LLM API prices by model
701 models, each compared across every lab, inference host and router we track. Prices are USD per 1M tokens. Blended weights input and output 3:1, the usual chat workload.
Model labs 24Inference hosts 31Hyperscaler AI platforms 5LLM routers 14LLM gateways 12
| Model | Creator | Providers | Cheapest input | Cheapest output | Cheapest blended | Spread | Context |
|---|---|---|---|---|---|---|---|
| gpt-oss-120b open openai/gpt-oss-120b |
openai | 30 | $0.03 | $0.14 | $0.059 | 7.6× | 131k |
| Llama 3.3 70B Instruct open meta-llama/llama-3.3-70b-instruct |
meta | 22 | $0.10 | $0.32 | $0.155 | 7.9× | 131k |
| GLM-5.2 open z-ai/glm-5.2 |
z-ai | 22 | $0.561 | $1.76 | $0.862 | 3.6× | 1.05M |
| GLM-5.3 open z-ai/glm-5.3 |
z-ai | 22 | $0.90 | $3 | $1.43 | 1.9× | 1.05M |
| Kimi K2.6 open moonshotai/kimi-k2.6 |
moonshotai | 21 | $0.50 | $2.85 | $1.09 | 2.1× | 262k |
| gpt-oss-20b open openai/gpt-oss-20b |
openai | 19 | $0.02 | $0.10 | $0.04 | 5.6× | 131k |
| GLM-5.3 Flash open z-ai/glm-5.3-flash |
z-ai | 19 | $0.09 | $0.28 | $0.138 | 1.7× | 1.05M |
| DeepSeek V4 Flash 0731 open deepseek/deepseek-v4-flash-0731 |
deepseek | 18 | $0.06 | $0.12 | $0.075 | 10.6× | 1.05M |
| Kimi K3 open moonshotai/kimi-k3 |
moonshotai | 18 | $2.10 | $10.95 | $4.31 | 1.7× | 1.05M |
| Gemma 4 31B open google/gemma-4-31b-it |
17 | $0 | $0 | $0 | 262k | ||
| DeepSeek V3.2 open deepseek/deepseek-v3.2 |
deepseek | 17 | $0.25 | $0.38 | $0.29 | 11.6× | 164k |
| Qwen3.8-27B open qwen/qwen3.8-27b |
qwen | 16 | $0.20 | $1.49 | $0.73 | 2.2× | 1.05M |
| DeepSeek V4 Pro 0423 open deepseek/deepseek-v4-pro |
deepseek | 16 | $0.87 | $1.74 | $1.09 | 2.4× | 1.05M |
| Qwen3.5-397B-A17B open qwen/qwen3.5-397b-a17b |
qwen | 15 | $0.36 | $2.40 | $0.87 | 1.9× | 262k |
| DeepSeek V4 Flash 0423 open deepseek/deepseek-v4-flash |
deepseek | 14 | $0.049 | $0.098 | $0.061 | 5.3× | 1.05M |
| Qwen3 235B A22B 2507 open qwen/qwen3-235b-a22b-2507 |
qwen | 14 | $0.087 | $0.35 | $0.153 | 8.4× | 262k |
| DeepSeek V4.1 Flash open deepseek/deepseek-v4.1-flash |
deepseek | 14 | $0.15 | $0.60 | $0.263 | 2.5× | 1.05M |
| MiniMax M3 open minimax/minimax-m3 |
minimax | 14 | $0.23 | $0.96 | $0.412 | 2.5× | 1M |
| GLM 5 open z-ai/glm-5 |
z-ai | 14 | $0.60 | $1.92 | $0.93 | 1.7× | 205k |
| DeepSeek V4 Pro 0813 open deepseek/deepseek-v4-pro-0813 |
deepseek | 14 | $0.659 | $1.98 | $0.988 | 2.0× | 1.05M |
| Kimi K2.7 Code open moonshotai/kimi-k2.7-code |
moonshotai | 14 | $0.68 | $3.21 | $1.33 | 1.3× | 262k |
| GLM 5.1 open z-ai/glm-5.1 |
z-ai | 14 | $0.966 | $3.04 | $1.48 | 1.6× | 205k |
| DeepSeek V3.1 open deepseek/deepseek-chat-v3.1 |
deepseek | 13 | $0.25 | $0.95 | $0.425 | 7.9× | 164k |
| MiniMax M2.5 open minimax/minimax-m2.5 |
minimax | 13 | $0.27 | $0.95 | $0.44 | 1.2× | 205k |
| Kimi K2.5 open moonshotai/kimi-k2.5 |
moonshotai | 13 | $0.45 | $2.25 | $0.90 | 1.8× | 262k |
| Gemma 4 26B A4B open google/gemma-4-26b-a4b-it |
12 | $0.056 | $0.272 | $0.11 | 3.3× | 262k | |
| Qwen3.6 35B A3B open qwen/qwen3.6-35b-a3b |
qwen | 12 | $0.10 | $0.90 | $0.30 | 2.8× | 262k |
| Llama 4 Maverick 17B Instruct open meta-llama/llama-4-maverick |
meta | 12 | $0.188 | $0.652 | $0.304 | 2.1× | 1.05M |
| MiniMax M2.7 open minimax/minimax-m2.7 |
minimax | 12 | $0.30 | $1.20 | $0.525 | 2.0× | 205k |
| GLM 4.7 open z-ai/glm-4.7 |
z-ai | 12 | $0.40 | $1.75 | $0.738 | 1.5× | 205k |
| Gemma 3 27B IT open google/gemma-3-27b-it |
11 | $0.08 | $0.16 | $0.10 | 2.7× | 198k | |
| NVIDIA Nemotron 3 Ultra (Preview) open nvidia/nemotron-3-ultra-550b-a55b |
nvidia | 10 | $0 | $0 | $0 | 1.05M | |
| Llama 3.1 8B Instruct open meta-llama/llama-3.1-8b-instruct |
meta | 10 | $0.02 | $0.04 | $0.025 | 8.8× | 131k |
| Qwen3 32B open qwen/qwen3-32b |
qwen | 10 | $0.064 | $0.224 | $0.104 | 2.7× | 131k |
| Llama 4 Scout 17B Instruct open meta-llama/llama-4-scout |
meta | 10 | $0.08 | $0.29 | $0.14 | 3.0× | 10M |
| Qwen3 Next 80B A3B open qwen/qwen3-next-80b-a3b-instruct |
qwen | 10 | $0.09 | $1.10 | $0.343 | 2.2× | 262k |
| Qwen3 Coder 480B A35B open qwen/qwen3-coder |
qwen | 10 | $0.22 | $0.40 | $0.40 | 7.5× | 262k |
| Qwen3.6 27B open qwen/qwen3.6-27b |
qwen | 10 | $0.30 | $2 | $0.725 | 1.9× | 262k |
| GLM 4.6 open z-ai/glm-4.6 |
z-ai | 9 | $0.43 | $1.75 | $0.76 | 1.3× | 205k |
| Qwen3.5-35B-A3B open qwen/qwen3.5-35b-a3b |
qwen | 8 | $0.112 | $0.80 | $0.284 | 2.4× | 262k |
| Nemotron 3 Nano 30B open nvidia/nemotron-3-nano-30b-a3b |
nvidia | 7 | $0 | $0 | $0 | 262k | |
| Nemotron 3 Super 120B A12B open nvidia/nemotron-3-super-120b-a12b |
nvidia | 7 | $0 | $0 | $0 | 1.05M | |
| GLM 4.7 Flash open z-ai/glm-4.7-flash |
z-ai | 7 | $0 | $0 | $0 | 203k | |
| R1 0528 open deepseek/deepseek-r1-0528 |
deepseek | 7 | $0.385 | $1.62 | $0.695 | 3.4× | 164k |
| Kimi K2 Thinking open moonshotai/kimi-k2-thinking |
moonshotai | 7 | $0.60 | $2.50 | $1.07 | 1.1× | 262k |
| Grok 4.3 x-ai/grok-4.3 |
x-ai | 7 | $1.25 | $2.50 | $1.56 | 1M | |
| Grok 4.6 x-ai/grok-4.6 |
x-ai | 7 | $2 | $6 | $3 | 1.1× | 500k |
| Mistral Nemo open mistralai/mistral-nemo |
mistral | 6 | $0.019 | $0.03 | $0.022 | 10.3× | 131k |
| Mistral Small 3.2 24B open mistralai/mistral-small-3.2-24b-instruct |
mistral | 6 | $0.075 | $0.20 | $0.106 | 2.5× | 256k |
| MiniMax M2 open minimax/minimax-m2 |
minimax | 6 | $0.255 | $1.02 | $0.446 | 1.2× | 1M |
| Qwen3.5-27B open qwen/qwen3.5-27b |
qwen | 6 | $0.195 | $1.56 | $0.536 | 1.6× | 262k |
| Qwen3.5-122B-A10B open qwen/qwen3.5-122b-a10b |
qwen | 6 | $0.26 | $2.08 | $0.715 | 1.5× | 262k |
| DeepSeek R1 open deepseek/deepseek-r1 |
deepseek | 6 | $0.70 | $2.50 | $1.15 | 4.6× | 128k |
| Qwen3.8-2.4T-A95B open qwen/qwen3.8-2.4t-a95b |
qwen | 6 | $2 | $6 | $3 | 1.2× | 1M |
| Claude Sonnet 5 anthropic/claude-sonnet-5 |
anthropic | 6 | $2 | $10 | $4 | 1.1× | 1M |
| Claude Sonnet 4.6 anthropic/claude-sonnet-4.6 |
anthropic | 6 | $3 | $15 | $6 | 1.1× | 1M |
| Claude Opus 5 anthropic/claude-opus-5 |
anthropic | 6 | $5 | $25 | $10 | 1.1× | 1M |
| Claude Fable 5.1 anthropic/claude-fable-5.1 |
anthropic | 6 | $10 | $50 | $20 | 1.1× | 1M |
| Qwen3-30B-A3B-Instruct-2507 open qwen/qwen3-30b-a3b-instruct-2507 |
qwen | 5 | $0.048 | $0.193 | $0.084 | 4.1× | 262k |
| Qwen3.5 9B open qwen/qwen3.5-9b |
qwen | 5 | $0.09 | $0.13 | $0.10 | 1.9× | 262k |
| Qwen3 30B A3B open qwen/qwen3-30b-a3b |
qwen | 5 | $0.051 | $0.335 | $0.122 | 2.9× | 41k |
| Gemini 2.5 Flash-Lite google/gemini-2.5-flash-lite |
5 | $0.10 | $0.40 | $0.175 | 1.05M | ||
| Qwen3 Coder Next open qwen/qwen3-coder-next |
qwen | 5 | $0.12 | $0.80 | $0.29 | 2.3× | 262k |
| Qwen2.5 72B Instruct open qwen/qwen-2.5-72b-instruct |
qwen | 5 | $0.36 | $0.40 | $0.37 | 33k | |
| Llama 3.1 70B Instruct open meta-llama/llama-3.1-70b-instruct |
meta | 5 | $0.293 | $0.40 | $0.40 | 2.0× | 131k |
| Gemini 2.5 Flash google/gemini-2.5-flash |
5 | $0.15 | $1.25 | $0.425 | 2.0× | 1.05M | |
| Grok 4.20 (Reasoning / Non-Reasoning) x-ai/grok-4.20 |
x-ai | 5 | $1.25 | $2.50 | $1.56 | 2M | |
| Claude Haiku 4.5 anthropic/claude-haiku-4.5 |
anthropic | 5 | $1 | $5 | $2 | 1.1× | 200k |
| GPT-5.4 openai/gpt-5.4 |
openai | 5 | $1.25 | $7.50 | $2.81 | 2.0× | 1.05M |
| Mistral Medium 3.5 (128B) mistralai/mistral-medium-3-5 |
mistral | 5 | $1.50 | $7.50 | $3 | 1.1× | 262k |
| Gemini 2.5 Pro google/gemini-2.5-pro |
5 | $1.25 | $10 | $3.44 | 1.05M | ||
| Claude Sonnet 4.5 anthropic/claude-sonnet-4.5 |
anthropic | 5 | $3 | $15 | $6 | 1.1× | 1M |
| Claude Opus 4.6 anthropic/claude-opus-4.6 |
anthropic | 5 | $5 | $25 | $10 | 1.1× | 1M |
| Claude Opus 4.8 anthropic/claude-opus-4.8 |
anthropic | 5 | $5 | $25 | $10 | 1.1× | 1M |
| Claude Fable 5 anthropic/claude-fable-5 |
anthropic | 5 | $10 | $50 | $20 | 1.1× | 1M |
| Llama 3.2 1B Instruct open meta-llama/llama-3.2-1b-instruct |
meta | 4 | $0.027 | $0.10 | $0.07 | 1.4× | 128k |
| NVIDIA Nemotron 3.5 Lightning 30B A3B open nvidia/nemotron-3.5-lightning |
nvidia | 4 | $0.05 | $0.20 | $0.087 | 1.3× | 262k |
| Qwen3 8B open qwen/qwen3-8b |
alibaba | 4 | $0.07 | $0.18 | $0.098 | 3.2× | 131k |
| Qwen3 14B open qwen/qwen3-14b |
alibaba | 4 | $0.07 | $0.20 | $0.102 | 6.0× | 131k |
| Llama 3.2 3B Instruct open meta-llama/llama-3.2-3b-instruct |
meta | 4 | $0.05 | $0.15 | $0.12 | 1.2× | 131k |
| Qwen3 Coder 30B A3B open qwen/qwen3-coder-30b-a3b-instruct |
qwen | 4 | $0.07 | $0.28 | $0.122 | 7.3× | 262k |
| GPT-5 nano openai/gpt-5-nano |
openai | 4 | $0.05 | $0.40 | $0.138 | 400k | |
| mistral-small-3.1-24b-instruct open mistralai/mistral-small-3.1-24b-instruct |
mistral | 4 | $0.10 | $0.30 | $0.15 | 2.7× | 128k |
| DeepSeek V3 open deepseek/deepseek-chat |
deepseek | 4 | $0.14 | $0.28 | $0.175 | 8.3× | 1M |
| GPT-4.1 nano openai/gpt-4.1-nano |
openai | 4 | $0.10 | $0.40 | $0.175 | 1.05M | |
| Ministral 3 14B open mistralai/ministral-14b-2512 |
mistralai | 4 | $0.20 | $0.20 | $0.20 | 262k | |
| Qwen3.8 Flash open qwen/qwen3.8-flash |
qwen | 4 | $0.15 | $0.47 | $0.23 | 1.05M | |
| GPT-5.4 nano openai/gpt-5.4-nano |
openai | 4 | $0.10 | $0.625 | $0.231 | 2.0× | 400k |
| GPT-4o mini openai/gpt-4o-mini |
openai | 4 | $0.15 | $0.60 | $0.263 | 128k | |
| Qwen3 235B A22B open qwen/qwen3-235b-a22b |
alibaba | 4 | $0.20 | $0.60 | $0.30 | 4.1× | 131k |
| GLM 4.5 Air open z-ai/glm-4.5-air |
z-ai | 4 | $0.13 | $0.85 | $0.31 | 1.4× | 131k |
| DeepSeek V4 Flash Vision Exp open deepseek/deepseek-v4-flash-vision-exp |
deepseek | 4 | $0.216 | $0.647 | $0.323 | 2.0× | 1.05M |
| Trinity Large (Thinking) open arcee-ai/trinity-large-thinking |
arcee | 4 | $0.22 | $0.80 | $0.378 | 1.1× | 262k |
| DeepSeek V3 0324 open deepseek/deepseek-chat-v3-0324 |
deepseek | 4 | $0.24 | $0.90 | $0.405 | 4.9× | 164k |
| Qwen3-Next-80B-Thinking open qwen/qwen3-next-80b-a3b-thinking |
qwen | 4 | $0.15 | $1.20 | $0.412 | 131k | |
| GPT-5.6 Luna openai/gpt-5.6-luna |
openai | 4 | $0.20 | $1.20 | $0.45 | 1.05M | |
| Qwen3-235B-A22B-Thinking-2507 open qwen/qwen3-235b-a22b-thinking-2507 |
qwen | 4 | $0.184 | $1.20 | $0.523 | 2.3× | 262k |
| MiniMax M2.1 open minimax/minimax-m2.1 |
minimax | 4 | $0.30 | $1.20 | $0.525 | 205k | |
| MiMo V2.5 Pro open xiaomi/mimo-v2.5-pro |
xiaomi | 4 | $0.40 | $0.87 | $0.544 | 1.2× | 1.05M |
| Qwen3.7 Plus qwen/qwen3.7-plus |
qwen | 4 | $0.32 | $1.28 | $0.56 | 1.2× | 1.05M |