools: YesVision: NoCache: Yes | 33.7 | 33.9 | No public latency | 44.6 | LiteLLMOpenRouter | |
GPT 5.4 Nano azure_ai/gpt-5.4-nano 2 gapsBenchmark: live | azure_ai | $0.20 | $1.25 | $1.04 | 1.1M | 128K | Reason: YesTools: YesVision: YesCache: Yes | 43.9 | 44 | No public latency | 43.5 | LiteLLMOpenRouter | |
Minimax.Minimax M2.1 minimax.minimax-m2.1 1 gapsBenchmark: live | bedrock_converse | $0.30 | $1.20 | $1.02 | 1M | 196.6K | Reason: YesTools: YesVision: YesCache: Yes | 32.8 | 39.4 | No public latency | 43 | LiteLLMOpenRouter | |
Llama 3.3 Nemotron Super 49B V1.5 deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5 3 gapsBenchmark: live | deepinfra | $0.10 | $0.40 | $0.34 | 131.1K | 131.1K | Reason: YesTools: YesVision: NoCache: Unknown | 15.1 | 18.7 | No public latency | 42.4 | LiteLLMOpenRouter | |
Hermes 4 70B nousresearch/hermes-4-70b 4 gapsBenchmark: live | nousresearch | $0.13 | $0.40 | $0.346 | 131.1K | No public limit | Reason: YesTools: NoVision: NoCache: Unknown | 14.4 | 16 | No public latency | 40.5 | OpenRouter | |
Minimax.Minimax M2 minimax.minimax-m2 1 gapsBenchmark: live | bedrock_converse | $0.30 | $1.20 | $1.02 | 204.8K | 204.8K | Reason: YesTools: YesVision: NoCache: Yes | 29.2 | 36.1 | No public latency | 39.8 | LiteLLMOpenRouter | |
Qwen3 Coder 480B A35B openrouter/qwen/qwen3-coder 2 gapsBenchmark: live | qwen | $0.22 | $0.95 | $0.804 | 1M | 262.1K | Reason: NoTools: YesVision: NoCache: Unknown | 24.6 | 24.8 | No public latency | 39.7 | LiteLLMOpenRouterBenchmark Seed | |
Nova Lite 1.0 amazon-nova/nova-lite-v1 2 gapsBenchmark: live | amazon_nova | $0.06 | $0.24 | $0.204 | 300K | 10K | Reason: NoTools: YesVision: YesCache: Yes | 5.1 | 12.7 | No public latency | 38.7 | LiteLLMOpenRouter | |
Qwen3 Vl 32b Instruct dashscope/qwen3-vl-32b-instruct 3 gapsBenchmark: live | dashscope | $0.16 | $0.64 | $0.544 | 262.1K | 32.8K | Reason: NoTools: YesVision: YesCache: Unknown | 14.5 | 24.7 | No public latency | 38.4 | LiteLLMOpenRouter | |
Gemma 3n 4B google/gemma-3n-e4b-it 4 gapsBenchmark: live | $0.06 | $0.12 | $0.108 | 32.8K | No public limit | Reason: NoTools: NoVision: NoCache: Unknown | 4.2 | 6.4 | No public latency | 38 | OpenRouter | ||
Qwen 2.5 72b Instruct deepinfra/Qwen/Qwen2.5-72B-Instruct 5 gapsBenchmark: live | hyperbolic | $0.12 | $0.39 | $0.336 | 131.1K | 131.1K | Reason: NoTools: YesVision: NoCache: Unknown | 11.9 | No score | No public latency | 35.4 | LiteLLMOpenRouter | |
Hermes 3 Llama 3.1 70B deepinfra/NousResearch/Hermes-3-Llama-3.1-70B 3 gapsBenchmark: live | nousresearch | $0.30 | $0.30 | $0.30 | 131.1K | 131.1K | Reason: NoTools: YesVision: NoCache: Unknown | 9.2 | 12.6 | No public latency | 35.3 | LiteLLMOpenRouter | |
Reka Flash 3 rekaai/reka-flash-3 3 gapsBenchmark: live | rekaai | $0.10 | $0.20 | $0.18 | 65.5K | 65.5K | Reason: YesTools: NoVision: NoCache: Unknown | 8.9 | 9.5 | No public latency | 33.9 | OpenRouter | |
Glm 4.5 Air vercel_ai_gateway/zai/glm-4.5-air 1 gapsBenchmark: live | vercel_ai_gateway | $0.20 | $1.10 | $0.92 | 131.1K | 131.1K | Reason: YesTools: YesVision: NoCache: Yes | 23.8 | 23.2 | No public latency | 32.8 | LiteLLMOpenRouter | |
Gemini 2.5 Flash Lite gemini-2.5-flash-lite 2 gapsBenchmark: live | vertex_ai-language-models | $0.10 | $0.40 | $0.34 | 1M | 65.5K | Reason: YesTools: YesVision: YesCache: Yes | 9.5 | 17.6 | No public latency | 32.7 | LiteLLMOpenRouter | |
Qwen3 Vl 8b Instruct novita/qwen/qwen3-vl-8b-instruct 3 gapsBenchmark: live | novita | $0.08 | $0.50 | $0.416 | 256K | 32.8K | Reason: NoTools: YesVision: YesCache: Unknown | 7.3 | 14.3 | No public latency | 32 | LiteLLMOpenRouter | |
Qwen3.6 Plus openrouter/qwen/qwen3.6-plus 1 gapsBenchmark: live | openrouter | $0.325 | $1.95 | $1.625 | 1M | 65.5K | Reason: YesTools: YesVision: YesCache: Yes | 42.9 | 50 | No public latency | 31.8 | LiteLLMOpenRouter | |
Mimo V2.5 openrouter/xiaomi/mimo-v2.5 1 gapsBenchmark: live | openrouter | $0.40 | $2.00 | $1.68 | 1M | 131.1K | Reason: YesTools: YesVision: YesCache: Yes | 42.1 | 49 | No public latency | 31.3 | LiteLLMOpenRouter | |
Deepseek V3.2 azure_ai/deepseek-v3.2 1 gapsBenchmark: live | bedrock_converse | $0.58 | $1.68 | $1.46 | 163.8K | 163.8K | Reason: YesTools: YesVision: NoCache: Yes | 36.7 | 41.7 | No public latency | 30.7 | LiteLLMOpenRouter | |
MiniMax M3 minimax/MiniMax-M3 1 gapsBenchmark: live | minimax | $0.60 | $2.40 | $2.04 | 1M | 512K | Reason: YesTools: YesVision: YesCache: Yes | 43.4 | 54.7 | No public latency | 27.7 | LiteLLMOpenRouter | |
INTELLECT-3 prime-intellect/intellect-3 2 gapsBenchmark: live | prime-intellect | $0.20 | $1.10 | $0.92 | 131.1K | 131.1K | Reason: YesTools: YesVision: NoCache: Unknown | 19.1 | 22.2 | No public latency | 27.2 | OpenRouter | |
Nano Banana (Gemini 2.5 Flash Image) google/gemini-2.5-flash-image 4 gapsBenchmark: live | $0.30 | $2.50 | $2.06 | 32.8K | 32.8K | Reason: NoTools: NoVision: YesCache: Yes | No score | No score | No public latency | 26.6 | OpenRouter | ||
Nano Banana 2 (Gemini 3.1 Flash Image Preview) google/gemini-3.1-flash-image-preview 5 gapsBenchmark: live | $0.50 | $3.00 | $2.50 | 131.1K | 65.5K | Reason: YesTools: NoVision: YesCache: Unknown | No score | No score | No public latency | 26.1 | OpenRouter | ||
GLM 4.6V z-ai/glm-4.6v 2 gapsBenchmark: live | z-ai | $0.30 | $0.90 | $0.78 | 131.1K | 32.8K | Reason: YesTools: YesVision: YesCache: Yes | 19.7 | 23.4 | No public latency | 25.9 | OpenRouter | |
Qwen3.5 122b A10b openrouter/qwen/qwen3.5-122b-a10b 3 gapsBenchmark: live | openrouter | $0.40 | $2.00 | $1.68 | 262.1K | 262.1K | Reason: YesTools: YesVision: YesCache: Unknown | 34.7 | 41.6 | No public latency | 25.7 | LiteLLMOpenRouter | |
Gemini 3.1 Flash Lite Preview gemini-3.1-flash-lite-preview 1 gapsBenchmark: live | vertex_ai-language-models | $0.25 | $1.50 | $1.25 | 1M | 65.5K | Reason: YesTools: YesVision: YesCache: Yes | 30.1 | 33.5 | No public latency | 25.6 | LiteLLMOpenRouter | |
GPT 5 Mini azure/gpt-5-mini 1 gapsBenchmark: live | github_copilot | $0.25 | $2.00 | $1.65 | 400K | 128K | Reason: YesTools: YesVision: YesCache: Yes | 35.3 | 41.2 | No public latency | 25.2 | LiteLLMOpenRouter | |
GPT-5 Image Mini openai/gpt-5-image-mini 4 gapsBenchmark: live | openai | $2.50 | $2.00 | $2.10 | 400K | 128K | Reason: YesTools: NoVision: YesCache: Yes | No score | No score | No public latency | 24.7 | OpenRouter | |
Zai.Glm 5 openrouter/z-ai/glm-5 1 gapsBenchmark: live | bedrock_converse | $0.80 | $2.56 | $2.208 | 202.8K | 128K | Reason: YesTools: YesVision: NoCache: Yes | 44.2 | 49.8 | No public latency | 24 | LiteLLMOpenRouter | |
Llama 4 Maverick snowflake/llama4-maverick 2 gapsBenchmark: live | meta-llama | $0.24 | $0.97 | $0.824 | 1M | 16.4K | Reason: NoTools: YesVision: YesCache: Unknown | 15.6 | 18.4 | No public latency | 23.8 | LiteLLMOpenRouter | |
Qwen3.5 Plus 2026-02-15 openrouter/qwen/qwen3.5-plus-02-15 5 gapsBenchmark: live | openrouter | $0.40 | $2.40 | $2.00 | 1M | 65.5K | Reason: YesTools: YesVision: YesCache: Unknown | No score | No score | No public latency | 23.7 | LiteLLMOpenRouter | |
Qwen3 Next 80b A3b Thinking dashscope/qwen3-next-80b-a3b-thinking 3 gapsBenchmark: live | together_ai | $0.15 | $1.20 | $0.99 | 262.1K | 262.1K | Reason: YesTools: YesVision: NoCache: Unknown | 19.5 | 26.7 | No public latency | 23.5 | LiteLLMOpenRouter | |
GPT 5.1 Codex Mini azure/gpt-5.1-codex-mini 1 gapsBenchmark: live | chatgpt | $0.25 | $2.00 | $1.65 | 400K | 128K | Reason: YesTools: YesVision: YesCache: Yes | 36.4 | 38.6 | No public latency | 23.3 | LiteLLMOpenRouter | |
Llama 3 2 1b Instruct watsonx/meta-llama/llama-3-2-1b-instruct 3 gapsBenchmark: live | meta-llama | $0.10 | $0.10 | $0.10 | 131.1K | 128K | Reason: NoTools: YesVision: NoCache: Unknown | 0.6 | 6.3 | No public latency | 23 | LiteLLMOpenRouter | |
Nemotron 3 Ultra nvidia/nemotron-3-ultra-550b-a55b 2 gapsBenchmark: live | nvidia | $0.50 | $2.50 | $2.10 | 1M | 16.4K | Reason: YesTools: YesVision: NoCache: Yes | 37.6 | 47.7 | No public latency | 22.6 | OpenRouter | |
Qwen3.5 35b A3b openrouter/qwen/qwen3.5-35b-a3b 2 gapsBenchmark: live | openrouter | $0.25 | $2.00 | $1.65 | 262.1K | 262.1K | Reason: YesTools: YesVision: YesCache: Yes | 30.3 | 37.1 | No public latency | 22.6 | LiteLLMOpenRouter | |
Grok 4.3 xai/grok-4.3 1 gapsBenchmark: live | x-ai | $1.25 | $2.50 | $2.25 | 1M | 1M | Reason: YesTools: YesVision: YesCache: Yes | 41 | 53.2 | No public latency | 22.5 | LiteLLMOpenRouter | |
Qwen3.5 27b openrouter/qwen/qwen3.5-27b 3 gapsBenchmark: live | openrouter | $0.30 | $2.40 | $1.98 | 262.1K | 65.5K | Reason: YesTools: YesVision: YesCache: Unknown | 34.9 | 42.1 | No public latency | 22.2 | LiteLLMOpenRouter | |
Qwen3 Vl 30b A3b Instruct novita/qwen/qwen3-vl-30b-a3b-instruct 3 gapsBenchmark: live | novita | $0.20 | $0.70 | $0.60 | 262.1K | 32.8K | Reason: NoTools: YesVision: YesCache: Unknown | 14.3 | 16 | No public latency | 22.2 | LiteLLMOpenRouter | |
Mimo V2.5 Pro openrouter/xiaomi/mimo-v2.5-pro 1 gapsBenchmark: live | openrouter | $1.00 | $3.00 | $2.60 | 1M | 131.1K | Reason: YesTools: YesVision: NoCache: Yes | 45.5 | 53.8 | No public latency | 22 | LiteLLMOpenRouter | |
Mistral Large 3 2512 mistral/mistral-large-2512 1 gapsBenchmark: live | openrouter | $0.50 | $1.50 | $1.30 | 262.1K | 262.1K | Reason: NoTools: YesVision: YesCache: Yes | 22.7 | 22.8 | No public latency | 21.4 | LiteLLMOpenRouter | |
GLM 5.1 z-ai/glm-5.1 2 gapsBenchmark: live | z-ai | $0.98 | $3.08 | $2.66 | 202.8K | No public limit | Reason: YesTools: YesVision: NoCache: Yes | 43.4 | 51.4 | No public latency | 20.8 | OpenRouter | |
GPT 4.1 Mini azure/gpt-4.1-mini 1 gapsBenchmark: live | vercel_ai_gateway | $0.40 | $1.60 | $1.36 | 1M | 32.8K | Reason: NoTools: YesVision: YesCache: Yes | 18.5 | 22.9 | No public latency | 20.8 | LiteLLMOpenRouter | |
Qwen 3 32b cerebras/qwen-3-32b 3 gapsBenchmark: live | deepinfra | $0.40 | $0.80 | $0.72 | 131.1K | 131K | Reason: YesTools: YesVision: NoCache: Unknown | 13.8 | 16.5 | No public latency | 20.3 | LiteLLMOpenRouter | |
Cogito v2.1 671B deepcogito/cogito-v2.1-671b 6 gapsBenchmark: live | deepcogito | $1.25 | $1.25 | $1.25 | 128K | No public limit | Reason: YesTools: NoVision: NoCache: Unknown | 24.8 | No score | No public latency | 19.8 | OpenRouter | |
Moonshotai.Kimi K2.5 bedrock/moonshotai.kimi-k2.5 1 gapsBenchmark: live | bedrock_converse | $0.60 | $3.03 | $2.544 | 262.1K | 262.1K | Reason: YesTools: YesVision: YesCache: Yes | 39.6 | 46.8 | No public latency | 19.6 | LiteLLMOpenRouter | |
Gemini 3 Flash Preview vertex_ai/gemini-3-flash-preview 1 gapsBenchmark: live | vertex_ai-language-models | $0.50 | $3.00 | $2.50 | 1M | 65.5K | Reason: YesTools: YesVision: YesCache: Yes | 42.6 | 46.4 | No public latency | 19.1 | LiteLLMOpenRouter | |
Qwen3.6 27B qwen/qwen3.6-27b 3 gapsBenchmark: live | qwen | $0.287 | $3.10 | $2.5374 | 262.1K | 262.1K | Reason: YesTools: YesVision: YesCache: Unknown | 36.5 | 45.8 | No public latency | 19.1 | OpenRouter | |
Qwen3 Vl 30b A3b Thinking novita/qwen/qwen3-vl-30b-a3b-thinking 3 gapsBenchmark: live | novita | $0.20 | $1.00 | $0.84 | 131.1K | 32.8K | Reason: YesTools: YesVision: YesCache: Unknown | 13.1 | 19.7 | No public latency | 18.9 | LiteLLMOpenRouter | |
Qwen3.7 Max qwen/qwen3.7-max 1 gapsBenchmark: live | qwen | $1.25 | $3.75 | $3.25 | 1M | 65.5K | Reason: YesTools: YesVision: NoCache: Yes | 50.1 | 56.6 | No public latency | 17.6 | OpenRouter | |
Llama 3 8b Instruct gradient_ai/llama3-8b-instruct 3 gapsBenchmark: live | gradient_ai | $0.20 | $0.20 | $0.20 | 8.2K | 8.2K | Reason: NoTools: NoVision: NoCache: Unknown | 4 | 6.4 | No public latency | 17.5 | LiteLLMOpenRouter | |
Zai Glm 4.7 cerebras/zai-glm-4.7 1 gapsBenchmark: live | bedrock_converse | $2.25 | $2.75 | $2.65 | 202.8K | 131.1K | Reason: YesTools: YesVision: YesCache: Yes | 36.3 | 42.1 | No public latency | 17.5 | LiteLLMOpenRouter | |
Kimi K2 0905 novita/moonshotai/kimi-k2-0905 2 gapsBenchmark: live | moonshotai | $0.60 | $2.50 | $2.12 | 262.1K | 262.1K | Reason: NoTools: YesVision: NoCache: Unknown | 25.9 | 30.9 | No public latency | 16.8 | LiteLLMOpenRouter | |
Moonshotai.Kimi K2 Thinking bedrock/moonshotai.kimi-k2-thinking 2 gapsBenchmark: live | moonshotai | $0.73 | $3.03 | $2.57 | 262.1K | 262.1K | Reason: YesTools: YesVision: NoCache: Unknown | 34.8 | 40.9 | No public latency | 16.8 | LiteLLMOpenRouter | |
Qwen3 Next 80b A3b Instruct dashscope/qwen3-next-80b-a3b-instruct 3 gapsBenchmark: live | together_ai | $0.15 | $1.20 | $0.99 | 262.1K | 262.1K | Reason: NoTools: YesVision: NoCache: Unknown | 15.3 | 20.1 | No public latency | 16.7 | LiteLLMOpenRouter | |
Kimi K2 0711 vercel_ai_gateway/moonshotai/kimi-k2 2 gapsBenchmark: live | vercel_ai_gateway | $0.55 | $2.20 | $1.87 | 131.1K | 32.8K | Reason: NoTools: YesVision: NoCache: Unknown | 22.1 | 26.3 | No public latency | 16.6 | LiteLLMOpenRouter | |
Glm 4.5 vercel_ai_gateway/zai/glm-4.5 1 gapsBenchmark: live | vercel_ai_gateway | $0.60 | $2.20 | $1.88 | 131.1K | 131.1K | Reason: YesTools: YesVision: NoCache: Yes | 26.3 | 26.4 | No public latency | 16.4 | LiteLLMOpenRouter | |
Kimi K2.6 azure_ai/kimi-k2.6 1 gapsBenchmark: live | moonshotai | $0.95 | $4.00 | $3.39 | 262.1K | 262.1K | Reason: YesTools: YesVision: YesCache: Yes | 47.1 | 53.9 | No public latency | 16.4 | LiteLLMOpenRouter | |
Qwen3.5 397b A17b openrouter/qwen/qwen3.5-397b-a17b 2 gapsBenchmark: live | together_ai | $0.60 | $3.60 | $3.00 | 262.1K | 65.5K | Reason: YesTools: YesVision: YesCache: Unknown | 41.3 | 45 | No public latency | 16.3 | LiteLLMOpenRouter | |
Llama 3.3 70B Instruct azure_ai/Llama-3.3-70B-Instruct 3 gapsBenchmark: live | gradient_ai | $0.71 | $0.71 | $0.71 | 131.1K | 131.1K | Reason: NoTools: YesVision: NoCache: Unknown | 10.7 | 14.5 | No public latency | 16.1 | LiteLLMOpenRouter | |
Mistral Medium 3.1 mistralai/mistral-medium-3.1 2 gapsBenchmark: live | mistralai | $0.40 | $2.00 | $1.68 | 131.1K | No public limit | Reason: NoTools: YesVision: YesCache: Yes | 18.3 | 21.3 | No public latency | 16 | OpenRouter | |
Llama 3.2 11B Vision Instruct azure_ai/Llama-3.2-11B-Vision-Instruct 3 gapsBenchmark: live | meta-llama | $0.37 | $0.37 | $0.37 | 131.1K | 131.1K | Reason: NoTools: YesVision: YesCache: Unknown | 4.2 | 8.7 | No public latency | 16 | LiteLLMOpenRouter | |
Hermes 3 Llama 3.1 405B deepinfra/NousResearch/Hermes-3-Llama-3.1-405B 3 gapsBenchmark: live | nousresearch | $1.00 | $1.00 | $1.00 | 131.1K | 131.1K | Reason: NoTools: YesVision: NoCache: Unknown | 18.1 | 17.6 | No public latency | 15.8 | LiteLLMOpenRouter | |
GLM 5 Turbo z-ai/glm-5-turbo 1 gapsBenchmark: live | z-ai | $1.20 | $4.00 | $3.44 | 262.1K | 131.1K | Reason: YesTools: YesVision: NoCache: Yes | 36.8 | 46.8 | No public latency | 15.1 | OpenRouter | |
Zai Glm 4.6 cerebras/zai-glm-4.6 1 gapsBenchmark: live | vercel_ai_gateway | $2.25 | $2.75 | $2.65 | 202.8K | 200K | Reason: YesTools: YesVision: NoCache: Yes | 29.5 | 32.5 | No public latency | 14.7 | LiteLLMOpenRouter | |
GPT-5.4 mini azure_ai/gpt-5.4-mini 2 gapsBenchmark: live | azure_ai | $0.75 | $4.50 | $3.75 | 1.1M | 128K | Reason: YesTools: YesVision: YesCache: Yes | 51.5 | 48.9 | No public latency | 14.2 | LiteLLMOpenRouterOfficial Catalog | |
Mistral Medium 3 vertex_ai/mistral-medium-3 1 gapsBenchmark: live | vertex_ai-mistral_models | $0.40 | $2.00 | $1.68 | 131.1K | 8.2K | Reason: NoTools: YesVision: YesCache: Yes | 13.6 | 18.8 | No public latency | 14.1 | LiteLLMOpenRouter | |
Nova 2 Lite amazon/nova-2-lite-v1 3 gapsBenchmark: live | amazon | $0.30 | $2.50 | $2.06 | 1M | 65.5K | Reason: YesTools: YesVision: YesCache: Unknown | 23.9 | 29.7 | No public latency | 14 | OpenRouter | |
Gemini 2.5 Flash deepinfra/google/gemini-2.5-flash 1 gapsBenchmark: live | vertex_ai-language-models | $0.30 | $2.50 | $2.06 | 1M | 1M | Reason: YesTools: YesVision: YesCache: Yes | 22.2 | 27 | No public latency | 13.9 | LiteLLMOpenRouter | |
Qwen3 Vl 235b A22b Instruct dashscope/qwen3-vl-235b-a22b-instruct 2 gapsBenchmark: live | dashscope | $0.40 | $1.60 | $1.36 | 262.1K | 32.8K | Reason: NoTools: YesVision: YesCache: Yes | 16.5 | 20.8 | No public latency | 13.8 | LiteLLMOpenRouter | |
Devstral 2 2512 mistral/devstral-2512 2 gapsBenchmark: live | openrouter | $0.40 | $2.00 | $1.68 | 262.1K | 256K | Reason: NoTools: YesVision: NoCache: Yes | 23.7 | 22 | No public latency | 13.4 | LiteLLMOpenRouter | |
Qwen3 235B A22B Thinking 2507 deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507 1 gapsBenchmark: live | together_ai | $0.30 | $2.90 | $2.38 | 262.1K | 262.1K | Reason: YesTools: YesVision: NoCache: Yes | 23.2 | 29.5 | No public latency | 12.6 | LiteLLMOpenRouter | |
Qwen3 VL 8B Thinking qwen/qwen3-vl-8b-thinking 3 gapsBenchmark: live | qwen | $0.117 | $1.365 | $1.1154 | 256K | 32.8K | Reason: YesTools: YesVision: YesCache: Unknown | 9.8 | 16.7 | No public latency | 12.6 | OpenRouter | |
MiniMax M1 minimax/minimax-m1 3 gapsBenchmark: live | minimax | $0.40 | $2.20 | $1.84 | 1M | 40K | Reason: YesTools: YesVision: NoCache: Unknown | 14.5 | 24.4 | No public latency | 12.3 | OpenRouter | |
Qwen3 Max Thinking qwen/qwen3-max-thinking 3 gapsBenchmark: live | qwen | $0.78 | $3.90 | $3.276 | 262.1K | 32.8K | Reason: YesTools: YesVision: NoCache: Unknown | 30.5 | 39.8 | No public latency | 12.2 | OpenRouter | |
Deepseek R1 Distill Llama 70b gradient_ai/deepseek-r1-distill-llama-70b 5 gapsBenchmark: live | vercel_ai_gateway | $0.99 | $0.99 | $0.99 | 131.1K | 131.1K | Reason: YesTools: YesVision: NoCache: Unknown | 11.4 | No score | No public latency | 11.5 | LiteLLMOpenRouter | |
Qwen3.6 Max Preview qwen/qwen3.6-max-preview 2 gapsBenchmark: live | qwen | $1.04 | $6.24 | $5.20 | 262.1K | 65.5K | Reason: YesTools: YesVision: NoCache: Yes | 44.9 | 51.8 | No public latency | 10.4 | OpenRouter | |
Llama 3.1 70b Instruct perplexity/llama-3.1-70b-instruct 3 gapsBenchmark: live | perplexity | $1.00 | $1.00 | $1.00 | 131.1K | 131.1K | Reason: NoTools: YesVision: NoCache: Unknown | 10.9 | 12.5 | No public latency | 9.5 | LiteLLMOpenRouter | |
O4 Mini azure/o4-mini 1 gapsBenchmark: live | vercel_ai_gateway | $1.10 | $4.40 | $3.74 | 200K | 100K | Reason: YesTools: YesVision: YesCache: Yes | 25.6 | 33.1 | No public latency | 9.4 | LiteLLMOpenRouter | |
Claude Haiku 4.5 azure_ai/claude-haiku-4-5 1 gapsBenchmark: live | vertex_ai-anthropic_models | $1.00 | $5.00 | $4.20 | 200K | 200K | Reason: YesTools: YesVision: YesCache: Yes | 32.6 | 37.1 | No public latency | 9.2 | LiteLLMOpenRouterOfficial Catalog | |
Claude 3 Haiku openrouter/anthropic/claude-3-haiku 2 gapsBenchmark: live | vertex_ai-anthropic_models | $0.25 | $1.25 | $1.05 | 200K | 4.1K | Reason: NoTools: YesVision: YesCache: Yes | 6.7 | 12.3 | No public latency | 8.3 | LiteLLMOpenRouter | |
Ft:GPT 3.5 Turbo azure/gpt-3.5-turbo 4 gapsBenchmark: live | vercel_ai_gateway | $0.50 | $1.50 | $1.30 | 16.4K | 4.1K | Reason: NoTools: YesVision: NoCache: Yes | 10.7 | No score | No public latency | 8.2 | LiteLLMOpenRouter | |
Glm 4.5v zai/glm-4.5v 2 gapsBenchmark: live | z-ai | $0.60 | $1.80 | $1.56 | 128K | 32K | Reason: YesTools: YesVision: YesCache: Yes | 10.9 | 15.1 | No public latency | 7.9 | LiteLLMOpenRouter | |
Qwen3 Vl 235b A22b Thinking dashscope/qwen3-vl-235b-a22b-thinking 3 gapsBenchmark: live | dashscope | $0.40 | $4.00 | $3.28 | 131.1K | 32.8K | Reason: YesTools: YesVision: YesCache: Unknown | 20.9 | 27.6 | No public latency | 7.7 | LiteLLMOpenRouter | |
Gemini 3.5 Flash vertex_ai/gemini-3.5-flash 1 gapsBenchmark: live | vertex_ai-language-models | $1.50 | $9.00 | $7.50 | 1M | 65.5K | Reason: YesTools: YesVision: YesCache: Yes | 45 | 55.3 | No public latency | 7.7 | LiteLLMOpenRouter | |
Llama 3 70b Instruct openrouter/meta-llama/llama-3-70b-instruct 3 gapsBenchmark: live | openrouter | $0.59 | $0.79 | $0.75 | 8.2K | 8K | Reason: NoTools: NoVision: NoCache: Unknown | 6.8 | 8.9 | No public latency | 6.9 | LiteLLMOpenRouter | |
Mistral Medium 3.5 mistralai/mistral-medium-3-5 4 gapsBenchmark: live | mistralai | $1.50 | $7.50 | $6.30 | 262.1K | No public limit | Reason: YesTools: YesVision: YesCache: Unknown | 35.4 | 39.2 | No public latency | 6.8 | OpenRouter | |
Nano Banana Pro (Gemini 3 Pro Image Preview) google/gemini-3-pro-image-preview 4 gapsBenchmark: live | $2.00 | $12.00 | $10.00 | 65.5K | 32.8K | Reason: YesTools: NoVision: YesCache: Yes | No score | No score | No public latency | 6.4 | OpenRouter | ||
O3 azure/o3 1 gapsBenchmark: live | vercel_ai_gateway | $2.00 | $8.00 | $6.80 | 200K | 100K | Reason: YesTools: YesVision: YesCache: Yes | 38.4 | 38.4 | No public latency | 6.1 | LiteLLMOpenRouter | |
Hermes 4 405B nousresearch/hermes-4-405b 4 gapsBenchmark: live | nousresearch | $1.00 | $3.00 | $2.60 | 131.1K | No public limit | Reason: YesTools: NoVision: NoCache: Unknown | 16 | 18.6 | No public latency | 6 | OpenRouter | |
GPT 5.1 azure/gpt-5.1 1 gapsBenchmark: live | github_copilot | $1.25 | $10.00 | $8.25 | 409.6K | 128K | Reason: YesTools: YesVision: YesCache: Yes | 44.7 | 47.7 | No public latency | 5.9 | LiteLLMOpenRouter | |
GPT 5 azure/gpt-5 1 gapsBenchmark: live | github_copilot | $1.25 | $10.00 | $8.25 | 409.6K | 128K | Reason: YesTools: YesVision: YesCache: Yes | 36 | 44.6 | No public latency | 5.8 | LiteLLMOpenRouter | |
Gemini 3.1 Pro Preview gemini-3.1-pro-preview 1 gapsBenchmark: live | vertex_ai-language-models | $2.00 | $12.00 | $10.00 | 1M | 65.5K | Reason: YesTools: YesVision: YesCache: Yes | 55.5 | 57.2 | No public latency | 5.7 | LiteLLMOpenRouter | |
O3 Mini High openrouter/openai/o3-mini-high 2 gapsBenchmark: live | openrouter | $1.10 | $4.40 | $3.74 | 200K | 100K | Reason: YesTools: YesVision: NoCache: Yes | 17.3 | 25.2 | No public latency | 5.6 | LiteLLMOpenRouter | |
GPT-5 Image openai/gpt-5-image 4 gapsBenchmark: live | openai | $10.00 | $10.00 | $10.00 | 400K | 128K | Reason: YesTools: NoVision: YesCache: Yes | No score | No score | No public latency | 5.5 | OpenRouter | |
GPT 5.1 Codex azure/gpt-5.1-codex 1 gapsBenchmark: live | openai | $1.25 | $10.00 | $8.25 | 400K | 128K | Reason: YesTools: YesVision: YesCache: Yes | 36.6 | 43.1 | No public latency | 5.5 | LiteLLMOpenRouter | |
GPT 5 Codex azure/gpt-5-codex 1 gapsBenchmark: live | openrouter | $1.25 | $10.00 | $8.25 | 400K | 128K | Reason: YesTools: YesVision: YesCache: Yes | 38.9 | 44.6 | No public latency | 5.4 | LiteLLMOpenRouter | |
Qwen3 Max dashscope/qwen3-max 1 gapsBenchmark: live | dashscope | $2.11 | $8.45 | $7.182 | 262.1K | 65.5K | Reason: YesTools: YesVision: NoCache: Yes | 26.4 | 31.4 | No public latency | 5 | LiteLLMOpenRouter | |
Gemini 2.5 Pro deepinfra/google/gemini-2.5-pro 1 gapsBenchmark: live | $1.25 | $10.00 | $8.25 | 1M | 1M | Reason: YesTools: YesVision: YesCache: Yes | 32 | 34.6 | No public latency | 4.8 | LiteLLMOpenRouterBenchmark Seed | ||
O3 Mini azure/o3-mini 4 gapsBenchmark: live | vercel_ai_gateway | $1.10 | $4.40 | $3.74 | 200K | 100K | Reason: YesTools: YesVision: NoCache: Yes | 17.9 | No score | No public latency | 4.8 | LiteLLMOpenRouter | |
GPT-5.4 azure_ai/gpt-5.4 1 gapsBenchmark: live | azure_ai | $2.50 | $15.00 | $12.50 | 1.1M | 128K | Reason: YesTools: YesVision: YesCache: Yes | 57.2 | 56.8 | No public latency | 4.7 | LiteLLMOpenRouterOfficial Catalog | |
GPT 4.1 azure/gpt-4.1 1 gapsBenchmark: live | openai | $2.00 | $8.00 | $6.80 | 1M | 32.8K | Reason: NoTools: YesVision: YesCache: Yes | 21.8 | 26.3 | No public latency | 4.6 | LiteLLMOpenRouterBenchmark Seed | |
Nova Pro 1.0 amazon-nova/nova-pro-v1 1 gapsBenchmark: live | amazon_nova | $0.80 | $3.20 | $2.72 | 300K | 10K | Reason: NoTools: YesVision: YesCache: Yes | 11 | 13.5 | No public latency | 4.6 | LiteLLMOpenRouter | |
GPT 5.3 Codex azure/gpt-5.3-codex 1 gapsBenchmark: live | github_copilot | $1.75 | $14.00 | $11.55 | 400K | 128K | Reason: YesTools: YesVision: YesCache: Yes | 53.1 | 53.6 | No public latency | 4.6 | LiteLLMOpenRouter | |
GPT 5.2 azure/gpt-5.2 1 gapsBenchmark: live | github_copilot | $1.75 | $14.00 | $11.55 | 409.6K | 128K | Reason: YesTools: YesVision: YesCache: Yes | 48.7 | 51.3 | No public latency | 4.6 | LiteLLMOpenRouter | |
Claude Sonnet 4.6 azure_ai/claude-sonnet-4-6 1 gapsBenchmark: live | vertex_ai-anthropic_models | $3.00 | $15.00 | $12.60 | 1M | 128K | Reason: YesTools: YesVision: YesCache: Yes | 50.9 | 51.7 | No public latency | 4.5 | LiteLLMOpenRouterOfficial Catalog | |
GPT 4o azure/gpt-4o 4 gapsBenchmark: live | vercel_ai_gateway | $2.50 | $10.00 | $8.50 | 131.1K | 16.4K | Reason: NoTools: YesVision: YesCache: Yes | No score | No score | No public latency | 4.4 | LiteLLMOpenRouter | |
GPT 5.2 Codex azure/gpt-5.2-codex 1 gapsBenchmark: live | openrouter | $1.75 | $14.00 | $11.55 | 400K | 128K | Reason: YesTools: YesVision: YesCache: Yes | 43 | 49 | No public latency | 4.2 | LiteLLMOpenRouter | |
Xai.Grok 4.20 oci/xai.grok-4.20 2 gapsBenchmark: live | x-ai | $3.00 | $15.00 | $12.60 | 2M | 131.1K | Reason: YesTools: YesVision: YesCache: Yes | 40.5 | 49.3 | No public latency | 3.8 | LiteLLMOpenRouter | |
Claude 3 5 Haiku heroku/claude-3-5-haiku 2 gapsBenchmark: live | vertex_ai-anthropic_models | $1.00 | $5.00 | $4.20 | 200K | 8.2K | Reason: NoTools: YesVision: YesCache: Yes | 10.7 | 18.7 | No public latency | 3.7 | LiteLLMOpenRouter | |
Claude Sonnet 4 5 azure_ai/claude-sonnet-4-5 1 gapsBenchmark: live | anthropic | $3.00 | $15.00 | $12.60 | 1M | 1M | Reason: YesTools: YesVision: YesCache: Yes | 38.6 | 43 | No public latency | 3.7 | LiteLLMOpenRouterBenchmark Seed | |
Claude Sonnet 4 github_copilot/claude-sonnet-4 1 gapsBenchmark: live | vertex_ai-anthropic_models | $3.00 | $15.00 | $12.60 | 1M | 64K | Reason: YesTools: YesVision: YesCache: Yes | 34.1 | 38.7 | No public latency | 3.4 | LiteLLMOpenRouter | |
Claude Opus 4.8 azure_ai/claude-opus-4-8 1 gapsBenchmark: live | vertex_ai-anthropic_models | $5.00 | $25.00 | $21.00 | 1M | 128K | Reason: YesTools: YesVision: YesCache: Yes | 56.7 | 61.4 | No public latency | 3 | LiteLLMOpenRouterOfficial Catalog | |
Claude Opus 4 7 azure_ai/claude-opus-4-7 1 gapsBenchmark: live | vertex_ai-anthropic_models | $5.00 | $25.00 | $21.00 | 1M | 128K | Reason: YesTools: YesVision: YesCache: Yes | 52.5 | 57.3 | No public latency | 2.9 | LiteLLMOpenRouter | |
Deepseek R1 azure_ai/deepseek-r1 2 gapsBenchmark: live | deepseek | $1.35 | $5.40 | $4.59 | 163.8K | 32.8K | Reason: YesTools: YesVision: NoCache: Yes | 15.9 | 18.8 | No public latency | 2.8 | LiteLLMOpenRouterBenchmark Seed | |
Claude Opus 4 6 azure_ai/claude-opus-4-6 1 gapsBenchmark: live | vertex_ai-anthropic_models | $5.00 | $25.00 | $21.00 | 1M | 128K | Reason: YesTools: YesVision: YesCache: Yes | 48.1 | 52.9 | No public latency | 2.8 | LiteLLMOpenRouter | |
Claude Opus 4 5 azure_ai/claude-opus-4-5 1 gapsBenchmark: live | vertex_ai-anthropic_models | $5.00 | $25.00 | $21.00 | 409.6K | 64K | Reason: YesTools: YesVision: YesCache: Yes | 47.8 | 49.7 | No public latency | 2.6 | LiteLLMOpenRouter | |
GPT 5 Chat azure/gpt-5-chat 4 gapsBenchmark: live | openrouter | $1.25 | $10.00 | $8.25 | 128K | 16.4K | Reason: YesTools: YesVision: YesCache: Yes | 21.2 | No score | No public latency | 2.6 | LiteLLMOpenRouter | |
Mistral Large 2407 azure_ai/mistral-large-2407 2 gapsBenchmark: live | vertex_ai-mistral_models | $2.00 | $6.00 | $5.20 | 131.1K | 128K | Reason: NoTools: YesVision: NoCache: Yes | 13.8 | 15.1 | No public latency | 2.5 | LiteLLMOpenRouter | |
GPT-5.5 azure/gpt-5.5 1 gapsBenchmark: live | openai | $5.00 | $30.00 | $25.00 | 1.1M | 128K | Reason: YesTools: YesVision: YesCache: Yes | 59.1 | 60.2 | No public latency | 2.5 | LiteLLMOpenRouterOfficial Catalog | |
GPT-4o (2024-05-13) azure/gpt-4o-2024-05-13 4 gapsBenchmark: live | github_copilot | $5.00 | $15.00 | $13.00 | 128K | 4.1K | Reason: NoTools: YesVision: YesCache: Yes | 24.2 | No score | No public latency | 1.9 | LiteLLMOpenRouter | |
Nova Premier 1.0 amazon-nova/nova-premier-v1 1 gapsBenchmark: live | amazon_nova | $2.50 | $12.50 | $10.50 | 1M | 32K | Reason: NoTools: YesVision: YesCache: Yes | 13.8 | 19 | No public latency | 1.8 | LiteLLMOpenRouter | |
Ft:GPT 4o 2024 08 06 azure/gpt-4o-2024-08-06 2 gapsBenchmark: live | github_copilot | $2.50 | $10.00 | $8.50 | 128K | 16.4K | Reason: NoTools: YesVision: YesCache: Yes | 16.6 | 18.6 | No public latency | 1.8 | LiteLLMOpenRouter | |
Claude Fable 5 azure_ai/claude-fable-5 1 gapsBenchmark: live | vertex_ai-anthropic_models | $10.00 | $50.00 | $42.00 | 1M | 128K | Reason: YesTools: YesVision: YesCache: Yes | 62 | 64.9 | No public latency | 1.7 | LiteLLMOpenRouterOfficial Catalog | |
Ft:GPT 4o 2024 11 20 azure/gpt-4o-2024-11-20 2 gapsBenchmark: live | github_copilot | $2.75 | $11.00 | $9.35 | 128K | 16.4K | Reason: NoTools: YesVision: YesCache: Yes | 16.7 | 17.3 | No public latency | 1.5 | LiteLLMOpenRouter | |
Jamba Large 1.7 jamba-large-1.7 3 gapsBenchmark: live | ai21 | $2.00 | $8.00 | $6.80 | 256K | 256K | Reason: NoTools: YesVision: NoCache: Unknown | 7.8 | 10.9 | No public latency | 1.1 | LiteLLMOpenRouter | |
GPT 4 Turbo azure/gpt-4-turbo 4 gapsBenchmark: live | vercel_ai_gateway | $10.00 | $30.00 | $26.00 | 128K | 4.1K | Reason: NoTools: YesVision: YesCache: Yes | 21.5 | No score | No public latency | 0.8 | LiteLLMOpenRouter | |
Claude Opus 4 1 azure_ai/claude-opus-4-1 3 gapsBenchmark: live | vertex_ai-anthropic_models | $15.00 | $75.00 | $63.00 | 200K | 32K | Reason: YesTools: YesVision: YesCache: Yes | 36.5 | No score | No public latency | 0.7 | LiteLLMOpenRouter | |
Claude Opus 4 gmi/anthropic/claude-opus-4 3 gapsBenchmark: live | vertex_ai-anthropic_models | $15.00 | $75.00 | $63.00 | 409.6K | 32K | Reason: YesTools: YesVision: YesCache: Yes | 34 | No score | No public latency | 0.7 | LiteLLMOpenRouter | |
O1 azure/o1 2 gapsBenchmark: live | vercel_ai_gateway | $15.00 | $60.00 | $51.00 | 200K | 100K | Reason: YesTools: YesVision: YesCache: Yes | 20.5 | 30.7 | No public latency | 0.5 | LiteLLMOpenRouter | |
GPT 4 azure/gpt-4 4 gapsBenchmark: live | github_copilot | $30.00 | $60.00 | $54.00 | 32.8K | 4.1K | Reason: NoTools: YesVision: NoCache: Yes | 13.1 | No score | No public latency | 0.2 | LiteLLMOpenRouter | |
Phi 4 Mini Instruct wandb/microsoft/Phi-4-mini-instruct 2 gapsBenchmark: live | microsoft | $8,000.00 | $35,000.00 | $29,600.00 | 131.1K | 128K | Reason: NoTools: NoVision: NoCache: Yes | 3.6 | 8.4 | No public latency | 0 | LiteLLMOpenRouter | |
Llama 3.1 405b Instruct meta-llama/llama-3.1-405b-instruct 9 gapsBenchmark: stale estimate | meta-llama | No public price | No public price | No public price | No public limit | No public limit | Reason: UnknownTools: UnknownVision: UnknownCache: Unknown | 66 | 68 | No public latency | No score | Benchmark Seed | |
Anthropic Claude Haiku Latest ~anthropic/claude-haiku-latest 5 gapsBenchmark: missing | ~anthropic | $1.00 | $5.00 | $4.20 | 200K | 64K | Reason: YesTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | OpenRouter | |
Anthropic Claude Sonnet Latest ~anthropic/claude-sonnet-latest 5 gapsBenchmark: missing | ~anthropic | $3.00 | $15.00 | $12.60 | 1M | 128K | Reason: YesTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | OpenRouter | |
Claude Fable Latest ~anthropic/claude-fable-latest 5 gapsBenchmark: missing | ~anthropic | $10.00 | $50.00 | $42.00 | 1M | 128K | Reason: YesTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | OpenRouter | |
Claude Opus Latest ~anthropic/claude-opus-latest 5 gapsBenchmark: missing | ~anthropic | $5.00 | $25.00 | $21.00 | 1M | 128K | Reason: YesTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | OpenRouter | |
Google Gemini Flash Latest gemini/gemini-flash-latest 5 gapsBenchmark: missing | $0.30 | $2.50 | $2.06 | 1M | 65.5K | Reason: YesTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | LiteLLMOpenRouter | ||
Google Gemini Pro Latest gemini-pro-latest 5 gapsBenchmark: missing | $1.25 | $10.00 | $8.25 | 1M | 65.5K | Reason: YesTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | LiteLLMOpenRouter | ||
MoonshotAI Kimi Latest moonshot/kimi-latest 5 gapsBenchmark: missing | ~moonshotai | $2.00 | $5.00 | $4.40 | 262.1K | 262.1K | Reason: YesTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | LiteLLMOpenRouter | |
OpenAI GPT Latest ~openai/gpt-latest 5 gapsBenchmark: missing | ~openai | $5.00 | $30.00 | $25.00 | 1.1M | 128K | Reason: YesTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | OpenRouter | |
OpenAI GPT Mini Latest ~openai/gpt-mini-latest 5 gapsBenchmark: missing | ~openai | $0.75 | $4.50 | $3.75 | 400K | 128K | Reason: YesTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | OpenRouter | |
J2 Light j2-light 9 gapsBenchmark: missing | ai21 | $3.00 | $3.00 | $3.00 | 8.2K | 8.2K | Reason: UnknownTools: UnknownVision: UnknownCache: Unknown | No score | No score | No public latency | No score | LiteLLM | |
J2 Mid j2-mid 9 gapsBenchmark: missing | ai21 | $10.00 | $10.00 | $10.00 | 8.2K | 8.2K | Reason: UnknownTools: UnknownVision: UnknownCache: Unknown | No score | No score | No public latency | No score | LiteLLM | |
J2 Ultra j2-ultra 9 gapsBenchmark: missing | ai21 | $15.00 | $15.00 | $15.00 | 8.2K | 8.2K | Reason: UnknownTools: UnknownVision: UnknownCache: Unknown | No score | No score | No public latency | No score | LiteLLM | |
Jamba Large 1.6 jamba-large-1.6 9 gapsBenchmark: missing | ai21 | $2.00 | $8.00 | $6.80 | 256K | 256K | Reason: UnknownTools: UnknownVision: UnknownCache: Unknown | No score | No score | No public latency | No score | LiteLLM | |
Jamba Mini 1.6 jamba-mini-1.6 9 gapsBenchmark: missing | ai21 | $0.20 | $0.40 | $0.36 | 256K | 256K | Reason: UnknownTools: UnknownVision: UnknownCache: Unknown | No score | No score | No public latency | No score | LiteLLM | |
Jamba Mini 1.7 jamba-mini-1.7 9 gapsBenchmark: missing | ai21 | $0.20 | $0.40 | $0.36 | 256K | 256K | Reason: UnknownTools: UnknownVision: UnknownCache: Unknown | No score | No score | No public latency | No score | LiteLLM | |
Aion-1.0 aion-labs/aion-1.0 6 gapsBenchmark: missing | aion-labs | $4.00 | $8.00 | $7.20 | 131.1K | 32.8K | Reason: YesTools: NoVision: NoCache: Unknown | No score | No score | No public latency | No score | OpenRouter | |
Aion-1.0-Mini aion-labs/aion-1.0-mini 6 gapsBenchmark: missing | aion-labs | $0.70 | $1.40 | $1.26 | 131.1K | 32.8K | Reason: YesTools: NoVision: NoCache: Unknown | No score | No score | No public latency | No score | OpenRouter | |
Aion-2.0 aion-labs/aion-2.0 5 gapsBenchmark: missing | aion-labs | $0.80 | $1.60 | $1.44 | 131.1K | 32.8K | Reason: YesTools: NoVision: NoCache: Yes | No score | No score | No public latency | No score | OpenRouter | |
Aion-RP 1.0 (8B) aion-labs/aion-rp-llama-3.1-8b 6 gapsBenchmark: missing | aion-labs | $0.80 | $1.60 | $1.44 | 32.8K | 32.8K | Reason: NoTools: NoVision: NoCache: Unknown | No score | No score | No public latency | No score | OpenRouter | |
Magnum v4 72B anthracite-org/magnum-v4-72b 6 gapsBenchmark: missing | anthracite-org | $3.00 | $5.00 | $4.60 | 32.8K | 2K | Reason: NoTools: NoVision: NoCache: Unknown | No score | No score | No public latency | No score | OpenRouter | |
Claude 4 Opus 20250514 claude-4-opus-20250514 5 gapsBenchmark: missing | anthropic | $15.00 | $75.00 | $63.00 | 200K | 32K | Reason: YesTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | LiteLLM | |
Claude 4 Sonnet 20250514 claude-4-sonnet-20250514 5 gapsBenchmark: missing | anthropic | $3.00 | $15.00 | $12.60 | 1M | 64K | Reason: YesTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | LiteLLM | |
Claude Opus 4 6 20260205 claude-opus-4-6-20260205 5 gapsBenchmark: missing | anthropic | $5.00 | $25.00 | $21.00 | 1M | 128K | Reason: YesTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | LiteLLM | |
Claude Opus 4 7 20260416 claude-opus-4-7-20260416 5 gapsBenchmark: missing | anthropic | $5.00 | $25.00 | $21.00 | 1M | 128K | Reason: YesTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | LiteLLM | |
Claude Opus 4.7 (Fast) anthropic/claude-opus-4.7-fast 5 gapsBenchmark: missing | anthropic | $30.00 | $150.00 | $126.00 | 1M | 128K | Reason: YesTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | OpenRouter | |
Claude Opus 4.8 (Fast) anthropic/claude-opus-4.8-fast 5 gapsBenchmark: missing | anthropic | $10.00 | $50.00 | $42.00 | 1M | 128K | Reason: YesTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | OpenRouter | |
CodeLlama 34b Instruct Hf anyscale/codellama/CodeLlama-34b-Instruct-hf 9 gapsBenchmark: missing | anyscale | $1.00 | $1.00 | $1.00 | 4.1K | 4.1K | Reason: UnknownTools: UnknownVision: UnknownCache: Unknown | No score | No score | No public latency | No score | LiteLLM | |
CodeLlama 70b Instruct Hf anyscale/codellama/CodeLlama-70b-Instruct-hf 9 gapsBenchmark: missing | anyscale | $1.00 | $1.00 | $1.00 | 4.1K | 4.1K | Reason: UnknownTools: UnknownVision: UnknownCache: Unknown | No score | No score | No public latency | No score | LiteLLM | |
Gemma 7b It anyscale/google/gemma-7b-it 8 gapsBenchmark: missing | anyscale | $0.15 | $0.15 | $0.15 | 8.2K | 8.2K | Reason: UnknownTools: YesVision: UnknownCache: Unknown | No score | No score | No public latency | No score | LiteLLM | |
Llama 2 13b Chat Hf anyscale/meta-llama/Llama-2-13b-chat-hf 9 gapsBenchmark: missing | anyscale | $0.25 | $0.25 | $0.25 | 4.1K | 4.1K | Reason: UnknownTools: UnknownVision: UnknownCache: Unknown | No score | No score | No public latency | No score | LiteLLM | |
Llama 2 70b Chat Hf anyscale/meta-llama/Llama-2-70b-chat-hf 9 gapsBenchmark: missing | anyscale | $1.00 | $1.00 | $1.00 | 4.1K | 4.1K | Reason: UnknownTools: UnknownVision: UnknownCache: Unknown | No score | No score | No public latency | No score | LiteLLM | |
Llama 2 7b Chat Hf anyscale/meta-llama/Llama-2-7b-chat-hf 9 gapsBenchmark: missing | anyscale | $0.15 | $0.15 | $0.15 | 4.1K | 4.1K | Reason: UnknownTools: UnknownVision: UnknownCache: Unknown | No score | No score | No public latency | No score | LiteLLM | |
Mixtral 8x22B Instruct V0.1 anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1 8 gapsBenchmark: missing | anyscale | $0.90 | $0.90 | $0.90 | 65.5K | 65.5K | Reason: UnknownTools: YesVision: UnknownCache: Unknown | No score | No score | No public latency | No score | LiteLLM | |
Zephyr 7b Beta anyscale/HuggingFaceH4/zephyr-7b-beta 9 gapsBenchmark: missing | anyscale | $0.15 | $0.15 | $0.15 | 16.4K | 16.4K | Reason: UnknownTools: UnknownVision: UnknownCache: Unknown | No score | No score | No public latency | No score | LiteLLM | |
Coder Large arcee-ai/coder-large 7 gapsBenchmark: missing | arcee-ai | $0.50 | $0.80 | $0.74 | 32.8K | No public limit | Reason: NoTools: NoVision: NoCache: Unknown | No score | No score | No public latency | No score | OpenRouter | |
Trinity Mini arcee-ai/trinity-mini 6 gapsBenchmark: missing | arcee-ai | $0.045 | $0.15 | $0.129 | 131.1K | 131.1K | Reason: YesTools: YesVision: NoCache: Unknown | No score | No score | No public latency | No score | OpenRouter | |
Virtuoso Large arcee-ai/virtuoso-large 6 gapsBenchmark: missing | arcee-ai | $0.75 | $1.20 | $1.11 | 131.1K | 64K | Reason: NoTools: YesVision: NoCache: Unknown | No score | No score | No public latency | No score | OpenRouter | |
Codex Mini azure/codex-mini 5 gapsBenchmark: missing | azure | $1.50 | $6.00 | $5.10 | 200K | 100K | Reason: YesTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | LiteLLM | |
Computer Use Preview azure/computer-use-preview 5 gapsBenchmark: missing | azure | $3.00 | $12.00 | $10.20 | 8.2K | 1K | Reason: YesTools: YesVision: YesCache: No | No score | No score | No public latency | No score | LiteLLM | |
GPT 35 Turbo 16k 0613 azure/gpt-35-turbo-16k-0613 8 gapsBenchmark: missing | azure | $3.00 | $4.00 | $3.80 | 16.4K | 4.1K | Reason: UnknownTools: YesVision: UnknownCache: Unknown | No score | No score | No public latency | No score | LiteLLM | |
GPT 4 32k azure/gpt-4-32k 9 gapsBenchmark: missing | azure | $60.00 | $120.00 | $108.00 | 32.8K | 4.1K | Reason: UnknownTools: UnknownVision: UnknownCache: Unknown | No score | No score | No public latency | No score | LiteLLM | |
GPT 4 32k 0613 azure/gpt-4-32k-0613 9 gapsBenchmark: missing | azure | $60.00 | $120.00 | $108.00 | 32.8K | 4.1K | Reason: UnknownTools: UnknownVision: UnknownCache: Unknown | No score | No score | No public latency | No score | LiteLLM | |
GPT 4 Turbo Vision Preview azure/gpt-4-turbo-vision-preview 8 gapsBenchmark: missing | azure | $10.00 | $30.00 | $26.00 | 128K | 4.1K | Reason: UnknownTools: UnknownVision: YesCache: Unknown | No score | No score | No public latency | No score | LiteLLM | |
GPT 4.1 2025 04 14 azure/us/gpt-4.1-2025-04-14 6 gapsBenchmark: missing | azure | $2.20 | $8.80 | $7.48 | 1M | 32.8K | Reason: UnknownTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | LiteLLM | |
GPT 4.1 Mini 2025 04 14 azure/us/gpt-4.1-mini-2025-04-14 6 gapsBenchmark: missing | azure | $0.44 | $1.76 | $1.496 | 1M | 32.8K | Reason: UnknownTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | LiteLLM | |
GPT 4.1 Nano 2025 04 14 azure/us/gpt-4.1-nano-2025-04-14 6 gapsBenchmark: missing | azure | $0.11 | $0.44 | $0.374 | 1M | 32.8K | Reason: UnknownTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | LiteLLM | |
GPT 4.5 Preview azure/gpt-4.5-preview 6 gapsBenchmark: missing | azure | $75.00 | $150.00 | $135.00 | 128K | 16.4K | Reason: UnknownTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | LiteLLM | |
GPT 4o 2024 08 06 azure/eu/gpt-4o-2024-08-06 6 gapsBenchmark: missing | azure | $2.75 | $11.00 | $9.35 | 128K | 16.4K | Reason: UnknownTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | LiteLLM | |
GPT 4o 2024 08 06 azure/global-standard/gpt-4o-2024-08-06 6 gapsBenchmark: missing | azure | $2.50 | $10.00 | $8.50 | 128K | 16.4K | Reason: UnknownTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | LiteLLM | |
GPT 4o 2024 08 06 azure/global/gpt-4o-2024-08-06 6 gapsBenchmark: missing | azure | $2.50 | $10.00 | $8.50 | 128K | 16.4K | Reason: UnknownTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | LiteLLM | |
GPT 4o 2024 08 06 azure/us/gpt-4o-2024-08-06 6 gapsBenchmark: missing | azure | $2.75 | $11.00 | $9.35 | 128K | 16.4K | Reason: UnknownTools: YesVision: YesCache: Yes | No score | No score | No public latency | No score | LiteLLM |