Model pricing
Compare AI model API prices.
444 language models, 20 video models, 55 image models and 2,622 offers from the AI labs, clouds and hosts: what each costs, who sells it cheapest and how it ranks on LMArena. Enter your usage to see a monthly estimate.
Open and partner models served by inference platforms and gateways.
Estimate your monthly cost
Est. per month = input tokens × input price + output tokens × output price. Prices are per million tokens, so 10M input tokens at $3.00 cost $30.
1,613 offers · prices per million tokens
| Model | Input | Output | Cached input | Context | Est. per month10M in · 2M out | Details |
|---|---|---|---|---|---|---|
| $3.00 | $15.00 | $0.30 | 1.05M | $60.00 | ||
 glm-5-3-flash-260828 | $0.1188 | $0.4156 | $0.0341 | 1M | $2.02 | |
glm-5-2-260617 | $1.19 | $4.16 | $0.2969 | 1M | $20.19 | |
deepseek-v4-pro-ga-260813 | $1.34 | $4.01 | $0.0445 | 1M | $21.37 | |
deepseek-v4-flash-ga-260731 | $0.4453 | $1.34 | $0.0148 | 1M | $7.12 | |
| $3.00 | $15.00 | $0.30 | 1.05M | $60.00 | ||
| $0.50 | $1.20 | $0.10 | 262K | $7.40 | ||
| $1.40 | $4.40 | $0.26 | 262K | $22.80 | ||
| $1.32 | $3.96 | $0.044 | 1.05M | $21.12 | ||
| $1.74 | $3.48 | $0.20 | 512K | $24.36 | ||
 zephyr-7b-beta | $0.20 | $0.20 | — | 33K | $2.40 | |
yi-large | $3.00 | $3.00 | — | 33K | $36.00 | |
yi-34b-chat | $0.90 | $0.90 | — | 4K | $10.80 | |
yi-34b-200k-capybara | $0.90 | $0.90 | — | 200K | $10.80 | |
yi-34b | $0.90 | $0.90 | — | 4K | $10.80 | |
yi-6b | $0.20 | $0.20 | — | 4K | $2.40 | |
toppy-m-7b | $0.20 | $0.20 | — | 33K | $2.40 | |
starcoder2-15b | $0.20 | $0.20 | — | 16K | $2.40 | |
starcoder2-7b | $0.20 | $0.20 | — | 16K | $2.40 | |
starcoder2-3b | $0.10 | $0.10 | — | 16K | $1.20 | |
starcoder-16b | $0.20 | $0.20 | — | 8K | $2.40 | |
starcoder-7b | $0.20 | $0.20 | — | 8K | $2.40 | |
stablecode-3b | $0.10 | $0.10 | — | 4K | $1.20 | |
snorkel-mistral-7b-pairrm-dpo | $0.20 | $0.20 | — | 33K | $2.40 | |
rolm-ocr | $0.20 | $0.20 | — | 128K | $2.40 | |
| $0.90 | $0.90 | — | 131K | $10.80 | ||
qwen3p8-max | $2.00 | $6.00 | $0.25 | 262K | $32.00 | |
qwen3p8-max | $2.00 | $6.00 | $0.25 | 262K | $32.00 | |
qwen3p8-2p4t-a95b | $2.00 | $6.00 | $0.25 | 262K | $32.00 | |
qwen3p7-plus | $0.40 | $1.60 | $0.08 | 262K | $7.20 | |
qwen3p7-plus | $0.40 | $1.60 | $0.08 | 262K | $7.20 | |
| $0.22 | $0.88 | — | 262K | $3.96 | ||
| $0.22 | $0.88 | — | 262K | $3.96 | ||
| $0.90 | $0.90 | — | 4K | $10.80 | ||
| $0.15 | $0.60 | — | 262K | $2.70 | ||
| $0.15 | $0.60 | — | 262K | $2.70 | ||
| $0.20 | $0.20 | — | 262K | $2.40 | ||
| $0.90 | $0.90 | — | 4K | $10.80 | ||
| $0.90 | $0.90 | — | 4K | $10.80 | ||
qwen3-coder-480b-instruct-bf16 | $0.90 | $0.90 | — | 262K | $10.80 | |
| $0.45 | $1.80 | — | 262K | $8.10 | ||
| $0.15 | $0.60 | — | 262K | $2.70 | ||
| $0.22 | $0.88 | — | 262K | $3.96 | ||
| $0.22 | $0.88 | — | 262K | $3.96 | ||
| $0.22 | $0.88 | — | 131K | $3.96 | ||
| $0.90 | $0.90 | — | 131K | $10.80 | ||
qwen3-30b-a3b-thinking-2507 | $0.90 | $0.90 | — | 262K | $10.80 | |
| $0.50 | $0.50 | — | 262K | $6.00 | ||
| $0.15 | $0.60 | — | 131K | $2.70 | ||
| $0.20 | $0.20 | — | 41K | $2.40 | ||
| $0.20 | $0.20 | — | 41K | $2.40 | ||
qwen3-4b-instruct-2507 | $0.20 | $0.20 | — | 262K | $2.40 | |
qwen3-4b | $0.20 | $0.20 | — | 41K | $2.40 | |
qwen3-1p7b-fp8-draft-131072 | $0.10 | $0.10 | — | 131K | $1.20 | |
qwen3-1p7b-fp8-draft-40960 | $0.10 | $0.10 | — | 41K | $1.20 | |
qwen3-1p7b-fp8-draft | $0.10 | $0.10 | — | 262K | $1.20 | |
qwen3-1p7b | $0.10 | $0.10 | — | 131K | $1.20 | |
qwen3-0p6b | $0.10 | $0.10 | — | 41K | $1.20 | |
qwen2p5-vl-72b-instruct | $0.90 | $0.90 | — | 128K | $10.80 | |
qwen2p5-vl-32b-instruct | $0.90 | $0.90 | — | 128K | $10.80 | |
qwen2p5-vl-7b-instruct | $0.20 | $0.20 | — | 128K | $2.40 | |
qwen2p5-vl-3b-instruct | $0.20 | $0.20 | — | 128K | $2.40 | |
qwen2p5-math-72b-instruct | $0.90 | $0.90 | — | 4K | $10.80 | |
qwen2p5-coder-32b-instruct-128k | $0.90 | $0.90 | — | 131K | $10.80 | |
qwen2p5-coder-32b-instruct-64k | $0.90 | $0.90 | — | 66K | $10.80 | |
qwen2p5-coder-32b-instruct-32k-rope | $0.90 | $0.90 | — | 33K | $10.80 | |
qwen2p5-coder-32b-instruct | $0.90 | $0.90 | — | 4K | $10.80 | |
qwen2p5-coder-32b | $0.90 | $0.90 | — | 33K | $10.80 | |
qwen2p5-coder-14b-instruct | $0.20 | $0.20 | — | 33K | $2.40 | |
qwen2p5-coder-14b | $0.20 | $0.20 | — | 33K | $2.40 | |
qwen2p5-coder-7b-instruct | $0.20 | $0.20 | — | 33K | $2.40 | |
qwen2p5-coder-7b | $0.20 | $0.20 | — | 33K | $2.40 | |
qwen2p5-coder-3b-instruct | $0.10 | $0.10 | — | 33K | $1.20 | |
qwen2p5-coder-3b | $0.10 | $0.10 | — | 33K | $1.20 | |
qwen2p5-coder-1p5b-instruct | $0.10 | $0.10 | — | 33K | $1.20 | |
qwen2p5-coder-1p5b | $0.10 | $0.10 | — | 33K | $1.20 | |
qwen2p5-coder-0p5b-instruct | $0.10 | $0.10 | — | 33K | $1.20 | |
qwen2p5-coder-0p5b | $0.10 | $0.10 | — | 33K | $1.20 | |
qwen2p5-72b-instruct | $0.90 | $0.90 | — | 33K | $10.80 | |
qwen2p5-72b | $0.90 | $0.90 | — | 131K | $10.80 | |
qwen2p5-32b-instruct | $0.90 | $0.90 | — | 33K | $10.80 | |
qwen2p5-32b | $0.90 | $0.90 | — | 131K | $10.80 | |
qwen2p5-14b | $0.20 | $0.20 | — | 131K | $2.40 | |
qwen2p5-7b-instruct | $0.20 | $0.20 | — | 33K | $2.40 | |
qwen2p5-1p5b-instruct | $0.10 | $0.10 | — | 33K | $1.20 | |
qwen2p5-0p5b-instruct | $0.10 | $0.10 | — | 33K | $1.20 | |
qwen2-vl-72b-instruct | $0.90 | $0.90 | — | 33K | $10.80 | |
qwen2-vl-7b-instruct | $0.20 | $0.20 | — | 33K | $2.40 | |
qwen2-vl-2b-instruct | $0.10 | $0.10 | — | 33K | $1.20 | |
qwen2-72b-instruct | $0.90 | $0.90 | — | 33K | $10.80 | |
qwen2-7b-instruct | $0.20 | $0.20 | — | 33K | $2.40 | |
qwen1p5-72b-chat | $0.90 | $0.90 | — | 33K | $10.80 | |
qwen-v2p5-14b-instruct | $0.20 | $0.20 | — | 33K | $2.40 | |
qwen-v2p5-7b | $0.20 | $0.20 | — | 131K | $2.40 | |
qwen-qwq-32b-preview | $0.90 | $0.90 | — | 33K | $10.80 | |
pythia-12b | $0.20 | $0.20 | — | 2K | $2.40 | |
phind-code-llama-34b-v2 | $0.90 | $0.90 | — | 16K | $10.80 | |
phind-code-llama-34b-v1 | $0.90 | $0.90 | — | 16K | $10.80 | |
phind-code-llama-34b-python-v1 | $0.90 | $0.90 | — | 16K | $10.80 | |
phi-3-vision-128k-instruct | $0.20 | $0.20 | — | 32K | $2.40 |
