model comparison
LLM model comparison
Context window, price, provider and price source for every tracked model — 438 of them, sortable and filterable. The hub the rest of the site links into.
| model | provider | context | input /1M | output /1M ↑ |
|---|---|---|---|---|
| Mistral Nemo routed | Mistral | 131K | $0.03 | $0.03 |
| Llama 3 8B Lunaris routed | Sao10k | 8K | $0.04 | $0.05 |
| Ling 3.0 Flash VL routed | Inclusionai | 262K | $0.02 | $0.06 |
| Ling 3.0 Flash routed | Inclusionai | 262K | $0.02 | $0.06 |
| Ministral 3 8B 2512 (batch) routed | Mistral | 262K | $0.07 | $0.07 |
| Mistral Small 3 routed | Mistral | 33K | $0.05 | $0.08 |
| Llama 3.1 8B Instruct routed | Meta | 131K | $0.05 | $0.08 |
| gpt-oss-20b routed | OpenAI | 131K | $0.02 | $0.09 |
| Reka Edge routed | Rekaai | 16K | $0.10 | $0.10 |
| Nex-N2.5-Mini routed | Nex Agi | 262K | $0.03 | $0.10 |
| Ministral 3 3B 2512 routed | Mistral | 131K | $0.10 | $0.10 |
| Gemma 3 4B routed | 131K | $0.05 | $0.10 | |
| MythoMax 13B routed | Gryphe | 8K | $0.08 | $0.11 |
| Granite 4.0 Micro routed | Ibm Granite | 131K | $0.02 | $0.11 |
| gpt-oss-20b (batch) routed | OpenAI | 131K | $0.02 | $0.11 |
| Laguna XS 2.1 routed | Poolside | 262K | $0.06 | $0.12 |
| Ling 3.0 Flash Sante routed | Inclusionai | 262K | $0.04 | $0.12 |
| Ling 3.0 Flash Fin routed | Inclusionai | 262K | $0.04 | $0.12 |
| Qwen3.7 Flash routed | Qwen | 1M | $0.03 | $0.13 |
| gpt-oss-120b (batch) routed | OpenAI | 131K | $0.03 | $0.14 |
| Phi 4 routed | Microsoft | 16K | $0.07 | $0.14 |
| Nova Micro 1.0 routed | Amazon | 128K | $0.04 | $0.14 |
| Schematron V2 Turbo routed | Inference Net | 128K | $0.03 | $0.15 |
| Qwen3.5-9B routed | Qwen | 262K | $0.10 | $0.15 |
| Ministral 3 8B 2512 routed | Mistral | 262K | $0.15 | $0.15 |
| Mercury 2.5 routed | Inception | 260K | $0.04 | $0.15 |
| Gemma 3 12B routed | 131K | $0.05 | $0.15 | |
| Command R7B (12-2024) routed | Cohere | 128K | $0.04 | $0.15 |
| gpt-oss-120b routed | OpenAI | 131K | $0.04 | $0.17 |
| Hy-MT2-1.8B routed | Tencent | 8K | $0.04 | $0.18 |
| Llama Guard 4 12B routed | Meta | 164K | $0.18 | $0.18 |
| Laguna S 2.1 routed | Poolside | 1.0M | $0.09 | $0.18 |
| UI-TARS 7B routed | ByteDance | 128K | $0.10 | $0.20 |
| Solar Mini 4 routed | Upstage | 524K | $0.05 | $0.20 |
| Reka Flash 3 routed | Rekaai | 66K | $0.10 | $0.20 |
| Qwen2.5 7B Instruct routed | Qwen | 33K | $0.10 | $0.20 |
| Nemotron 3.5 Lightning routed | NVIDIA | 262K | $0.07 | $0.20 |
| Nemotron 3.5 Content Safety routed | NVIDIA | 131K | $0.20 | $0.20 |
| Muse Spark 1.3 Contributor routed | Meta | 1.0M | $0.10 | $0.20 |
| Muse Spark 1.2 Contributor routed | Meta | 1.0M | $0.10 | $0.20 |
| Ministral 3 14B 2512 routed | Mistral | 262K | $0.20 | $0.20 |
| GPT-5 Nano (batch) | OpenAI | 400K | $0.03 | $0.20 |
| GPT-4.1 Nano (batch) | OpenAI | 1.0M | $0.05 | $0.20 |
| GLM 5.3 Flash (batch) routed | Z.AI | 1.0M | $0.06 | $0.20 |
| Gemini 2.5 Flash Lite (batch) | 1.0M | $0.05 | $0.20 | |
| Llama 3.2 1B Instruct routed | Meta | 60K | $0.03 | $0.20 |
| Gemma 4 26B A4B routed | 262K | $0.07 | $0.23 | |
| Schematron V2 Small routed | Inference Net | 128K | $0.05 | $0.23 |
| Qwen3 14B routed | Qwen | 41K | $0.12 | $0.24 |
| Nova Lite 1.0 routed | Amazon | 300K | $0.06 | $0.24 |
| Nemotron 3 Nano 30B A3B routed | NVIDIA | 262K | $0.06 | $0.24 |
| Nex-N2.5-Pro routed | Nex Agi | 262K | $0.07 | $0.25 |
| Mistral Small 3.2 24B routed | Mistral | 256K | $0.09 | $0.25 |
| Granite 4.2 8B routed | Ibm Granite | 131K | $0.06 | $0.25 |
| GPT-6 Luna Pro (batch) | OpenAI | 1.1M | $0.05 | $0.25 |
| GPT-6 Luna (batch) | OpenAI | 1.1M | $0.05 | $0.25 |
| Claude Haiku 5.5 (batch) | Anthropic | 1M | $0.05 | $0.25 |
| Qwen3.5-Flash routed | Qwen | 1M | $0.07 | $0.26 |
| Qwen3 Coder 30B A3B Instruct routed | Qwen | 262K | $0.07 | $0.28 |
| Qwen3 32B routed | Qwen | 131K | $0.08 | $0.28 |
| MiMo-V2.6-Flash routed | Xiaomi | 1.1M | $0.14 | $0.28 |
| MiMo-V2.5 routed | Xiaomi | 1.1M | $0.14 | $0.28 |
| DeepSeek V4 Flash first-party | DeepSeek | 1.0M | $0.14 | $0.28 |
| Hy-MT2-7B routed | Tencent | 8K | $0.07 | $0.29 |
| Hy-MT2-30B-A3B routed | Tencent | 8K | $0.07 | $0.29 |
| Voxtral Small 24B 2507 routed | Mistral | 33K | $0.10 | $0.30 |
| Step 3.5 Flash routed | Stepfun | 262K | $0.10 | $0.30 |
| Seed 1.6 Flash routed | Bytedance Seed | 262K | $0.07 | $0.30 |
| Qwen3 30B A3B Instruct 2507 routed | Qwen | 262K | $0.10 | $0.30 |
| Mistral Small 4 (batch) routed | Mistral | 262K | $0.07 | $0.30 |
| Llama 4 Scout routed | Meta | 1.3M | $0.10 | $0.30 |
| gpt-oss-safeguard-20b routed | OpenAI | 131K | $0.07 | $0.30 |
| GPT-4o-mini (batch) | OpenAI | 128K | $0.07 | $0.30 |
| Llama 3.2 3B Instruct routed | Meta | 131K | $0.05 | $0.33 |
| DeepSeek V4.1 Flash (batch) routed | DeepSeek | 1.0M | $0.11 | $0.34 |
| Gemma 4 31B routed | 262K | $0.09 | $0.34 | |
| Solar Pro 4 routed | Upstage | 524K | $0.09 | $0.36 |
| UnslopNemo 12B routed | Thedrummer | 1.0M | $0.40 | $0.40 |
| Seed-2.0-Mini routed | Bytedance Seed | 262K | $0.10 | $0.40 |
| Qwen2.5 72B Instruct routed | Qwen | 33K | $0.36 | $0.40 |
| Llama 3.1 70B Instruct routed | Meta | 131K | $0.40 | $0.40 |
| GPT-5 Nano | OpenAI | 400K | $0.05 | $0.40 |
| GPT-4.1 Nano | OpenAI | 1.0M | $0.10 | $0.40 |
| GLM 4.7 Flash routed | Z.AI | 200K | $0.06 | $0.40 |
| Gemini 2.5 Flash-Lite | 1.0M | $0.10 | $0.40 | |
| Gemini 2.5 Flash Lite Preview 09-2025 | 1.0M | $0.10 | $0.40 | |
| DeepSeek V3.2 Exp routed | DeepSeek | 164K | $0.27 | $0.41 |
| Nemotron 3 Super routed | NVIDIA | 262K | $0.08 | $0.45 |
| Gemma 3 27B routed | 131K | $0.08 | $0.45 | |
| Codestral 2508 (batch) routed | Mistral | 256K | $0.15 | $0.45 |
| Qwen3.8 Omni Flash routed | Qwen | 1M | $0.15 | $0.47 |
| Qwen3.8 Flash routed | Qwen | 1M | $0.15 | $0.47 |
| Ternary Bonsai 2 27B routed | Prism Ml | 262K | $0.07 | $0.50 |
| Qwen3 30B A3B routed | Qwen | 41K | $0.12 | $0.50 |
| Llama 3.3 70B Instruct routed | Meta | 131K | $0.22 | $0.50 |
| GPT-6 Luna Pro | OpenAI | 1.1M | $0.10 | $0.50 |
| GPT-6 Luna | OpenAI | 1.1M | $0.10 | $0.50 |
| GLM 5.3 Flash routed | Z.AI | 1.0M | $0.15 | $0.50 |
| Cydonia 24B V4.1 routed | Thedrummer | 131K | $0.30 | $0.50 |
| Claude Haiku 5.5 | Anthropic | 1M | $0.10 | $0.50 |
| Hy3 routed | Tencent | 262K | $0.13 | $0.53 |
| Qwen3 235B A22B Instruct 2507 routed | Qwen | 262K | $0.09 | $0.55 |
| Mistral Small 3.1 24B routed | Mistral | 128K | $0.35 | $0.56 |
| Hunyuan A13B Instruct routed | Tencent | 131K | $0.14 | $0.57 |
| Solar Pro 3 routed | Upstage | 131K | $0.15 | $0.60 |
| Saba routed | Mistral | 33K | $0.20 | $0.60 |
| Qwen3 VL 30B A3B Instruct routed | Qwen | 262K | $0.15 | $0.60 |
| Mistral Small 4 routed | Mistral | 262K | $0.15 | $0.60 |
| Hy3 preview routed | Tencent | 262K | $0.18 | $0.60 |
| GPT-5.6 Luna Pro (batch) | OpenAI | 1.1M | $0.10 | $0.60 |
| GPT-5.6 Luna (batch) | OpenAI | 1.1M | $0.10 | $0.60 |
| GPT-4o-mini Search Preview | OpenAI | 128K | $0.15 | $0.60 |
| GPT-4o-mini (2024-07-18) | OpenAI | 128K | $0.15 | $0.60 |
| GPT-4o-mini | OpenAI | 128K | $0.15 | $0.60 |
| Command R (08-2024) routed | Cohere | 128K | $0.15 | $0.60 |
| WizardLM-2 8x22B routed | Microsoft | 66K | $0.62 | $0.62 |
| GPT-5.4 Nano (batch) | OpenAI | 400K | $0.10 | $0.63 |
| DeepSeek V4 Flash 0731 routed | DeepSeek | 1.0M | $0.02 | $0.64 |
| DeepSeek V4 Flash Vision Exp routed | DeepSeek | 1.0M | $0.22 | $0.65 |
| ReMM SLERP 13B routed | Undi95 | 6K | $0.35 | $0.65 |
| Gemma 2 27B routed | 8K | $0.65 | $0.65 | |
| Llama 4 Maverick routed | Meta | 1.0M | $0.19 | $0.65 |
| Hermes 3 70B Instruct routed | Nousresearch | 131K | $0.70 | $0.70 |
| Weaver (alpha) routed | Mancer | 8K | $0.40 | $0.75 |
| Qwen3.5-35B-A3B routed | Qwen | 262K | $0.08 | $0.75 |
| Qwen3 VL 8B Instruct routed | Qwen | 262K | $0.25 | $0.75 |
| Mistral Large 3 2512 (batch) routed | Mistral | 262K | $0.25 | $0.75 |
| Mercury 2 routed | Inception | 128K | $0.25 | $0.75 |
| Llama 3.3 Euryale 70B routed | Sao10k | 131K | $0.65 | $0.75 |
| GPT-3.5 Turbo (batch) | OpenAI | 16K | $0.25 | $0.75 |
| Gemini 3.1 Flash Lite (batch) | 1.0M | $0.13 | $0.75 | |
| Qwen-Plus routed | Qwen | 1M | $0.26 | $0.78 |
| Trinity Large Thinking routed | Arcee Ai | 262K | $0.25 | $0.80 |
| Skyfall 36B V2 routed | Thedrummer | 33K | $0.55 | $0.80 |
| Qwen3 Coder Next routed | Qwen | 262K | $0.12 | $0.80 |
| GPT-4.1 Mini (batch) | OpenAI | 1.0M | $0.20 | $0.80 |
| DeepSeek V3.2 routed | DeepSeek | 164K | $0.26 | $0.80 |
| MiniMax M2.7 routed | MiniMax | 205K | $0.21 | $0.84 |
| Llama 3.1 Euryale 70B v2.2 routed | Sao10k | 131K | $0.85 | $0.85 |
| GLM 4.5 Air routed | Z.AI | 131K | $0.13 | $0.85 |
| MiMo-V2.6-Pro routed | Xiaomi | 1.1M | $0.43 | $0.87 |
| MiMo-V2.5-Pro routed | Xiaomi | 1.1M | $0.43 | $0.87 |
| DeepSeek V4 Pro first-party | DeepSeek | 1.0M | $0.43 | $0.87 |
| DeepSeek V3 routed | DeepSeek | 164K | $0.32 | $0.89 |
| Uncensored routed | Cognitivecomputations | 128K | $0.20 | $0.90 |
| GLM 4.6V routed | Z.AI | 131K | $0.30 | $0.90 |
| Codestral 2508 routed | Mistral | 256K | $0.30 | $0.90 |
| Qwen3.6 35B A3B routed | Qwen | 262K | $0.10 | $0.95 |
| DeepSeek V3.1 routed | DeepSeek | 164K | $0.25 | $0.95 |
| Qwen3 Coder Flash routed | Qwen | 1M | $0.20 | $0.97 |
| Sonar routed | Perplexity | 127K | $1.00 | $1.00 |
| Qwen3 VL 30B A3B Thinking routed | Qwen | 262K | $0.29 | $1.00 |
| Qwen3 Coder 480B A35B routed | Qwen | 262K | $0.30 | $1.00 |
| Qwen2.5 VL 72B Instruct routed | Qwen | 128K | $0.80 | $1.00 |
| Qwen2.5 Coder 32B Instruct routed | Qwen | 33K | $0.66 | $1.00 |
| Mistral Medium 3.1 (batch) routed | Mistral | 131K | $0.20 | $1.00 |
| Hermes 3 405B Instruct routed | Nousresearch | 131K | $1.00 | $1.00 |
| GPT-5 Mini (batch) | OpenAI | 400K | $0.13 | $1.00 |
| DeepSeek V3.1 Terminus routed | DeepSeek | 164K | $0.27 | $1.00 |
| MiniMax M2.5 routed | MiniMax | 205K | $0.27 | $1.08 |
| Qwen3 Next 80B A3B Instruct routed | Qwen | 262K | $0.10 | $1.10 |
| MiniMax-01 routed | MiniMax | 1.0M | $0.20 | $1.10 |
| Qwen3.6 Flash routed | Qwen | 1M | $0.19 | $1.13 |
| DeepSeek V3 0324 routed | DeepSeek | 164K | $0.29 | $1.14 |
| Step 3.7 Flash routed | Stepfun | 262K | $0.20 | $1.15 |
| Qwen3 Next 80B A3B Thinking routed | Qwen | 262K | $0.15 | $1.20 |
| Muse Glimmer 30B routed | Meta | 131K | $0.30 | $1.20 |
| Morph V3 Fast routed | Morph | 82K | $0.80 | $1.20 |
| MiniMax M3 routed | MiniMax | 1.0M | $0.30 | $1.20 |
| MiniMax M2.1 routed | MiniMax | 205K | $0.30 | $1.20 |
| MiniMax M2-her routed | MiniMax | 66K | $0.30 | $1.20 |
| MiniMax M2 routed | MiniMax | 205K | $0.30 | $1.20 |
| LongCat 2.0 routed | Meituan | 1.0M | $0.30 | $1.20 |
| Inkling Small routed | Thinkingmachines | 524K | $0.45 | $1.20 |
| GPT-5.6 Luna Pro | OpenAI | 1.1M | $0.20 | $1.20 |
| GPT-5.6 Luna | OpenAI | 1.1M | $0.20 | $1.20 |
| DeepSeek V4.1 Flash routed | DeepSeek | 1.0M | $0.30 | $1.20 |
| Relace Apply 3 routed | Relace | 256K | $0.85 | $1.25 |
| GPT-5.4 nano | OpenAI | 400K | $0.20 | $1.25 |
| GLM 5.3 FlashX routed | Z.AI | 1.0M | $0.37 | $1.25 |
| Gemini 3.5 Flash Lite (batch) | 1.0M | $0.15 | $1.25 | |
| Gemini 2.5 Flash (batch) | 1.0M | $0.15 | $1.25 | |
| Claude 3 Haiku | Anthropic | 200K | $0.25 | $1.25 |
| Qwen3.7 Plus routed | Qwen | 1M | $0.32 | $1.28 |
| Aion-3.0-Mini routed | Aion Labs | 131K | $0.70 | $1.40 |
| Aion 3.5 Mini routed | Aion Labs | 262K | $0.70 | $1.40 |
| Perceptron Mk1.5 routed | Perceptron | 37K | $0.15 | $1.50 |
| Perceptron Mk1 routed | Perceptron | 33K | $0.15 | $1.50 |
| Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | 66K | $0.25 | $1.50 | |
| Mistral Large 3 | Mistral | 262K | $0.50 | $1.50 |
| GPT-3.5 Turbo | OpenAI | 16K | $0.50 | $1.50 |
| Gemini 3.1 Flash Lite Preview | 1.0M | $0.25 | $1.50 | |
| Gemini 3.1 Flash Lite | 1.0M | $0.25 | $1.50 | |
| Gemini 3 Flash Preview (batch) | 1.0M | $0.25 | $1.50 | |
| Command A+ routed | Cohere | 192K | $0.30 | $1.50 |
| Qwen3.5 Plus 2026-02-15 routed | Qwen | 1M | $0.26 | $1.56 |
| GPT-4.1 Mini | OpenAI | 1.0M | $0.40 | $1.60 |
| Aion-RP 1.0 (8B) routed | Aion Labs | 33K | $0.80 | $1.60 |
| Aion-2.0 routed | Aion Labs | 131K | $0.80 | $1.60 |
| Qwen3.5 Plus 2026-04-20 routed | Qwen | 1M | $0.30 | $1.80 |
| GLM 4.5V routed | Z.AI | 66K | $0.60 | $1.80 |
| Gemini 3.8 Flash (batch) | 1.0M | $0.38 | $1.88 | |
| Gemini 3.7 Flash (batch) | 1.0M | $0.38 | $1.88 | |
| Gemini 3.6 Flash (batch) | 1.0M | $0.38 | $1.88 | |
| Qwen3 VL 235B A22B Instruct routed | Qwen | 262K | $0.21 | $1.90 |
| Morph V3 Large routed | Morph | 262K | $0.90 | $1.90 |
| GLM 5 routed | Z.AI | 205K | $0.60 | $1.92 |
| Qwen3.6 Plus routed | Qwen | 1M | $0.33 | $1.95 |
| DeepSeek V4 Pro 0813 routed | DeepSeek | 1.0M | $0.66 | $1.98 |
| Seed-2.0-Lite routed | Bytedance Seed | 262K | $0.25 | $2.00 |
| Seed 1.6 routed | Bytedance Seed | 262K | $0.25 | $2.00 |
| Mistral Medium 3.1 routed | Mistral | 131K | $0.40 | $2.00 |
| Mistral Medium 3 routed | Mistral | 131K | $0.40 | $2.00 |
| Grok Build 0.1 | xAI | 256K | $1.00 | $2.00 |
| Grok 4.3 (batch) | xAI | 1M | $1.00 | $2.00 |
| GPT-5.1-Codex-Mini | OpenAI | 400K | $0.25 | $2.00 |
| GPT-5 Mini | OpenAI | 400K | $0.25 | $2.00 |
| GPT-5 Image Mini | OpenAI | 400K | $2.50 | $2.00 |
| GPT-3.5 Turbo Instruct | OpenAI | 4K | $1.50 | $2.00 |
| GPT-3.5 Turbo (older v0613) | OpenAI | 4K | $1.00 | $2.00 |
| GLM 5.3 (batch) routed | Z.AI | 1.0M | $0.45 | $2.00 |
| GLM 4.6 routed | Z.AI | 205K | $0.50 | $2.00 |
| Devstral 2 2512 routed | Mistral | 262K | $0.40 | $2.00 |
| Qwen3.5-122B-A10B routed | Qwen | 262K | $0.26 | $2.08 |
| Mistral Large 4 routed | Mistral | 1.0M | $0.68 | $2.09 |
| R1 0528 routed | DeepSeek | 164K | $0.50 | $2.15 |
| o4 Mini High (batch) | OpenAI | 200K | $0.55 | $2.20 |
| o4 Mini (batch) | OpenAI | 200K | $0.55 | $2.20 |
| o3 Mini High (batch) | OpenAI | 200K | $0.55 | $2.20 |
| o3 Mini (batch) | OpenAI | 200K | $0.55 | $2.20 |
| Nemotron 3 Ultra routed | NVIDIA | 262K | $0.50 | $2.20 |
| MiniMax M1 routed | MiniMax | 1M | $0.55 | $2.20 |
| GLM 4.7 routed | Z.AI | 205K | $0.60 | $2.20 |
| GLM 4.5 routed | Z.AI | 131K | $0.60 | $2.20 |
| GPT-5.4 Mini (batch) | OpenAI | 400K | $0.38 | $2.25 |
| Qwen3.8 27B routed | Qwen | 1M | $0.04 | $2.30 |
| Kimi K2 0711 routed | Moonshot | 131K | $0.57 | $2.30 |
| GPT Audio Mini | OpenAI | 128K | $0.60 | $2.40 |
| Seed 2.1 Turbo routed | Bytedance Seed | 262K | $0.50 | $2.50 |
| R1 routed | DeepSeek | 64K | $0.70 | $2.50 |
| Nova 2 Lite routed | Amazon | 1M | $0.30 | $2.50 |
| Nano Banana (Gemini 2.5 Flash Image) | 33K | $0.30 | $2.50 | |
| Kimi K2.5 routed | Moonshot | 262K | $0.50 | $2.50 |
| Kimi K2 Thinking routed | Moonshot | 262K | $0.60 | $2.50 |
| Kimi K2 0905 routed | Moonshot | 262K | $0.60 | $2.50 |
| Grok 4.3 | xAI | 1M | $1.25 | $2.50 |
| Grok 4.20 Multi-Agent | xAI | 2M | $1.25 | $2.50 |
| Grok 4.20 | xAI | 2M | $1.25 | $2.50 |
| Gemini 3.5 Flash Lite | 1.0M | $0.30 | $2.50 | |
| Gemini 2.5 Flash | 1.0M | $0.30 | $2.50 | |
| Claude Haiku 4.5 (batch) | Anthropic | 200K | $0.50 | $2.50 |
| Hy4 preview routed | Tencent | 1.0M | $0.83 | $2.50 |
| Qwen3.5-27B routed | Qwen | 262K | $0.26 | $2.60 |
| Step 5 Preview routed | Stepfun | 1M | $1.00 | $2.70 |
| Seed-2.0-Code routed | Bytedance Seed | 262K | $0.50 | $3.00 |
| Relace Search routed | Relace | 256K | $1.00 | $3.00 |
| Nano Banana 2 (Gemini 3.1 Flash Image) | 131K | $0.50 | $3.00 | |
| Nano Banana 2 (Gemini 3.1 Flash Image Preview) | 66K | $0.50 | $3.00 | |
| Hermes 4 405B routed | Nousresearch | 131K | $1.00 | $3.00 |
| Gemini 3 Flash Preview | 1.0M | $0.50 | $3.00 | |
| GLM 5.1 routed | Z.AI | 205K | $0.97 | $3.04 |
| Qwen3.6 27B routed | Qwen | 262K | $0.32 | $3.20 |
| Pareto 26.10 Preview routed | Unbiased | 1.0M | $0.80 | $3.20 |
| Nova Pro 1.0 routed | Amazon | 300K | $0.80 | $3.20 |
| Kimi K2.7 Code routed | Moonshot | 262K | $0.67 | $3.35 |
| Kimi K2.6 routed | Moonshot | 262K | $0.65 | $3.41 |
| Qwen3.5 397B A17B routed | Qwen | 262K | $0.55 | $3.50 |
| Qwen3 235B A22B Thinking 2507 routed | Qwen | 128K | $0.45 | $3.50 |
| Mistral Medium 3.5 (batch) routed | Mistral | 262K | $0.75 | $3.75 |
| Gemini 3.8 Flash | 1.0M | $0.75 | $3.75 | |
| Gemini 3.7 Flash | 1.0M | $0.75 | $3.75 | |
| Gemini 3.6 Flash | 1.0M | $0.75 | $3.75 | |
| Sakana Namazu routed | Sakana | 262K | $0.95 | $4.00 |
| o3 (batch) | OpenAI | 200K | $1.00 | $4.00 |
| GPT-4.1 (batch) | OpenAI | 1.0M | $1.00 | $4.00 |
| GPT-3.5 Turbo 16k | OpenAI | 16K | $3.00 | $4.00 |
| GLM 5V Turbo routed | Z.AI | 203K | $1.20 | $4.00 |
| GLM 5 Turbo routed | Z.AI | 203K | $1.20 | $4.00 |
| Claude 3.5 Haiku | Anthropic | 200K | $0.80 | $4.00 |
| Inkling routed | Thinkingmachines | 524K | $1.00 | $4.05 |
| Muse Spark 1.3 routed | Meta | 1.0M | $1.25 | $4.25 |
| Muse Spark 1.2 routed | Meta | 1.0M | $1.25 | $4.25 |
| Muse Spark 1.1 routed | Meta | 1.0M | $1.25 | $4.25 |
| o4 Mini High | OpenAI | 200K | $1.10 | $4.40 |
| o4 Mini | OpenAI | 200K | $1.10 | $4.40 |
| o3 Mini High | OpenAI | 200K | $1.10 | $4.40 |
| o3 Mini | OpenAI | 200K | $1.10 | $4.40 |
| Qwen3.7 Max routed | Qwen | 1M | $1.48 | $4.42 |
| GPT-5.4 mini | OpenAI | 400K | $0.75 | $4.50 |
| Gemini 3.5 Flash (batch) | 1.0M | $0.75 | $4.50 | |
| GLM 5.3 routed | Z.AI | 1.0M | $0.07 | $4.80 |
| Magnum v4 72B routed | Anthracite Org | 33K | $2.50 | $5.00 |
| GPT-6.1 Sol Pro (batch) | OpenAI | 1.1M | $1.00 | $5.00 |
| GPT-6.1 Sol (batch) | OpenAI | 1.1M | $1.00 | $5.00 |
| GPT-6 Sol Pro (batch) | OpenAI | 1.1M | $1.00 | $5.00 |
| GPT-6 Sol (batch) | OpenAI | 1.1M | $1.00 | $5.00 |
| GPT-5.6 Sol Pro (batch) | OpenAI | 1.1M | $1.00 | $5.00 |
| GPT-5.6 Sol (batch) | OpenAI | 1.1M | $1.00 | $5.00 |
| GPT-5.1 (batch) | OpenAI | 400K | $0.63 | $5.00 |
| GPT-5 Codex (batch) | OpenAI | 400K | $0.63 | $5.00 |
| GPT-5 (batch) | OpenAI | 400K | $0.63 | $5.00 |
| GPT-4o (batch) | OpenAI | 128K | $1.25 | $5.00 |
| Gemini 2.5 Pro (batch) | 1.0M | $0.63 | $5.00 | |
| Claude Sonnet 5.5 (batch) | Anthropic | 1M | $1.00 | $5.00 |
| Claude Sonnet 5 (batch) | Anthropic | 1M | $1.00 | $5.00 |
| Claude Haiku 4.5 | Anthropic | 200K | $1.00 | $5.00 |
| Qwen3.8 Max (0902) routed | Qwen | 1M | $2.00 | $6.00 |
| Qwen3.8 2.4T A95B routed | Qwen | 1.0M | $2.00 | $6.00 |
| Palmyra X5 routed | Writer | 1.0M | $0.60 | $6.00 |
| Mixtral 8x22B Instruct routed | Mistral | 66K | $2.00 | $6.00 |
| Mistral Large 2407 routed | Mistral | 131K | $2.00 | $6.00 |
| Mistral Large routed | Mistral | 128K | $2.00 | $6.00 |
| Grok 4.7 | xAI | 500K | $2.00 | $6.00 |
| Grok 4.6 | xAI | 500K | $2.00 | $6.00 |
| Grok 4.5 | xAI | 500K | $2.00 | $6.00 |
| GPT-5.6 Terra Pro (batch) | OpenAI | 1.1M | $1.00 | $6.00 |
| GPT-5.6 Terra (batch) | OpenAI | 1.1M | $1.00 | $6.00 |
| Gemini 3.1 Pro Preview (batch) | 1.0M | $1.00 | $6.00 | |
| Fugu Max routed | Sakana | 1M | $2.00 | $6.00 |
| Aion-3.0 routed | Aion Labs | 131K | $3.00 | $6.00 |
| Aion 3.5 routed | Aion Labs | 262K | $3.00 | $6.00 |
| GPT-5.2 (batch) | OpenAI | 400K | $0.88 | $7.00 |
| GLM 5.2 routed | Z.AI | 1.0M | $0.06 | $7.00 |
| Pareto routed | Unbiased | 262K | $2.50 | $7.50 |
| Nano Banana 2.1 | 66K | $1.50 | $7.50 | |
| Mistral Medium 3.5 | Mistral | 262K | $1.50 | $7.50 |
| GPT-5.4 (batch) | OpenAI | 1.1M | $1.25 | $7.50 |
| Claude Sonnet 4.6 (batch) | Anthropic | 1M | $1.50 | $7.50 |
| Claude Sonnet 4.5 (batch) | Anthropic | 1M | $1.50 | $7.50 |
| Sonar Reasoning Pro routed | Perplexity | 128K | $2.00 | $8.00 |
| Sonar Deep Research routed | Perplexity | 128K | $2.00 | $8.00 |
| o4 Mini Deep Research | OpenAI | 200K | $2.00 | $8.00 |
| o3 | OpenAI | 200K | $2.00 | $8.00 |
| GPT-4.1 | OpenAI | 1.0M | $2.00 | $8.00 |
| MiMo-V2.6-Pro-UltraSpeed routed | Xiaomi | 1.0M | $4.35 | $8.70 |
| GLM 5.3 Prime routed | Z.AI | 1M | $2.80 | $8.80 |
| Gemini 3.5 Flash | 1.0M | $1.50 | $9.00 | |
| Kimi K3 routed | Moonshot | 1.0M | $0.80 | $10.00 |
| GPT-6.1 Sol Pro | OpenAI | 1.1M | $2.00 | $10.00 |
| GPT-6.1 Sol | OpenAI | 1.1M | $2.00 | $10.00 |
| GPT-6 Sol Pro | OpenAI | 1.1M | $2.00 | $10.00 |
| GPT-6 Sol | OpenAI | 1.1M | $2.00 | $10.00 |
| GPT-5.6 Sol Pro | OpenAI | 1.1M | $2.00 | $10.00 |
| GPT-5.6 Sol | OpenAI | 1.1M | $2.00 | $10.00 |
| GPT-5.1-Codex-Max | OpenAI | 400K | $1.25 | $10.00 |
| GPT-5.1-Codex | OpenAI | 400K | $1.25 | $10.00 |
| GPT-5.1 Chat | OpenAI | 128K | $1.25 | $10.00 |
| GPT-5.1 | OpenAI | 400K | $1.25 | $10.00 |
| GPT-5 Image | OpenAI | 400K | $10.00 | $10.00 |
| GPT-5 Codex | OpenAI | 400K | $1.25 | $10.00 |
| GPT-5 Chat | OpenAI | 128K | $1.25 | $10.00 |
| GPT-5 | OpenAI | 400K | $1.25 | $10.00 |
| GPT-4o Search Preview | OpenAI | 128K | $2.50 | $10.00 |
| GPT-4o (2024-11-20) | OpenAI | 128K | $2.50 | $10.00 |
| GPT-4o (2024-08-06) | OpenAI | 128K | $2.50 | $10.00 |
| GPT-4o | OpenAI | 128K | $2.50 | $10.00 |
| GPT Audio | OpenAI | 128K | $2.50 | $10.00 |
| Gemini 2.5 Pro Preview 06-05 | 1.0M | $1.25 | $10.00 | |
| Gemini 2.5 Pro Preview 05-06 | 1.0M | $1.25 | $10.00 | |
| Gemini 2.5 Pro | 1.0M | $1.25 | $10.00 | |
| Command R+ (08-2024) routed | Cohere | 128K | $2.50 | $10.00 |
| Command A routed | Cohere | 256K | $2.50 | $10.00 |
| Claude Sonnet 5.5 | Anthropic | 1M | $2.00 | $10.00 |
| Claude Sonnet 5 | Anthropic | 1M | $2.00 | $10.00 |
| Claude Opus 5.5 (batch) | Anthropic | 1M | $2.00 | $10.00 |
| Kimi K3 (batch) routed | Moonshot | 1.0M | $2.28 | $11.40 |
| Qwen3.8 Max Prime routed | Qwen | 1M | $4.00 | $12.00 |
| Nano Banana Pro (Gemini 3 Pro Image) | 131K | $2.00 | $12.00 | |
| Nano Banana Pro (Gemini 3 Pro Image Preview) | 66K | $2.00 | $12.00 | |
| GPT-5.6 Terra Pro | OpenAI | 1.1M | $2.00 | $12.00 |
| GPT-5.6 Terra | OpenAI | 1.1M | $2.00 | $12.00 |
| Gemini 3.1 Pro Preview Custom Tools | 1.0M | $2.00 | $12.00 | |
| Gemini 3.1 Pro | 1.0M | $2.00 | $12.00 | |
| Nova Premier 1.0 routed | Amazon | 1M | $2.50 | $12.50 |
| Claude Opus 5 (batch) | Anthropic | 1M | $2.50 | $12.50 |
| Claude Opus 4.8 (batch) | Anthropic | 1M | $2.50 | $12.50 |
| Claude Opus 4.7 (batch) | Anthropic | 1M | $2.50 | $12.50 |
| Claude Opus 4.6 (batch) | Anthropic | 1M | $2.50 | $12.50 |
| Claude Opus 4.5 (batch) | Anthropic | 200K | $2.50 | $12.50 |
| GPT-5.3-Codex | OpenAI | 400K | $1.75 | $14.00 |
| GPT-5.3 Chat | OpenAI | 128K | $1.75 | $14.00 |
| GPT-5.2-Codex | OpenAI | 400K | $1.75 | $14.00 |
| GPT-5.2 Chat | OpenAI | 128K | $1.75 | $14.00 |
| GPT-5.2 | OpenAI | 400K | $1.75 | $14.00 |
| Sonar Pro Search routed | Perplexity | 200K | $3.00 | $15.00 |
| Sonar Pro routed | Perplexity | 200K | $3.00 | $15.00 |
| GPT-5.5 (batch) | OpenAI | 1.1M | $2.50 | $15.00 |
| GPT-5.4 Image 2 | OpenAI | 272K | $8.00 | $15.00 |
| GPT-5.4 | OpenAI | 1.1M | $2.50 | $15.00 |
| GPT-4o (2024-05-13) | OpenAI | 128K | $5.00 | $15.00 |
| GPT-4 Turbo (batch) | OpenAI | 128K | $5.00 | $15.00 |
| Ember-1 routed | Fireworks | 1.0M | $3.00 | $15.00 |
| Claude Sonnet 4.6 | Anthropic | 1M | $3.00 | $15.00 |
| Claude Sonnet 4.5 | Anthropic | 1M | $3.00 | $15.00 |
| Claude Sonnet 4 | Anthropic | 200K | $3.00 | $15.00 |
| Claude Opus 5.5 | Anthropic | 1M | $4.00 | $20.00 |
| GPT-6 Astra Pro (batch) | OpenAI | 1.1M | $5.00 | $25.00 |
| GPT-6 Astra (batch) | OpenAI | 1.1M | $5.00 | $25.00 |
| Claude Opus 5 | Anthropic | 1M | $5.00 | $25.00 |
| Claude Opus 4.8 | Anthropic | 1M | $5.00 | $25.00 |
| Claude Opus 4.7 | Anthropic | 1M | $5.00 | $25.00 |
| Claude Opus 4.6 | Anthropic | 1M | $5.00 | $25.00 |
| Claude Opus 4.5 | Anthropic | 200K | $5.00 | $25.00 |
| Claude Fable 5.1 (batch) | Anthropic | 1M | $5.00 | $25.00 |
| Claude Fable 5 (batch) | Anthropic | 1M | $5.00 | $25.00 |
| o1 (batch) | OpenAI | 200K | $7.50 | $30.00 |
| GPT-5.5 | OpenAI | 1.1M | $5.00 | $30.00 |
| GPT-4 Turbo Preview | OpenAI | 128K | $10.00 | $30.00 |
| GPT-4 Turbo | OpenAI | 128K | $10.00 | $30.00 |
| GPT Chat Latest | OpenAI | 400K | $5.00 | $30.00 |
| Fugu Ultra v2 routed | Sakana | 1M | $5.00 | $30.00 |
| Fugu Ultra routed | Sakana | 1M | $5.00 | $30.00 |
| Claude Opus 4.1 (batch) | Anthropic | 200K | $7.50 | $37.50 |
| o3 Pro (batch) | OpenAI | 200K | $10.00 | $40.00 |
| o3 Deep Research | OpenAI | 200K | $10.00 | $40.00 |
| GPT-6 Astra Pro | OpenAI | 1.1M | $10.00 | $50.00 |
| GPT-6 Astra | OpenAI | 1.1M | $10.00 | $50.00 |
| Claude Opus 5 (Fast) | Anthropic | 1M | $10.00 | $50.00 |
| Claude Opus 4.8 (Fast) | Anthropic | 1M | $10.00 | $50.00 |
| Claude Fable 5.1 | Anthropic | 1M | $10.00 | $50.00 |
| Claude Fable 5 | Anthropic | 1M | $10.00 | $50.00 |
| o1 | OpenAI | 200K | $15.00 | $60.00 |
| GPT-5 Pro (batch) | OpenAI | 400K | $7.50 | $60.00 |
| GPT-4 | OpenAI | 8K | $30.00 | $60.00 |
| Claude Opus 4.1 | Anthropic | 200K | $15.00 | $75.00 |
| Claude Opus 4 | Anthropic | 200K | $15.00 | $75.00 |
| o3 Pro | OpenAI | 200K | $20.00 | $80.00 |
| GPT-5.2 Pro (batch) | OpenAI | 400K | $10.50 | $84.00 |
| GPT-5.5 Pro (batch) | OpenAI | 1.1M | $15.00 | $90.00 |
| GPT-5.4 Pro (batch) | OpenAI | 1.1M | $15.00 | $90.00 |
| GPT-5 Pro | OpenAI | 400K | $15.00 | $120 |
| Claude Opus 4.7 (Fast) | Anthropic | 1M | $30.00 | $150 |
| Claude Opus 4.6 (Fast) | Anthropic | 1M | $30.00 | $150 |
| GPT-5.2 Pro | OpenAI | 400K | $21.00 | $168 |
| GPT-5.5 Pro | OpenAI | 1.1M | $30.00 | $180 |
| GPT-5.4 Pro | OpenAI | 1.1M | $30.00 | $180 |
| o1-pro (batch) | OpenAI | 200K | $75.00 | $300 |
| o1-pro | OpenAI | 200K | $150 | $600 |
Snapshot · 198 premier (first-party list) · 240 routed (OpenRouter). How we measure →
How to read this table
Three numbers drive most model choices: the context window, the input price, and the output price — which carries a thermal bar (cool = cheap, hot = expensive) because output is where bills run. Each row is tagged by price source: routed is OpenRouter's market price; / first-party are premier providers' official list prices.
Two sources, one honest number
OpenRouter gives us the live market price for 300+ models. For the premier providers we also track the official first-party list price and reconcile the two every run: if they agree the market price stands; if they diverge, the first-party price wins and the row says so. It's the difference between "what a reseller charges" and "what the lab charges" — and we show which is which. The full rule is on the methodology page.
Frequently asked questions
What is a context window?
The maximum tokens a model can consider at once — prompt, attached documents, conversation, and the model's own output all share it. A 1M-token window holds roughly 750,000 words. Bigger windows let you send more, but you pay input rates for every token you actually send.
What do 'routed' and 'first-party' mean?
Most rows show the routed market price from OpenRouter. The premier providers (OpenAI, Anthropic, Google, xAI, DeepSeek, Mistral) also carry the official first-party list price; when the two differ, the first-party value wins and the row is tagged accordingly. See the methodology page for the full reconciliation rule.
How current are these specs?
Prices are captured from OpenRouter and official provider sources with a date; the latest snapshot is 2026-10-11, refreshed every other day and tracked in the price-history archive. Verify against the provider before relying on a figure.
Related
- Compare models head-to-head — side-by-side pricing and specs for the leading models.
- API cost calculator — your monthly cost for any workload.
- Token counter — how many tokens your text is.
- Context window visualizer — what a context length holds.