AI inference market
Every public model, one screener.
Track model pricing, benchmark coverage, context limits, and capability support across consumer apps, enterprise workflows, research, automation, coding, and agentic systems.
Models
2252
0 filters
Priced
2153/2252
Public token prices
Scored
232/2252
Benchmark coverage
Median blend
$1.30
standard · 20% in / 80% out
1M context
501
Large-window models
Tool ready
1528
Function/tool support
Model screener
Sorted by value descending. Click a model to open its dashboard page.
2252 rows
| Capabilities | Data | ||||||
|---|---|---|---|---|---|---|---|
Ling 3.1 Flash inclusionai/ling-3.1-flash | inclusionai | $0.00 in $0.00 / out $0.00 | 41.1 | 4110.0 | 262.1K | RTVC | 5 gapslive |
Nemotron 3 Ultra (free) nvidia/nemotron-3-ultra-550b-a55b:free | nvidia | $0.00 in $0.00 / out $0.00 | 32.1 | 3210.0 | 1M | RTVC | 2 gapslive |
Nemotron 3 Super (free) nvidia/nemotron-3-super-120b-a12b:free | nvidia | $0.00 in $0.00 / out $0.00 | 17.4 | 1740.0 | 262.1K | RTVC | 3 gapslive |
Nemotron 3.5 Lightning (free) apodex/apodex-1.1-mini:free | thinkingmachines | $0.00 in $0.00 / out $0.00 | 14.9 | 1490.0 | 1M | RTVC | 2 gapslive |
Nemotron 3 Nano Omni (free) nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | nvidia | $0.00 in $0.00 / out $0.00 | 12.1 | 1210.0 | 256K | RTVC | 4 gapslive |
Ling 3.0 Flash VL inclusionai/ling-3.0-flash-vl | inclusionai | $0.0535 in $0.021 / out $0.0616 | 36.8 | 688.1 | 262.1K | RTVC | 2 gapslive |
Ling 3.0 Flash novita/inclusionai/ling-3.0-flash | inclusionai | $0.0546 in $0.021 / out $0.063 | 30.0 | 549.5 | 262.1K | RTVC | 2 gapslive |
Ling 3.0 Flash Fin inclusionai/ling-3.0-flash-fin | inclusionai | $0.107 in $0.042 / out $0.1232 | 35.4 | 331.0 | 262.1K | RTVC | 2 gapslive |
GPT Oss 20b deepinfra/openai/gpt-oss-20b | fireworks_ai | $0.0756 in $0.018 / out $0.09 | 21.9 | 289.7 | 131.1K | RTVC | 3 gapslive |
Mistral Small 3.2 24B mistralai/mistral-small-3.2-24b-instruct | mistralai | $0.2188 in $0.0938 / out $0.25 | 40.3 | 184.2 | 256K | RTVC | 5 gapslive |
Solar Mini 4 upstage/solar-mini4 | upstage | $0.17 in $0.05 / out $0.20 | 29.2 | 171.8 | 524.3K | RTVC | 3 gapslive |
Mimo V2.6 Flash xiaomi_mimo/mimo-v2.6-flash | xiaomi_mimo | $0.252 in $0.14 / out $0.28 | 37.9 | 150.4 | 1.1M | RTVC | 4 gapslive |
MiMo-V2.5 xiaomi/mimo-v2.5 | xiaomi | $0.252 in $0.14 / out $0.28 | 37.4 | 148.4 | 1.1M | RTVC | 1 gapslive |
Qwen3 Coder 30b A3b Instruct scaleway/qwen/qwen3-coder-30b-a3b-instruct | scaleway | $0.238 in $0.07 / out $0.28 | 32.4 | 136.1 | 262.1K | RTVC | 4 gapslive |
Qwen3.5 9B together_ai/Qwen/Qwen3.5-9B | together_ai | $0.14 in $0.10 / out $0.15 | 18.4 | 131.4 | 262.1K | RTVC | 4 gapslive |
Solar Pro 4 upstage/solar-pro4 | upstage | $0.306 in $0.09 / out $0.36 | 39.8 | 130.1 | 524.3K | RTVC | 2 gapslive |
Ministral 3 3B 2512 mistral/ministral-3b-2512 | mistralai | $0.10 in $0.10 / out $0.10 | 11.6 | 116.0 | 131.1K | RTVC | 1 gapslive |
Claude Haiku 5.5 github_copilot/claude-haiku-5.5 | vertex_ai-anthropic_models | $0.42 in $0.10 / out $0.50 | 48.7 | 116.0 | 1M | RTVC | 3 gapslive |
Zai.Glm 4.7 Flash zai.glm-4.7-flash | bedrock_converse | $0.3321 in $0.0605 / out $0.40 | 32.8 | 98.8 | 203K | RTVC | 3 gapslive |
Ministral 3 8B 2512 mistral/ministral-8b-2512 | mistralai | $0.15 in $0.15 / out $0.15 | 14.6 | 97.3 | 262.1K | RTVC | 1 gapslive |
Mercury 2.5 inception/mercury-2.5 | inception | $0.128 in $0.04 / out $0.15 | 12.3 | 96.1 | 260K | RTVC | 4 gapslive |
DeepSeek V4 Flash 0731 azure_ai/DeepSeek-V4-Flash-0731 | qwen_ai_platform | $0.5152 in $0.016 / out $0.64 | 47.1 | 91.4 | 1M | RTVC | 1 gapslive |
GPT 6 Luna azure_ai/gpt-6-luna | github_copilot | $0.42 in $0.10 / out $0.50 | 38.1 | 90.7 | 1.1M | RTVC | 4 gapslive |
Mistral Small 24B Instruct 2501 deepinfra/mistralai/Mistral-Small-24B-Instruct-2501 | together_ai | $0.074 in $0.05 / out $0.08 | 6.7 | 90.5 | 32.8K | RTVC | 5 gapslive |
GPT 5 Nano azure/gpt-5-nano | perplexity | $0.33 in $0.05 / out $0.40 | 29.7 | 90.0 | 400K | RTVC | 3 gapslive |
Deepseek V3.2 Exp novita/deepseek/deepseek-v3.2-exp | deepseek | $0.382 in $0.27 / out $0.41 | 34.3 | 89.8 | 163.8K | RTVC | 4 gapslive |
Hy3 novita/tencent/hy3 | deepinfra | $0.4488 in $0.132 / out $0.528 | 40.2 | 89.6 | 262.1K | RTVC | 4 gapslive |
Deepseek V4 Flash Vision Exp deepseek-v4-flash-vision-exp | fireworks_ai | $0.5606 in $0.2156 / out $0.6468 | 49.1 | 87.6 | 1M | RTVC | 2 gapslive |
Gemini 3.1 Pro Preview (batch) anthropic/claude-haiku-5.5:batch | moonshotai | $0.65 in $0.25 / out $0.75 | 56.3 | 86.6 | 1.1M | RTVC | 1 gapslive |
Llama 3.1 8B Instruct lambda_ai/llama3.1-8b-instruct | perplexity | $0.074 in $0.05 / out $0.08 | 6.2 | 83.8 | 131.1K | RTVC | 3 gapslive |
Codestral 2501 azure_ai/Codestral-2501 | mistral | $0.78 in $0.30 / out $0.90 | 65.3 | 83.7 | 256K | RTVC | 5 gapsstale |
Nemotron 3 5 Lightning nebius/nvidia/Nemotron-3_5-Lightning | nebius | $0.174 in $0.07 / out $0.20 | 14.4 | 82.8 | 1M | RTVC | 2 gapslive |
Ministral 3 14B 2512 mistral/ministral-14b-2512 | mistralai | $0.20 in $0.20 / out $0.20 | 16.1 | 80.5 | 262.1K | RTVC | 1 gapslive |
Gemma 4 26b A4b It gemini/gemma-4-26b-a4b-it | deepinfra | $0.258 in $0.09 / out $0.30 | 19.6 | 76.0 | 262.1K | RTVC | 2 gapslive |
Glm 5.3 Flash zai/glm-5.3-flash | aihubmix | $0.7252 in $0.0261 / out $0.90 | 54.2 | 74.7 | 1M | RTVC | 1 gapslive |
Deepseek V4.1 Flash coralbricks/deepseek-v4.1-flash | coralbricks | $0.5488 in $0.0441 / out $0.675 | 39.5 | 72.0 | 1M | RTVC | 4 gapslive |
Gemma 4 31B It sail/google/gemma-4-31B-it | together_ai | $0.29 in $0.09 / out $0.34 | 20.8 | 71.7 | 262.1K | RTVC | 2 gapslive |
Hy3 preview tencent/hy3-preview | tencent | $0.516 in $0.18 / out $0.60 | 36.1 | 70.0 | 262.1K | RTVC | 2 gapslive |
Step 3.5 Flash stepfun/step-3.5-flash | stepfun | $0.26 in $0.10 / out $0.30 | 17.0 | 65.4 | 262.1K | RTVC | 5 gapslive |
Mimo V2.6 Pro xiaomi_mimo/mimo-v2.6-pro | xiaomi_mimo | $0.783 in $0.435 / out $0.87 | 51.0 | 65.1 | 1.1M | RTVC | 3 gapslive |
GPT 4.1 Nano azure/gpt-4.1-nano | vercel_ai_gateway | $0.34 in $0.10 / out $0.40 | 21.6 | 63.5 | 1M | RTVC | 2 gapslive |
Deepseek Chat deepseek-chat | deepseek | $0.776 in $0.32 / out $0.89 | 47.5 | 61.2 | 163.8K | RTVC | 4 gapslive |
Qwen3 235B A22B Instruct 2507 deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507 | deepinfra | $0.458 in $0.09 / out $0.55 | 26.8 | 58.5 | 262.1K | RTVC | 4 gapslive |
Granite 4.0 Micro ibm-granite/granite-4.0-h-micro | ibm-granite | $0.093 in $0.017 / out $0.112 | 5.1 | 54.8 | 131K | RTVC | 5 gapslive |
Granite 4.2 8b wandb/ibm-granite/granite-4.2-8b | ibm-granite | $0.212 in $0.06 / out $0.25 | 11.6 | 54.7 | 131.1K | RTVC | 2 gapslive |
Deepseek V3.2 azure_ai/deepseek-v3.2 | bedrock_converse | $0.6918 in $0.259 / out $0.80 | 37.4 | 54.1 | 164K | RTVC | 2 gapslive |
Qwen3 30b A3b dashscope/qwen3-30b-a3b | qwen_ai_platform | $0.424 in $0.12 / out $0.50 | 22.9 | 54.0 | 129K | RTVC | 4 gapslive |
Codestral 2508 mistral/codestral-2508 | mistralai | $0.78 in $0.30 / out $0.90 | 41.0 | 52.6 | 256K | RTVC | 4 gapslive |
MiMo-V2.5-Pro xiaomi/mimo-v2.5-pro | xiaomi | $0.783 in $0.435 / out $0.87 | 39.6 | 50.6 | 1.1M | RTVC | 1 gapslive |
GPT 5.6 Luna azure/gpt-5.6-luna | github_copilot | $1.00 in $0.20 / out $1.20 | 50.3 | 50.3 | 1.1M | RTVC | 2 gapslive |
Nova Micro 1.0 amazon-nova/nova-micro-v1 | amazon_nova | $0.119 in $0.035 / out $0.14 | 5.9 | 49.6 | 128K | RTVC | 4 gapslive |
Phi 4 deepinfra/microsoft/phi-4 | deepinfra | $0.126 in $0.07 / out $0.14 | 5.9 | 46.8 | 16.4K | RTVC | 5 gapslive |
Nemotron 3 Super 120b A12b nebius/nvidia/nemotron-3-super-120b-a12b | nebius | $0.376 in $0.08 / out $0.45 | 17.4 | 46.3 | 262.1K | RTVC | 3 gapslive |
Glm 4.5 Air vercel_ai_gateway/zai/glm-4.5-air | vercel_ai_gateway | $0.706 in $0.13 / out $0.85 | 31.9 | 45.2 | 131.1K | RTVC | 3 gapslive |
Minimax.Minimax M2.5 minimax.minimax-m2.5 | bedrock_converse | $0.918 in $0.27 / out $1.08 | 39.0 | 42.5 | 1M | RTVC | 3 gapslive |
Gemma 3 4b It deepinfra/google/gemma-3-4b-it | deepinfra | $0.09 in $0.05 / out $0.10 | 3.8 | 42.2 | 131.1K | RTVC | 4 gapslive |
Qwen3 Coder 480B A35B qwen/qwen3-coder | qwen | $0.86 in $0.30 / out $1.00 | 35.8 | 41.6 | 262.1K | RTVC | 3 gapslive |
Minimax M3 fireworks_ai/minimax-m3 | fireworks_ai | $1.02 in $0.30 / out $1.20 | 41.3 | 40.5 | 1M | RTVC | 1 gapslive |
GPT Oss 120b azure_ai/gpt-oss-120b | fireworks_ai | $0.51 in $0.15 / out $0.60 | 20.4 | 40.0 | 131.1K | RTVC | 1 gapslive |
Nemotron 3 Nano 30b A3b novita/nvidia/nemotron-3-nano-30b-a3b | deepinfra | $0.204 in $0.06 / out $0.24 | 8.1 | 39.7 | 262.1K | RTVC | 2 gapslive |
Minimax.Minimax M2.1 minimax.minimax-m2.1 | bedrock_converse | $1.02 in $0.30 / out $1.20 | 38.5 | 37.8 | 1M | RTVC | 3 gapslive |
DeepSeek V3.1 sambanova/DeepSeek-V3.1 | bedrock_mantle | $0.81 in $0.25 / out $0.95 | 29.9 | 36.9 | 163.8K | RTVC | 3 gapslive |
Qwen3.5 Plus 2026-02-15 qwen/qwen3.5-plus-02-15 | qwen | $1.30 in $0.26 / out $1.56 | 47.2 | 36.3 | 1M | RTVC | 5 gapslive |
DeepSeek V4 Flash 0423 azure_ai/deepseek-v4-flash | qwen_ai_platform | $1.034 in $0.05 / out $1.28 | 37.4 | 36.2 | 1M | RTVC | 1 gapslive |
Reka Flash 3 rekaai/reka-flash-3 | rekaai | $0.18 in $0.10 / out $0.20 | 6.4 | 35.6 | 65.5K | RTVC | 5 gapslive |
Qwen3 14B deepinfra/Qwen/Qwen3-14B | deepinfra | $0.216 in $0.12 / out $0.24 | 7.6 | 35.2 | 41K | RTVC | 3 gapslive |
Deepseek V3.1 Terminus novita/deepseek/deepseek-v3.1-terminus | deepseek | $0.854 in $0.27 / out $1.00 | 30.0 | 35.1 | 163.8K | RTVC | 1 gapslive |
Step 3.7 Flash novita/stepfun/step-3.7-flash | stepfun | $0.96 in $0.20 / out $1.15 | 33.6 | 35.0 | 262.1K | RTVC | 2 gapslive |
Qwen 3 32b cerebras/qwen-3-32b | deepinfra | $0.24 in $0.08 / out $0.28 | 8.3 | 34.6 | 131.1K | RTVC | 3 gapslive |
Minimax M2.7 novita/minimax/minimax-m2.7 | minimax | $1.02 in $0.30 / out $1.20 | 35.1 | 34.4 | 204.8K | RTVC | 1 gapslive |
Qwen3.7 Plus dashscope/qwen3.7-plus | qwen_ai_platform | $1.088 in $0.32 / out $1.28 | 36.8 | 33.8 | 1M | RTVC | 1 gapslive |
Minimax.Minimax M2 minimax.minimax-m2 | bedrock_converse | $1.02 in $0.30 / out $1.20 | 34.1 | 33.4 | 1M | RTVC | 3 gapslive |
Nova Lite 1.0 amazon-nova/nova-lite-v1 | amazon_nova | $0.204 in $0.06 / out $0.24 | 6.7 | 32.8 | 300K | RTVC | 4 gapslive |
Inkling Small deepinfra/thinkingmachines/Inkling-Small | thinkingmachines | $1.05 in $0.45 / out $1.20 | 34.0 | 32.4 | 1M | RTVC | 2 gapslive |
Qwen3.5 35b A3b novita/qwen/qwen3.5-35b-a3b | deepinfra | $0.616 in $0.08 / out $0.75 | 19.3 | 31.3 | 262.1K | RTVC | 4 gapslive |
Qwen3.6 35B A3B sail/Qwen/Qwen3.6-35B-A3B | deepinfra | $0.78 in $0.10 / out $0.95 | 24.4 | 31.3 | 262.1K | RTVC | 2 gapslive |
Gemini 2.5 Flash Lite gemini-2.5-flash-lite | vertex_ai-language-models | $0.34 in $0.10 / out $0.40 | 10.4 | 30.6 | 1M | RTVC | 4 gapslive |
GPT 5.4 Nano azure_ai/gpt-5.4-nano | perplexity | $1.04 in $0.20 / out $1.25 | 30.9 | 29.7 | 400K | RTVC | 2 gapslive |
Llama 3 2 1b Instruct watsonx/meta-llama/llama-3-2-1b-instruct | together_ai | $0.1662 in $0.027 / out $0.201 | 4.8 | 28.9 | 131.1K | RTVC | 5 gapslive |
Qwen3 30B A3B Instruct 2507 nebius/Qwen/Qwen3-30B-A3B-Instruct-2507 | nebius | $0.26 in $0.10 / out $0.30 | 7.5 | 28.9 | 262.1K | RTVC | 5 gapslive |
Llama 4 Maverick snowflake/llama4-maverick | meta-llama | $0.5595 in $0.1875 / out $0.6525 | 16.0 | 28.6 | 1M | RTVC | 1 gapslive |
Trinity Large Thinking arcee-ai/trinity-large-thinking | arcee-ai | $0.69 in $0.25 / out $0.80 | 19.0 | 27.5 | 262.1K | RTVC | 1 gapslive |
Qwen3.6 Plus together_ai/Qwen/Qwen3.6-Plus | together_ai | $1.625 in $0.325 / out $1.95 | 43.6 | 26.8 | 1M | RTVC | 2 gapslive |
Qwen 3.8 27b cerebras/qwen-3.8-27b | deepinfra | $1.848 in $0.04 / out $2.30 | 49.2 | 26.6 | 1M | RTVC | 2 gapslive |
Nano Banana (Gemini 2.5 Flash Image) google/gemini-2.5-flash-image | $2.06 in $0.30 / out $2.50 | 54.6 | 26.5 | 32.8K | RTVC | 4 gapslive | |
Mercury 2 inception/mercury-2 | inception | $0.65 in $0.25 / out $0.75 | 17.2 | 26.5 | 128K | RTVC | 1 gapslive |
Nano Banana 2 (Gemini 3.1 Flash Image Preview) google/gemini-3.1-flash-image-preview | $2.50 in $0.50 / out $3.00 | 64.8 | 25.9 | 65.5K | RTVC | 5 gapslive | |
Longcat 2.0 aihubmix/longcat-2.0 | aihubmix | $1.02 in $0.30 / out $1.20 | 26.1 | 25.6 | 1M | RTVC | 2 gapslive |
Mistral Large 4 0 mistral/mistral-large-4-0 | mistralai | $1.808 in $0.68 / out $2.09 | 45.9 | 25.4 | 1M | RTVC | 4 gapslive |
Mistral Small 2603 mistral/mistral-small-2603 | mistralai | $0.51 in $0.15 / out $0.60 | 12.9 | 25.3 | 262.1K | RTVC | 2 gapslive |
Gemma 3 12b It deepinfra/google/gemma-3-12b-it | deepinfra | $0.13 in $0.05 / out $0.15 | 3.2 | 24.6 | 131.1K | RTVC | 3 gapslive |
Muse Glimmer 30b fireworks_ai/muse-glimmer-30b | fireworks_ai | $1.02 in $0.30 / out $1.20 | 25.0 | 24.5 | 131.1K | RTVC | 2 gapslive |
Zai Glm 5 mistral/zai-glm-5 | bedrock_converse | $1.656 in $0.60 / out $1.92 | 40.3 | 24.3 | 1M | RTVC | 3 gapslive |
GPT-5 Image Mini openai/gpt-5-image-mini | openai | $2.10 in $2.50 / out $2.00 | 50.0 | 23.8 | 400K | RTVC | 4 gapslive |
DeepSeek V4 Pro 0423 azure_ai/deepseek-v4-pro | qwen_ai_platform | $1.7195 in $0.9553 / out $1.9105 | 40.1 | 23.3 | 1M | RTVC | 1 gapslive |
Qwen3 Coder Next novita/qwen/qwen3-coder-next | aihubmix | $0.664 in $0.12 / out $0.80 | 15.4 | 23.2 | 262.1K | RTVC | 2 gapslive |
Glm 4.6 vercel_ai_gateway/zai/glm-4.6 | vercel_ai_gateway | $1.70 in $0.50 / out $2.00 | 38.7 | 22.8 | 204.8K | RTVC | 2 gapslive |
Llama 4 Scout meta-llama/llama-4-scout | meta-llama | $0.508 in $0.18 / out $0.59 | 11.3 | 22.2 | 1.3M | RTVC | 2 gapslive |
Grok Build 0.1 xai/grok-build-0.1 | aihubmix | $1.80 in $1.00 / out $2.00 | 39.4 | 21.9 | 256K | RTVC | 3 gapslive |
Zai.Glm 4.7 zai.glm-4.7 | bedrock_converse | $1.88 in $0.60 / out $2.20 | 39.5 | 21.0 | 204.8K | RTVC | 2 gapslive |
Llama 3.2 3B Instruct deepinfra/meta-llama/Llama-3.2-3B-Instruct | together_ai | $0.274 in $0.05 / out $0.33 | 5.7 | 20.8 | 131.1K | RTVC | 5 gapslive |
Qwen 2.5 72b Instruct deepinfra/Qwen/Qwen2.5-72B-Instruct | together_ai | $0.392 in $0.36 / out $0.40 | 7.7 | 19.6 | 131.1K | RTVC | 5 gapslive |
Moonshotai.Kimi K2.5 bedrock/moonshotai.kimi-k2.5 | bedrock_converse | $2.10 in $0.50 / out $2.50 | 41.2 | 19.6 | 262.1K | RTVC | 2 gapslive |
GPT 5 Mini azure/gpt-5-mini | github_copilot | $1.65 in $0.25 / out $2.00 | 32.0 | 19.4 | 400K | RTVC | 3 gapslive |
Llama 3.1 405B Instruct together_ai/meta-llama/Llama-3.1-405B-Instruct | meta-llama | $3.50 in $3.50 / out $3.50 | 66.8 | 19.1 | 4.1K | RTVC | 5 gapsstale |
GPT 4.1 Mini azure/gpt-4.1-mini | vercel_ai_gateway | $1.36 in $0.40 / out $1.60 | 25.6 | 18.8 | 1M | RTVC | 2 gapslive |
GPT 5.1 Codex Mini azure/gpt-5.1-codex-mini | chatgpt | $1.65 in $0.25 / out $2.00 | 30.3 | 18.4 | 400K | RTVC | 3 gapslive |
Deepseek R1 0528 lambda_ai/deepseek-r1-0528 | lambda_ai | $1.82 in $0.50 / out $2.15 | 33.2 | 18.2 | 163.8K | RTVC | 3 gapslive |
Gemini 3.1 Flash Lite Preview gemini-3.1-flash-lite-preview | vertex_ai-language-models | $1.25 in $0.25 / out $1.50 | 22.7 | 18.2 | 1M | RTVC | 1 gapslive |
Glm 4.5 vercel_ai_gateway/zai/glm-4.5 | vercel_ai_gateway | $1.88 in $0.60 / out $2.20 | 33.7 | 17.9 | 131.1K | RTVC | 3 gapslive |
GPT 4o Mini azure/gpt-4o-mini | openai | $0.51 in $0.15 / out $0.60 | 9.1 | 17.8 | 131.1K | RTVC | 3 gapslive |
Qwen3.5 122b A10b libertai/qwen3.5-122b-a10b | deepinfra | $1.716 in $0.26 / out $2.08 | 30.5 | 17.8 | 262.1K | RTVC | 4 gapslive |
Gemini 3.7 Flash vertex_ai/gemini-3.7-flash | vertex_ai-language-models | $3.15 in $0.75 / out $3.75 | 54.5 | 17.3 | 1M | RTVC | 2 gapslive |
Mistral Medium 3 mistral/mistral-medium-3 | vertex_ai-mistral_models | $1.68 in $0.40 / out $2.00 | 28.8 | 17.1 | 262.1K | RTVC | 3 gapslive |
Moonshotai.Kimi K2 Thinking bedrock/moonshotai.kimi-k2-thinking | bedrock_mantle | $2.12 in $0.60 / out $2.50 | 35.4 | 16.7 | 262.1K | RTVC | 3 gapslive |
Solar Pro 3 upstage/solar-pro-3 | upstage | $0.51 in $0.15 / out $0.60 | 8.5 | 16.7 | 131.1K | RTVC | 2 gapslive |
Llama 3.1 70b Instruct perplexity/llama-3.1-70b-instruct | perplexity | $0.40 in $0.40 / out $0.40 | 6.6 | 16.5 | 131.1K | RTVC | 5 gapslive |
Gemini 3.8 Flash vertex_ai/gemini-3.8-flash | vertex_ai-language-models | $3.15 in $0.75 / out $3.75 | 51.6 | 16.4 | 1M | RTVC | 1 gapslive |
Kimi K2 0711 vercel_ai_gateway/moonshotai/kimi-k2 | vercel_ai_gateway | $1.954 in $0.57 / out $2.30 | 31.9 | 16.3 | 131.1K | RTVC | 4 gapslive |
Xai.Grok 4.20 oci/xai.grok-4.20 | x-ai | $2.25 in $1.25 / out $2.50 | 36.5 | 16.2 | 2M | RTVC | 3 gapslive |
Muse Spark 1.3 meta/muse-spark-1.3 | meta | $3.65 in $1.25 / out $4.25 | 58.7 | 16.1 | 1M | RTVC | 1 gapslive |
Nemotron 3 Ultra 550b A55b nebius/nvidia/Nemotron-3-Ultra-550b-a55b | together_ai | $2.04 in $0.60 / out $2.40 | 32.1 | 15.7 | 1M | RTVC | 1 gapslive |
Qwen3 Vl 30b A3b Instruct novita/qwen/qwen3-vl-30b-a3b-instruct | deepinfra | $0.51 in $0.15 / out $0.60 | 7.9 | 15.5 | 262.1K | RTVC | 5 gapslive |
Gemini 3 Flash Preview vertex_ai/gemini-3-flash-preview | vertex_ai-language-models | $2.50 in $0.50 / out $3.00 | 37.9 | 15.2 | 1M | RTVC | 3 gapslive |
Glm 5.1 dashscope/glm-5.1 | qwen_ai_platform | $2.622 in $0.966 / out $3.036 | 39.7 | 15.1 | 204.8K | RTVC | 1 gapslive |
Gemini 2.5 Flash deepinfra/google/gemini-2.5-flash | vertex_ai-language-models | $2.06 in $0.30 / out $2.50 | 31.1 | 15.1 | 1M | RTVC | 3 gapslive |
Kimi K2 0905 novita/moonshotai/kimi-k2-0905 | moonshotai | $2.12 in $0.60 / out $2.50 | 31.9 | 15.1 | 262.1K | RTVC | 4 gapslive |
Zai Glm 5 3 mistral/zai-glm-5-3 | aihubmix | $3.8558 in $0.079 / out $4.80 | 56.3 | 14.6 | 1M | RTVC | 1 gapslive |
Gemini 3.6 Flash vertex_ai/gemini-3.6-flash | vertex_ai-language-models | $3.15 in $0.75 / out $3.75 | 45.5 | 14.4 | 1M | RTVC | 1 gapslive |
Qwen3 Next 80b A3b Thinking dashscope/qwen3-next-80b-a3b-thinking | qwen_ai_platform | $0.99 in $0.15 / out $1.20 | 14.3 | 14.4 | 262.1K | RTVC | 4 gapslive |
GLM 4.6V z-ai/glm-4.6v | z-ai | $0.78 in $0.30 / out $0.90 | 11.2 | 14.4 | 131.1K | RTVC | 4 gapslive |
Mistral Large 3 2512 mistral/mistral-large-2512 | mistralai | $1.30 in $0.50 / out $1.50 | 18.6 | 14.3 | 262.1K | RTVC | 1 gapslive |
Deepseek V4 Pro 0813 fireworks_ai/deepseek-v4-pro-0813 | fireworks_ai | $3.432 in $1.32 / out $3.96 | 48.7 | 14.2 | 1M | RTVC | 2 gapslive |
Muse Spark 1.2 meta/muse-spark-1.2 | aihubmix | $3.65 in $1.25 / out $4.25 | 51.5 | 14.1 | 1M | RTVC | 1 gapslive |
Kimi K2.6 sail/moonshotai/Kimi-K2.6 | together_ai | $2.858 in $0.65 / out $3.41 | 40.1 | 14.0 | 262.1K | RTVC | 1 gapslive |
Gemini 3.5 Flash Lite gemini-3.5-flash-lite | vertex_ai-language-models | $2.06 in $0.30 / out $2.50 | 28.6 | 13.9 | 1M | RTVC | 2 gapslive |
Kimi K2.7 Code nebius/moonshotai/Kimi-K2.7-Code | together_ai | $2.8142 in $0.6712 / out $3.35 | 39.0 | 13.9 | 262.1K | RTVC | 1 gapslive |
Gemma 3 27b It deepinfra/google/gemma-3-27b-it | deepinfra | $0.376 in $0.08 / out $0.45 | 5.0 | 13.3 | 131.1K | RTVC | 2 gapslive |
Xai.Grok 4.3 vertex_ai/xai/grok-4.3 | bedrock_mantle | $2.25 in $1.25 / out $2.50 | 29.5 | 13.1 | 1M | RTVC | 1 gapslive |
Llama 3.3 70B Instruct azure_ai/Llama-3.3-70B-Instruct | gradient_ai | $0.75 in $0.59 / out $0.79 | 9.8 | 13.1 | 131.1K | RTVC | 3 gapslive |
Qwen3.5 397B A17B nebius/Qwen/Qwen3.5-397B-A17B | together_ai | $2.91 in $0.55 / out $3.50 | 37.3 | 12.8 | 262.1K | RTVC | 3 gapslive |
Saba mistralai/mistral-saba | mistralai | $0.52 in $0.20 / out $0.60 | 6.5 | 12.5 | 32.8K | RTVC | 4 gapslive |
Muse Spark 1.1 meta/muse-spark-1.1 | meta | $3.65 in $1.25 / out $4.25 | 44.9 | 12.3 | 1M | RTVC | 1 gapslive |
Qwen3.6 27b libertai/qwen3.6-27b | deepinfra | $2.624 in $0.32 / out $3.20 | 31.2 | 11.9 | 262.1K | RTVC | 2 gapslive |
GLM 5 Turbo z-ai/glm-5-turbo | z-ai | $3.44 in $1.20 / out $4.00 | 40.1 | 11.7 | 202.8K | RTVC | 3 gapslive |
Qwen3.8 Max (0902) qwen/qwen3.8-max-0902 | qwen | $5.20 in $2.00 / out $6.00 | 59.2 | 11.4 | 1M | RTVC | 2 gapslive |
Qwen3 Vl 8b Instruct novita/qwen/qwen3-vl-8b-instruct | together_ai | $0.65 in $0.25 / out $0.75 | 7.3 | 11.2 | 262.1K | RTVC | 4 gapslive |
Qwen3 Vl 30b A3b Thinking novita/qwen/qwen3-vl-30b-a3b-thinking | novita | $0.858 in $0.29 / out $1.00 | 9.5 | 11.1 | 262.1K | RTVC | 5 gapslive |
Qwen3.7 Max dashscope/qwen3.7-max | qwen_ai_platform | $3.835 in $1.475 / out $4.425 | 42.3 | 11.0 | 1M | RTVC | 1 gapslive |
Xai.Grok 4.6 vertex_ai/xai/grok-4.6 | bedrock_mantle | $5.20 in $2.00 / out $6.00 | 57.0 | 11.0 | 524.3K | RTVC | 1 gapslive |
Mistral Medium 3.1 mistralai/mistral-medium-3.1 | mistralai | $1.68 in $0.40 / out $2.00 | 18.4 | 10.9 | 131.1K | RTVC | 1 gapslive |
Deepseek V3 0324 lambda_ai/deepseek-v3-0324 | lambda_ai | $0.97 in $0.29 / out $1.14 | 10.6 | 10.9 | 163.8K | RTVC | 2 gapslive |
Qwen3.5 27b novita/qwen/qwen3.5-27b | deepinfra | $2.132 in $0.26 / out $2.60 | 22.9 | 10.7 | 262.1K | RTVC | 5 gapslive |
Qwen3 Next 80b A3b Instruct dashscope/qwen3-next-80b-a3b-instruct | qwen_ai_platform | $0.90 in $0.10 / out $1.10 | 9.6 | 10.7 | 262.1K | RTVC | 4 gapslive |
Qwen3.8 2.4T A95B together_ai/Qwen/Qwen3.8-2.4T-A95B | together_ai | $5.20 in $2.00 / out $6.00 | 54.0 | 10.4 | 1M | RTVC | 2 gapslive |
Glm 5v Turbo aihubmix/glm-5v-turbo | aihubmix | $3.44 in $1.20 / out $4.00 | 35.5 | 10.3 | 202.8K | RTVC | 3 gapslive |
Inkling together_ai/thinkingmachines/Inkling | thinkingmachines | $3.44 in $1.00 / out $4.05 | 34.9 | 10.2 | 1M | RTVC | 1 gapslive |
Grok 4.5 xai/grok-4.5 | perplexity | $5.20 in $2.00 / out $6.00 | 51.5 | 9.9 | 500K | RTVC | 1 gapslive |
Hermes 3 Llama 3.1 70B deepinfra/NousResearch/Hermes-3-Llama-3.1-70B | nousresearch | $0.70 in $0.70 / out $0.70 | 6.7 | 9.6 | 131.1K | RTVC | 5 gapslive |
Grok 4.7 xai/grok-4.7 | perplexity | $5.20 in $2.00 / out $6.00 | 47.3 | 9.1 | 524.3K | RTVC | 3 gapslive |
Nova 2 Lite amazon/nova-2-lite-v1 | amazon | $2.06 in $0.30 / out $2.50 | 18.2 | 8.8 | 1M | RTVC | 4 gapslive |
GPT-5.4 mini azure_ai/gpt-5.4-mini | github_copilot | $3.75 in $0.75 / out $4.50 | 32.7 | 8.7 | 400K | RTVC | 2 gapslive |
Zai Glm 5 2 mistral/zai-glm-5-2 | scaleway | $5.612 in $0.06 / out $7.00 | 47.9 | 8.5 | 1M | RTVC | 1 gapslive |
Devstral 2 2512 mistralai/devstral-2512 | mistralai | $1.68 in $0.40 / out $2.00 | 14.1 | 8.4 | 262.1K | RTVC | 2 gapslive |
O4 Mini azure/o4-mini | vercel_ai_gateway | $3.74 in $1.10 / out $4.40 | 31.2 | 8.3 | 200K | RTVC | 3 gapslive |
Sonar perplexity/sonar | vercel_ai_gateway | $1.00 in $1.00 / out $1.00 | 7.7 | 7.7 | 128K | RTVC | 4 gapslive |
Hermes 3 Llama 3.1 405B deepinfra/NousResearch/Hermes-3-Llama-3.1-405B | nousresearch | $1.00 in $1.00 / out $1.00 | 7.4 | 7.4 | 131.1K | RTVC | 5 gapslive |
Claude Sonnet 5 5 claude-sonnet-5-5 | vertex_ai-anthropic_models | $8.40 in $2.00 / out $10.00 | 60.8 | 7.2 | 1M | RTVC | 3 gapslive |
Qwen2.5 Coder 32B Instruct hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct | together_ai | $0.932 in $0.66 / out $1.00 | 6.7 | 7.2 | 131.1K | RTVC | 5 gapslive |
GPT 5.6 Sol azure/gpt-5.6-sol | github_copilot | $8.40 in $2.00 / out $10.00 | 58.2 | 6.9 | 1.1M | RTVC | 2 gapslive |
GPT 6.1 Sol azure_ai/gpt-6.1-sol | github_copilot | $8.40 in $2.00 / out $10.00 | 56.5 | 6.7 | 1.1M | RTVC | 3 gapslive |
Claude Haiku 4.5 azure_ai/claude-haiku-4-5 | vertex_ai-anthropic_models | $4.20 in $1.00 / out $5.00 | 28.2 | 6.7 | 200K | RTVC | 1 gapslive |
Nano Banana Pro (Gemini 3 Pro Image Preview) google/gemini-3-pro-image-preview | $10.00 in $2.00 / out $12.00 | 63.7 | 6.4 | 65.5K | RTVC | 4 gapslive | |
Qwen3 Vl 235b A22b Instruct dashscope/qwen3-vl-235b-a22b-instruct | qwen_ai_platform | $1.562 in $0.21 / out $1.90 | 9.9 | 6.3 | 262.1K | RTVC | 4 gapslive |
Qwen3 235B A22B Thinking 2507 deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507 | deepinfra | $2.89 in $0.45 / out $3.50 | 18.3 | 6.3 | 262.1K | RTVC | 2 gapslive |
MiniMax M1 minimax/minimax-m1 | minimax | $1.87 in $0.55 / out $2.20 | 11.7 | 6.3 | 1M | RTVC | 5 gapslive |
Ft:GPT 3.5 Turbo azure/gpt-3.5-turbo | vercel_ai_gateway | $1.30 in $0.50 / out $1.50 | 8.1 | 6.2 | 16.4K | RTVC | 3 gapslive |
Claude Sonnet 5 azure_ai/claude-sonnet-5 | vertex_ai-anthropic_models | $8.40 in $2.00 / out $10.00 | 51.5 | 6.1 | 1M | RTVC | 1 gapslive |
Gemini 3.5 Flash vertex_ai/gemini-3.5-flash | vertex_ai-language-models | $7.50 in $1.50 / out $9.00 | 43.6 | 5.8 | 1M | RTVC | 3 gapslive |
Deepseek R1 deepseek/deepseek-r1 | deepseek | $2.14 in $0.70 / out $2.50 | 12.4 | 5.8 | 128K | RTVC | 2 gapslive |
GPT 6 Sol azure_ai/gpt-6-sol | github_copilot | $8.40 in $2.00 / out $10.00 | 47.6 | 5.7 | 1.1M | RTVC | 4 gapslive |
GPT 5.6 Terra azure/gpt-5.6-terra | github_copilot | $10.00 in $2.00 / out $12.00 | 54.0 | 5.4 | 1.1M | RTVC | 2 gapslive |
O3 azure/o3 | vercel_ai_gateway | $6.80 in $2.00 / out $8.00 | 36.5 | 5.4 | 200K | RTVC | 3 gapslive |
Moonshotai.Kimi K3 sail/moonshotai/Kimi-K3 | bedrock_converse | $10.946 in $0.73 / out $13.50 | 57.3 | 5.2 | 1M | RTVC | 1 gapslive |
Nova Pro 1.0 amazon-nova/nova-pro-v1 | amazon_nova | $2.72 in $0.80 / out $3.20 | 14.2 | 5.2 | 300K | RTVC | 3 gapslive |
GPT-5 Image openai/gpt-5-image | openai | $10.00 in $10.00 / out $10.00 | 51.8 | 5.2 | 400K | RTVC | 4 gapslive |
GPT 5.1 azure/gpt-5.1 | perplexity | $8.25 in $1.25 / out $10.00 | 42.3 | 5.1 | 409.6K | RTVC | 2 gapslive |
Glm 4.5v zai/glm-4.5v | z-ai | $1.56 in $0.60 / out $1.80 | 7.6 | 4.9 | 128K | RTVC | 4 gapslive |
GPT 5 azure/gpt-5 | perplexity | $8.25 in $1.25 / out $10.00 | 38.6 | 4.7 | 409.6K | RTVC | 2 gapslive |
GPT 4.1 azure/gpt-4.1 | openai | $6.80 in $2.00 / out $8.00 | 31.6 | 4.7 | 1M | RTVC | 3 gapslive |
GPT 5.1 Codex azure/gpt-5.1-codex | openai | $8.25 in $1.25 / out $10.00 | 38.1 | 4.6 | 400K | RTVC | 3 gapslive |
GPT 4o azure/gpt-4o | vercel_ai_gateway | $8.50 in $2.50 / out $10.00 | 37.0 | 4.3 | 131.1K | RTVC | 4 gapslive |
GPT-5.4 azure_ai/gpt-5.4 | github_copilot | $12.50 in $2.50 / out $15.00 | 53.5 | 4.3 | 1.1M | RTVC | 2 gapslive |
Gemini 3.1 Pro Preview gemini-3.1-pro-preview | vertex_ai-language-models | $10.00 in $2.00 / out $12.00 | 39.4 | 3.9 | 1M | RTVC | 1 gapslive |
Claude Sonnet 4.6 azure_ai/claude-sonnet-4-6 | vertex_ai-anthropic_models | $12.60 in $3.00 / out $15.00 | 46.1 | 3.7 | 1M | RTVC | 1 gapslive |
Muse Wonder meta/muse-wonder | meta | $16.80 in $4.00 / out $20.00 | 61.2 | 3.6 | 1M | RTVC | 4 gapslive |
Claude Opus 5 5 azure_ai/claude-opus-5-5 | vertex_ai-anthropic_models | $16.80 in $4.00 / out $20.00 | 60.7 | 3.6 | 1M | RTVC | 3 gapslive |
Mistral Medium 3 5 mistral/mistral-medium-3-5 | mistralai | $6.30 in $1.50 / out $7.50 | 22.7 | 3.6 | 262.1K | RTVC | 2 gapslive |
GPT 5.2 azure/gpt-5.2 | perplexity | $11.55 in $1.75 / out $14.00 | 40.1 | 3.5 | 409.6K | RTVC | 3 gapslive |
GPT 5.3 Codex azure/gpt-5.3-codex | github_copilot | $11.55 in $1.75 / out $14.00 | 38.6 | 3.3 | 400K | RTVC | 3 gapslive |
O3 Mini azure/o3-mini | vercel_ai_gateway | $3.74 in $1.10 / out $4.40 | 12.5 | 3.3 | 200K | RTVC | 4 gapslive |
Gemini 2.5 Pro deepinfra/google/gemini-2.5-pro | $8.25 in $1.25 / out $10.00 | 27.2 | 3.3 | 1M | RTVC | 1 gapslive | |
GPT 5.2 Codex azure/gpt-5.2-codex | chatgpt | $11.55 in $1.75 / out $14.00 | 36.1 | 3.1 | 400K | RTVC | 3 gapslive |
Claude Sonnet 4 gmi/anthropic/claude-sonnet-4 | vercel_ai_gateway | $12.60 in $3.00 / out $15.00 | 37.1 | 2.9 | 409.6K | RTVC | 2 gapslive |
Claude Opus 5 azure_ai/claude-opus-5 | vertex_ai-anthropic_models | $21.00 in $5.00 / out $25.00 | 60.9 | 2.9 | 1M | RTVC | 1 gapslive |
Hermes 4 405B nebius/NousResearch/Hermes-4-405B | nousresearch | $2.60 in $1.00 / out $3.00 | 7.5 | 2.9 | 131.1K | RTVC | 5 gapslive |
Claude Sonnet 4 5 azure_ai/claude-sonnet-4-5 | anthropic | $12.60 in $3.00 / out $15.00 | 34.7 | 2.8 | 1M | RTVC | 1 gapslive |
Claude Opus 4.8 azure_ai/claude-opus-4-8 | vertex_ai-anthropic_models | $21.00 in $5.00 / out $25.00 | 53.8 | 2.6 | 1M | RTVC | 1 gapslive |
o3 Mini High openai/o3-mini-high | openai | $3.74 in $1.10 / out $4.40 | 9.4 | 2.5 | 200K | RTVC | 2 gapslive |
Claude Opus 4 7 azure_ai/claude-opus-4-7 | vertex_ai-anthropic_models | $21.00 in $5.00 / out $25.00 | 51.0 | 2.4 | 1M | RTVC | 2 gapslive |
Claude Opus 4 6 azure_ai/claude-opus-4-6 | vertex_ai-anthropic_models | $21.00 in $5.00 / out $25.00 | 45.8 | 2.2 | 1M | RTVC | 3 gapslive |
Claude Opus 4 5 azure_ai/claude-opus-4-5 | vertex_ai-anthropic_models | $21.00 in $5.00 / out $25.00 | 44.1 | 2.1 | 409.6K | RTVC | 3 gapslive |
GPT-5.5 azure_ai/gpt-5.5 | github_copilot | $25.00 in $5.00 / out $30.00 | 49.4 | 2.0 | 1.1M | RTVC | 1 gapslive |
Sonar Reasoning Pro perplexity/sonar-reasoning-pro | vercel_ai_gateway | $6.80 in $2.00 / out $8.00 | 11.8 | 1.7 | 128K | RTVC | 5 gapslive |
Nova Premier 1.0 amazon-nova/nova-premier-v1 | amazon_nova | $10.50 in $2.50 / out $12.50 | 17.7 | 1.7 | 1M | RTVC | 3 gapslive |
Cohere Command A azure_ai/cohere-command-a | vercel_ai_gateway | $8.50 in $2.50 / out $10.00 | 14.0 | 1.6 | 256K | RTVC | 3 gapslive |
Claude Fable 5 1 azure_ai/claude-fable-5-1 | vertex_ai-anthropic_models | $42.00 in $10.00 / out $50.00 | 63.3 | 1.5 | 1M | RTVC | 1 gapslive |
Mistral Large 2407 azure_ai/mistral-large-2407 | vertex_ai-mistral_models | $5.20 in $2.00 / out $6.00 | 7.6 | 1.5 | 131.1K | RTVC | 4 gapslive |
GPT 6 Astra azure_ai/gpt-6-astra | github_copilot | $42.00 in $10.00 / out $50.00 | 60.2 | 1.4 | 1.1M | RTVC | 2 gapslive |
Claude Fable 5 azure_ai/claude-fable-5 | vertex_ai-anthropic_models | $42.00 in $10.00 / out $50.00 | 59.4 | 1.4 | 1M | RTVC | 1 gapslive |
Showing first 220 rows after filters.
Data sources
Public feeds, static catalog rows, and benchmark seed data stay visible with freshness labels instead of being hidden.
LiteLLM
liveFetched 2026-10-13 07:57:16 UTC
Normalization notes
LiteLLM input_cost_per_token and output_cost_per_token are converted to dollars per 1M tokens.
OpenRouter prompt and completion pricing are interpreted as dollars per token and converted to dollars per 1M tokens. When both LiteLLM and OpenRouter provide token prices for the same model, OpenRouter route pricing is preferred and LiteLLM fills gaps.
LiteLLM long-context tier fields above 272K tokens are preserved separately and can be selected as the dashboard price basis.
Token prices must be zero or positive and no higher than $1,000 per 1M tokens; negative sentinels and unit-mismatched outliers are treated as missing.
OpenRouter router routes such as openrouter/openrouter/auto use variable downstream pricing and are not treated as fixed-price free models.
Official Catalog rows are static public provider-doc entries used to keep frontier models visible when router feeds lag. They do not imply benchmark scores.