Charis pricing
Live best price per model market on Charis, the best-execution AI-inference marketplace. Prices are all-in — exactly what a request is charged (provider fees + ~1–2% Charis fee included; display price == charged price), in USD per 1M tokens. Every row aggregates the cheapest live verified source for that model and lane; the sparkline is the last 14 days of the best price (output solid, input dashed).
Machine-readable: JSON · markdown for agents · agent guide (llms.txt) · full catalog with capabilities: /v1/models
| Model | Lane | Input $/1M | Output $/1M | 14-day trend | Throughput | Sources | vs retail |
|---|---|---|---|---|---|---|---|
| aion-2.0 | public | $0.5775 | $1.16 | — | 2 | −28% | |
| aion-3.0 | public | $3.23 | $6.46 | 287 tok/s | 1 | — | |
| aion-3.0-mini | public | $0.7533 | $1.51 | 287 tok/s | 1 | — | |
| aion-labs-aion-3.0 | anonymous | $3.83 | $7.65 | — | 1 | — | |
| aion-labs-aion-3.0-mini | anonymous | $0.8925 | $1.78 | — | 1 | — | |
| aion-rp-llama-3.1-8b | public | $0.8609 | $1.72 | 287 tok/s | 1 | — | |
| chainscout | public | $4.20 | $25.20 | — | 1 | — | |
| chainscout-guard-v1 | public | $4.20 | $25.20 | — | 1 | — | |
| claude-3-haiku | public | $0.269 | $1.35 | 287 tok/s | 1 | — | |
| claude-fable-5 | anonymous | $12.24 | $61.20 | — | 1 | — | |
| claude-fable-5 | public | $5.78 | $34.65 | — | 3 | −31% | |
| claude-fable-latest | public | $10.76 | $53.80 | 287 tok/s | 1 | — | |
| claude-haiku-4.5 | public | $0.3465 | $1.73 | — | 2 | −66% | |
| claude-haiku-latest | public | $1.08 | $5.38 | 287 tok/s | 1 | — | |
| claude-opus-4 | public | $16.14 | $80.71 | 287 tok/s | 1 | — | |
| claude-opus-4.1 | public | $16.14 | $80.71 | 287 tok/s | 1 | — | |
| claude-opus-4.5 | anonymous | $6.12 | $30.60 | — | 1 | — | |
| claude-opus-4.5 | public | $5.38 | $26.90 | 287 tok/s | 1 | — | |
| claude-opus-4.6 | anonymous | $6.12 | $30.60 | — | 1 | — | |
| claude-opus-4.6 | public | $5.38 | $26.90 | 287 tok/s | 1 | — | |
| claude-opus-4.7 | anonymous | $6.12 | $30.60 | — | 1 | — | |
| claude-opus-4.7 | public | $1.16 | $5.78 | — | 2 | −77% | |
| claude-opus-4.7-fast | public | $32.28 | $161 | 287 tok/s | 1 | — | |
| claude-opus-4.8 | anonymous | $6.12 | $30.60 | — | 1 | — | |
| claude-opus-4.8 | public | $1.16 | $5.78 | — | 2 | −77% | |
| claude-opus-4.8-fast | anonymous | $12.24 | $61.20 | — | 1 | — | |
| claude-opus-4.8-fast | public | $10.76 | $53.80 | 287 tok/s | 1 | — | |
| claude-opus-5 | anonymous | $6.12 | $30.60 | — | 1 | — | |
| claude-opus-5 | public | $2.31 | $11.55 | — | 2 | −54% | |
| claude-opus-5-fast | anonymous | $12.24 | $61.20 | — | 1 | — | |
| claude-opus-5-fast | public | $10.76 | $53.80 | 287 tok/s | 1 | — | |
| claude-opus-latest | public | $5.38 | $26.90 | 287 tok/s | 1 | — | |
| claude-sonnet-4 | public | $3.23 | $16.14 | 287 tok/s | 1 | — | |
| claude-sonnet-4.5 | anonymous | $3.83 | $19.12 | — | 1 | — | |
| claude-sonnet-4.5 | public | $3.23 | $16.14 | 287 tok/s | 1 | — | |
| claude-sonnet-4.6 | anonymous | $3.67 | $18.36 | — | 1 | — | |
| claude-sonnet-4.6 | public | $0.693 | $3.46 | — | 2 | −77% | |
| claude-sonnet-5 | anonymous | $3.06 | $15.30 | — | 1 | — | |
| claude-sonnet-5 | public | $1.16 | $5.78 | — | 2 | −43% | |
| claude-sonnet-latest | public | $2.15 | $10.76 | 287 tok/s | 1 | — | |
| codestral-2508 | public | $0.3228 | $0.9685 | 287 tok/s | 1 | — | |
| cogito-v2.1-671b | public | $1.35 | $1.35 | 287 tok/s | 1 | — | |
| command-a | public | $2.69 | $10.76 | 287 tok/s | 1 | — | |
| command-r-08.2024 | public | $0.1614 | $0.6457 | 287 tok/s | 1 | — | |
| command-r-plus-08.2024 | public | $2.69 | $10.76 | 287 tok/s | 1 | — | |
| command-r7b-12.2024 | public | $0.0404 | $0.1614 | 287 tok/s | 1 | — | |
| cydonia-24b-v4.1 | public | $0.3228 | $0.5381 | 287 tok/s | 1 | — | |
| deepseek | public | $0.3444 | $0.9577 | 287 tok/s | 1 | — | |
| deepseek-chat-v3.0324 | public | $0.2905 | $1.21 | 287 tok/s | 1 | — | |
| deepseek-chat-v3.1 | public | $0.269 | $1.02 | 287 tok/s | 1 | — | |
| deepseek-r1 | public | $0.7533 | $2.69 | 287 tok/s | 1 | — | |
| deepseek-r1-distill-llama-70b | public | $0.8609 | $0.8609 | 287 tok/s | 1 | — | |
| deepseek-r1.0528 | public | $0.5381 | $2.31 | 287 tok/s | 1 | — | |
| deepseek-v3.1 | public | $0.3675 | $1.05 | — | 1 | — | |
| deepseek-v3.1-terminus | public | $0.2905 | $1.02 | 287 tok/s | 1 | — | |
| deepseek-v3.2 | private | $0.3366 | $0.4896 | — | 1 | — | |
| deepseek-v3.2 | public | $0.1906 | $0.2772 | — | 2 | −12% | |
| deepseek-v3.2-exp | public | $0.2905 | $0.4412 | 287 tok/s | 1 | — | |
| deepseek-v4-flash | anonymous | $0.1408 | $0.2805 | — | 1 | — | |
| deepseek-v4-flash | private | $0.1856 | $0.3805 | — | 1 | — | |
| deepseek-v4-flash | public | $0.0904 | $0.1808 | 287 tok/s | 3 | — | |
| deepseek-v4-flash-0731 | private | $0.1785 | $0.357 | — | 1 | — | |
| deepseek-v4-flash-0731 | public | $0.0968 | $0.1937 | 287 tok/s | 1 | — | |
| deepseek-v4-flash-latest | public | $0.0968 | $0.1937 | 287 tok/s | 1 | — | |
| deepseek-v4-pro | anonymous | $1.68 | $3.37 | — | 1 | — | |
| deepseek-v4-pro | public | $0.4681 | $0.9362 | 287 tok/s | 1 | — | |
| dolphin-mistral-24b-venice-edition | public | $0.2152 | $0.9685 | 287 tok/s | 1 | — | |
| ernie-4.5-vl-424b-a47b | public | $0.452 | $1.35 | 287 tok/s | 1 | — | |
| fable-5 | public | $5.25 | $31.50 | — | 1 | — | |
| fugu-ultra | public | $5.38 | $32.28 | 287 tok/s | 1 | — | |
| gemini-2.5-flash | public | $0.1614 | $1.35 | 287 tok/s | 1 | — | |
| gemini-2.5-flash-image | public | $0.1614 | $1.35 | 287 tok/s | 1 | — | |
| gemini-2.5-flash-lite | public | $0.0538 | $0.2152 | 287 tok/s | 1 | — | |
| gemini-2.5-pro | public | $0.6726 | $5.38 | 287 tok/s | 1 | — | |
| gemini-2.5-pro-preview | public | $0.6726 | $5.38 | 287 tok/s | 1 | — | |
| gemini-2.5-pro-preview-05.06 | public | $0.6726 | $5.38 | 287 tok/s | 1 | — | |
| gemini-3-flash-preview | anonymous | $0.714 | $3.83 | — | 1 | — | |
| gemini-3-flash-preview | public | $0.269 | $1.61 | 287 tok/s | 1 | — | |
| gemini-3-pro-image | public | $2.15 | $12.91 | 287 tok/s | 1 | — | |
| gemini-3-pro-image-preview | public | $1.08 | $6.46 | 287 tok/s | 1 | — | |
| gemini-3.1-flash-image | public | $0.5381 | $3.23 | 287 tok/s | 1 | — | |
| gemini-3.1-flash-image-preview | public | $0.5381 | $3.23 | 287 tok/s | 1 | — | |
| gemini-3.1-flash-lite | public | $0.1345 | $0.8071 | 287 tok/s | 1 | — | |
| gemini-3.1-flash-lite-image | public | $0.269 | $1.61 | 287 tok/s | 1 | — | |
| gemini-3.1-flash-lite-preview | public | $0.1345 | $0.8071 | 287 tok/s | 1 | — | |
| gemini-3.1-pro-preview | anonymous | $2.55 | $15.30 | — | 1 | — | |
| gemini-3.1-pro-preview | public | $1.08 | $6.46 | 287 tok/s | 1 | — | |
| gemini-3.1-pro-preview-customtools | public | $2.15 | $12.91 | 287 tok/s | 1 | — | |
| gemini-3.5-flash | anonymous | $1.58 | $9.64 | — | 1 | — | |
| gemini-3.5-flash | public | $0.8071 | $4.84 | 287 tok/s | 1 | — | |
| gemini-3.5-flash-lite | anonymous | $0.3825 | $3.19 | — | 1 | — | |
| gemini-3.5-flash-lite | public | $0.1614 | $1.35 | 287 tok/s | 1 | — | |
| gemini-3.6-flash | anonymous | $1.91 | $9.56 | — | 1 | — | |
| gemini-3.6-flash | public | $0.8071 | $4.04 | 287 tok/s | 1 | — | |
| gemini-flash-latest | public | $1.61 | $8.07 | 287 tok/s | 1 | — | |
| gemini-pro-latest | public | $2.15 | $12.91 | 287 tok/s | 1 | — | |
| gemma-2-27b | public | $0.6995 | $0.6995 | 287 tok/s | 1 | — | |
| gemma-3-12b | public | $0.0538 | $0.1614 | 287 tok/s | 1 | — | |
| gemma-3-27b | private | $0.1428 | $0.51 | — | 1 | — | |
| gemma-3-27b | public | $0.0861 | $0.1722 | 287 tok/s | 1 | — | |
| gemma-3-4b | public | $0.0538 | $0.1076 | 287 tok/s | 1 | — | |
| gemma-3n-e4b | public | $0.0646 | $0.1291 | 287 tok/s | 1 | — | |
| gemma-4-26b | public | $0.3675 | $1.05 | — | 1 | — | |
| gemma-4-26b-a4b | private | $0.1326 | $0.408 | — | 1 | — | |
| gemma-4-26b-a4b | public | $0.1076 | $0.3228 | 287 tok/s | 1 | — | |
| gemma-4-26b-a4b-uncensored | encrypted (tee) | $0.0718 | $0.3324 | — | 2 | −63% | |
| gemma-4-31b | private | $0.1418 | $0.4386 | — | 1 | — | |
| gemma-4-31b | public | $0.0968 | $0.3659 | 287 tok/s | 1 | — | |
| gemma-4-uncensored | private | $0.1658 | $0.51 | — | 1 | — | |
| gemma-4-uncensored | public | $0.0938 | $0.2888 | — | 1 | −43% | |
| glm-4.5 | public | $0.6457 | $2.37 | 287 tok/s | 1 | — | |
| glm-4.5-air | public | $0.1399 | $0.9147 | 287 tok/s | 1 | — | |
| glm-4.5v | public | $0.6457 | $1.94 | 287 tok/s | 1 | — | |
| glm-4.6 | private | $0.4386 | $1.78 | — | 1 | — | |
| glm-4.6 | public | $0.4627 | $1.88 | 287 tok/s | 1 | — | |
| glm-4.6v | public | $0.3228 | $0.9685 | 287 tok/s | 1 | — | |
| glm-4.7 | private | $1.12 | $4.23 | — | 1 | — | |
| glm-4.7 | public | $0.3176 | $1.53 | — | 2 | −13% | |
| glm-4.7-flash | private | $0.0612 | $0.408 | — | 1 | — | |
| glm-4.7-flash | public | $0.0646 | $0.4304 | 287 tok/s | 1 | — | |
| glm-4.7-flash-heretic | public | $0.0735 | $0.42 | — | 1 | — | |
| glm-5 | private | $1.02 | $3.26 | — | 1 | — | |
| glm-5 | public | $0.5775 | $1.85 | — | 2 | −5% | |
| glm-5-turbo | anonymous | $1.22 | $4.08 | — | 1 | — | |
| glm-5-turbo | public | $0.693 | $2.31 | — | 2 | −43% | |
| glm-5.1 | private | $1.57 | $4.94 | — | 1 | — | |
| glm-5.1 | public | $0.6352 | $2.40 | — | 2 | −21% | |
| glm-5.1 | encrypted (tee) | $0.3596 | $1.13 | — | 2 | −63% | |
| glm-5.2 | private | $1.78 | $5.87 | — | 1 | — | |
| glm-5.2 | public | $0.3013 | $0.947 | 289 tok/s | 1 | — | |
| glm-5v-turbo | public | $0.8662 | $2.89 | — | 2 | −28% | |
| google-gemma-3-27b | public | $0.063 | $0.105 | — | 1 | — | |
| google-gemma-4-26b-a4b | public | $0.0853 | $0.2625 | — | 1 | — | |
| google-gemma-4-31b | public | $0.0919 | $0.2625 | — | 1 | — | |
| gpt-3.5-turbo | public | $0.5381 | $1.61 | 287 tok/s | 1 | — | |
| gpt-3.5-turbo-0613 | public | $1.08 | $2.15 | 287 tok/s | 1 | — | |
| gpt-3.5-turbo-16k | public | $3.23 | $4.30 | 287 tok/s | 1 | — | |
| gpt-4 | public | $32.28 | $64.57 | 287 tok/s | 1 | — | |
| gpt-4-turbo | public | $10.76 | $32.28 | 287 tok/s | 1 | — | |
| gpt-4-turbo-preview | public | $10.76 | $32.28 | 287 tok/s | 1 | — | |
| gpt-4.1 | public | $2.15 | $8.61 | 287 tok/s | 1 | — | |
| gpt-4.1-mini | public | $0.4304 | $1.72 | 287 tok/s | 1 | — | |
| gpt-4.1-nano | public | $0.1076 | $0.4304 | 287 tok/s | 1 | — | |
| gpt-4o | public | $1.80 | $7.22 | — | 2 | −28% | |
| gpt-4o-2024.05-13 | public | $5.38 | $16.14 | 287 tok/s | 1 | — | |
| gpt-4o-2024.08-06 | public | $2.69 | $10.76 | 287 tok/s | 1 | — | |
| gpt-4o-2024.11-20 | anonymous | $3.19 | $12.75 | — | 1 | — | |
| gpt-4o-2024.11-20 | public | $2.69 | $10.76 | 287 tok/s | 1 | — | |
| gpt-4o-mini | public | $0.1083 | $0.4331 | — | 2 | −28% | |
| gpt-4o-mini-2024.07-18 | anonymous | $0.1913 | $0.765 | — | 1 | — | |
| gpt-4o-mini-2024.07-18 | public | $0.1614 | $0.6457 | 287 tok/s | 1 | — | |
| gpt-5 | public | $1.35 | $10.76 | 287 tok/s | 1 | — | |
| gpt-5-image | public | $10.76 | $10.76 | 287 tok/s | 1 | — | |
| gpt-5-image-mini | public | $2.69 | $2.15 | 287 tok/s | 1 | — | |
| gpt-5-mini | public | $0.1345 | $1.08 | 287 tok/s | 1 | — | |
| gpt-5-nano | public | $0.0269 | $0.2152 | 287 tok/s | 1 | — | |
| gpt-5-pro | public | $16.14 | $129 | 287 tok/s | 1 | — | |
| gpt-5.1 | public | $0.6726 | $5.38 | 287 tok/s | 1 | — | |
| gpt-5.1-codex | public | $1.35 | $10.76 | 287 tok/s | 1 | — | |
| gpt-5.1-codex-max | public | $1.35 | $10.76 | 287 tok/s | 1 | — | |
| gpt-5.1-codex-mini | public | $0.269 | $2.15 | 287 tok/s | 1 | — | |
| gpt-5.2 | anonymous | $2.23 | $17.85 | — | 1 | — | |
| gpt-5.2 | public | $0.9416 | $7.53 | 287 tok/s | 1 | — | |
| gpt-5.2-codex | anonymous | $2.23 | $17.85 | — | 1 | — | |
| gpt-5.2-codex | public | $1.88 | $15.07 | 287 tok/s | 1 | — | |
| gpt-5.2-pro | public | $22.60 | $181 | 287 tok/s | 1 | — | |
| gpt-5.3 | public | $1.88 | $15.07 | 287 tok/s | 1 | — | |
| gpt-5.3-codex | anonymous | $2.23 | $17.85 | — | 1 | — | |
| gpt-5.3-codex | public | $1.04 | $4.62 | — | 3 | −67% | |
| gpt-5.3-codex-spark | public | $0.525 | $3.15 | — | 1 | — | |
| gpt-5.4 | anonymous | $3.19 | $19.18 | — | 1 | — | |
| gpt-5.4 | public | $0.2888 | $1.16 | — | 4 | −85% | |
| gpt-5.4-image-2 | public | $8.61 | $16.14 | 287 tok/s | 1 | — | |
| gpt-5.4-mini | anonymous | $0.9563 | $5.74 | — | 1 | — | |
| gpt-5.4-mini | public | $0.1155 | $0.5775 | — | 4 | −87% | |
| gpt-5.4-nano | public | $0.2152 | $1.35 | 287 tok/s | 1 | — | |
| gpt-5.4-pro | anonymous | $38.25 | $230 | — | 1 | — | |
| gpt-5.4-pro | public | $16.14 | $96.85 | 287 tok/s | 1 | — | |
| gpt-5.5 | anonymous | $6.38 | $38.25 | — | 1 | — | |
| gpt-5.5 | public | $0.4158 | $1.73 | — | 4 | −89% | |
| gpt-5.5-pro | anonymous | $38.25 | $230 | — | 1 | — | |
| gpt-5.5-pro | public | $16.14 | $96.85 | 287 tok/s | 1 | — | |
| gpt-5.6-luna | public | $0.0538 | $0.3228 | 287 tok/s | 1 | — | |
| gpt-5.6-luna-pro | public | $0.0538 | $0.3228 | 287 tok/s | 1 | — | |
| gpt-5.6-sol | public | $0.6352 | $3.18 | — | 2 | −79% | |
| gpt-5.6-sol-pro | public | $2.69 | $16.14 | 287 tok/s | 1 | — | |
| gpt-5.6-terra | public | $0.462 | $1.73 | — | 2 | −43% | |
| gpt-5.6-terra-pro | public | $0.5381 | $3.23 | 287 tok/s | 1 | — | |
| gpt-audio | public | $2.69 | $10.76 | 287 tok/s | 1 | — | |
| gpt-audio-mini | public | $0.6457 | $2.58 | 287 tok/s | 1 | — | |
| gpt-chat-latest | public | $5.38 | $32.28 | 287 tok/s | 1 | — | |
| gpt-latest | public | $5.38 | $32.28 | 287 tok/s | 1 | — | |
| gpt-mini-latest | public | $0.8071 | $4.84 | 287 tok/s | 1 | — | |
| gpt-oss-120b | private | $0.1326 | $0.663 | — | 1 | — | |
| gpt-oss-120b | public | $0.0323 | $0.1829 | 287 tok/s | 1 | — | |
| gpt-oss-20b | public | $0.0289 | $0.1097 | — | 2 | −16% | |
| gpt-oss-20b | encrypted (tee) | $0.0113 | $0.0491 | — | 2 | −63% | |
| gpt-oss-safeguard-20b | public | $0.0807 | $0.3228 | 287 tok/s | 1 | — | |
| granite-4.0-h-micro | public | $0.0183 | $0.1205 | 287 tok/s | 1 | — | |
| granite-4.1-8b | public | $0.0538 | $0.1076 | 287 tok/s | 1 | — | |
| grok-4.20 | private | $1.45 | $2.89 | — | 1 | — | |
| grok-4.20 | public | $0.82 | $1.63 | — | 2 | −35% | |
| grok-4.20-multi-agent | private | $1.45 | $2.89 | — | 1 | — | |
| grok-4.20-multi-agent | public | $0.82 | $1.63 | — | 2 | −35% | |
| grok-4.3 | private | $1.45 | $2.89 | — | 1 | — | |
| grok-4.3 | public | $0.82 | $1.63 | — | 2 | −35% | |
| grok-4.5 | private | $2.32 | $6.94 | — | 1 | — | |
| grok-4.5 | public | $1.31 | $3.93 | — | 2 | −35% | |
| grok-41-fast | public | $0.273 | $0.693 | — | 1 | — | |
| grok-build-0.1 | private | $1.02 | $2.04 | — | 1 | — | |
| grok-build-0.1 | public | $1.08 | $2.15 | 287 tok/s | 1 | — | |
| grok-latest | public | $2.15 | $6.46 | 287 tok/s | 1 | — | |
| hermes-3-llama-3.1-405b | private | $1.12 | $3.06 | — | 1 | — | |
| hermes-3-llama-3.1-405b | public | $1.08 | $1.08 | 287 tok/s | 1 | — | |
| hermes-3-llama-3.1-70b | public | $0.7533 | $0.7533 | 287 tok/s | 1 | — | |
| hermes-4-405b | public | $1.08 | $3.23 | 287 tok/s | 1 | — | |
| hermes-4-70b | public | $0.1399 | $0.4304 | 287 tok/s | 1 | — | |
| high-quality-gpt-5.3-codex-spark | public | $2.10 | $10.50 | — | 1 | — | |
| high-quality-gpt-5.4 | public | $3.15 | $21.00 | — | 1 | — | |
| high-quality-gpt-5.4-mini | public | $0.525 | $3.15 | — | 1 | — | |
| high-quality-gpt-5.5 | public | $10.50 | $52.50 | — | 1 | — | |
| hunyuan-a13b | public | $0.1507 | $0.6134 | 287 tok/s | 1 | — | |
| hy3 | public | $0.142 | $0.5682 | 287 tok/s | 1 | — | |
| hy3-preview | public | $0.0678 | $0.226 | 287 tok/s | 1 | — | |
| inkling | private | $1.27 | $5.16 | — | 1 | — | |
| inkling | public | $1.02 | $4.36 | 287 tok/s | 1 | — | |
| inkling-small | public | $0.5381 | $1.29 | 287 tok/s | 1 | — | |
| jamba-large-1.7 | public | $2.15 | $8.61 | 287 tok/s | 1 | — | |
| kat-coder-air-v2.5 | public | $0.1614 | $0.6457 | 287 tok/s | 1 | — | |
| kat-coder-pro-v2 | public | $0.3228 | $1.29 | 287 tok/s | 1 | — | |
| kat-coder-pro-v2.5 | public | $0.7963 | $3.19 | 287 tok/s | 1 | — | |
| kimi-k2 | public | $0.6134 | $2.48 | 287 tok/s | 1 | — | |
| kimi-k2-thinking | public | $0.6457 | $2.69 | 287 tok/s | 1 | — | |
| kimi-k2.0905 | public | $0.6457 | $2.69 | 287 tok/s | 1 | — | |
| kimi-k2.5 | private | $0.5712 | $3.57 | — | 1 | — | |
| kimi-k2.5 | public | $0.3977 | $1.91 | — | 3 | −7% | |
| kimi-k2.6 | private | $0.765 | $3.57 | — | 1 | — | |
| kimi-k2.6 | public | $0.6338 | $2.67 | 287 tok/s | 1 | — | |
| kimi-k2.7-code | private | $0.765 | $3.57 | — | 1 | — | |
| kimi-k2.7-code | public | $0.7533 | $3.77 | 287 tok/s | 1 | — | |
| kimi-k3 | private | $3.83 | $19.12 | — | 1 | — | |
| kimi-k3 | public | $2.17 | $10.83 | — | 2 | −23% | |
| kimi-k3-fast-api | private | $4.59 | $22.95 | — | 1 | — | |
| kimi-latest | public | $3.12 | $15.07 | 287 tok/s | 1 | — | |
| l3-lunaris-8b | public | $0.043 | $0.0538 | 287 tok/s | 1 | — | |
| l3.1-euryale-70b | public | $0.9147 | $0.9147 | 287 tok/s | 1 | — | |
| l3.3-euryale-70b | public | $0.6995 | $0.8071 | 287 tok/s | 1 | — | |
| laguna-s-2.1 | public | $0.0968 | $0.1937 | 287 tok/s | 1 | — | |
| laguna-xs-2.1 | public | $0.0646 | $0.1291 | 287 tok/s | 1 | — | |
| ling-2.6-flash | public | $0.0108 | $0.0323 | 287 tok/s | 1 | — | |
| ling-2.6.1t | public | $0.0807 | $0.6726 | 287 tok/s | 1 | — | |
| ling-3.0-flash | public | $0.3675 | $1.05 | — | 1 | — | |
| llama-3.1-70b | public | $0.4304 | $0.4304 | 287 tok/s | 1 | — | |
| llama-3.1-8b | public | $0.0215 | $0.043 | 287 tok/s | 1 | — | |
| llama-3.1-8b-instant | public | $5.25 | $10.50 | — | 1 | — | |
| llama-3.2-1b | public | $0.0291 | $0.2163 | 287 tok/s | 1 | — | |
| llama-3.2-3b | private | $0.153 | $0.612 | — | 1 | — | |
| llama-3.2-3b | public | $0.0538 | $0.3551 | 287 tok/s | 1 | — | |
| llama-3.3-70b | private | $0.714 | $2.86 | — | 1 | — | |
| llama-3.3-70b | public | $0.1076 | $0.3444 | 287 tok/s | 1 | — | |
| llama-4-maverick | public | $0.2152 | $0.749 | 287 tok/s | 1 | — | |
| llama-4-scout | public | $0.1076 | $0.3228 | 287 tok/s | 1 | — | |
| llama-guard-4-12b | public | $0.1937 | $0.1937 | 287 tok/s | 1 | — | |
| llama70b | public | $0.0063 | $0.021 | — | 1 | — | |
| longcat-2.0 | public | $0.3228 | $1.29 | 287 tok/s | 1 | — | |
| magnum-v4-72b | public | $3.23 | $5.38 | 287 tok/s | 1 | — | |
| medical-reasoning-r1 | public | $1.26 | $3.15 | — | 1 | — | |
| mercury-2 | anonymous | $0.3187 | $0.9563 | — | 1 | — | |
| mercury-2 | public | $0.1805 | $0.5414 | — | 2 | −28% | |
| mimo-v2.5 | private | $0.1428 | $0.2856 | — | 1 | — | |
| mimo-v2.5 | public | $0.1205 | $0.241 | 287 tok/s | 1 | — | |
| mimo-v2.5-pro | public | $0.3745 | $0.749 | 287 tok/s | 1 | — | |
| minimax-01 | public | $0.2152 | $1.18 | 287 tok/s | 1 | — | |
| minimax-m1 | public | $0.4304 | $2.37 | 287 tok/s | 1 | — | |
| minimax-m2 | public | $0.2744 | $1.10 | 287 tok/s | 1 | — | |
| minimax-m2-her | public | $0.3228 | $1.29 | 287 tok/s | 1 | — | |
| minimax-m2.1 | public | $0.3228 | $1.29 | 287 tok/s | 1 | — | |
| minimax-m2.5 | private | $0.2754 | $0.969 | — | 1 | — | |
| minimax-m2.5 | public | $0.1963 | $0.6872 | — | 2 | −24% | |
| minimax-m2.7 | private | $0.3825 | $1.53 | — | 1 | — | |
| minimax-m2.7 | public | $0.0578 | $0.1155 | — | 3 | −88% | |
| minimax-m3 | public | $0.1732 | $0.693 | — | 2 | −28% | |
| minimax-m3-preview | private | $0.306 | $1.22 | — | 1 | — | |
| ministral-14b-2512 | public | $0.2152 | $0.2152 | 287 tok/s | 1 | — | |
| ministral-3b-2512 | public | $0.1076 | $0.1076 | 287 tok/s | 1 | — | |
| ministral-8b-2512 | public | $0.1614 | $0.1614 | 287 tok/s | 1 | — | |
| mistral-large | public | $2.15 | $6.46 | 287 tok/s | 1 | — | |
| mistral-large-2407 | public | $2.15 | $6.46 | 287 tok/s | 1 | — | |
| mistral-large-2512 | public | $0.5381 | $1.61 | 287 tok/s | 1 | — | |
| mistral-medium-3 | public | $0.4304 | $2.15 | 287 tok/s | 1 | — | |
| mistral-medium-3.1 | public | $0.4304 | $2.15 | 287 tok/s | 1 | — | |
| mistral-medium-3.5 | public | $1.61 | $8.07 | 287 tok/s | 1 | — | |
| mistral-nemo | public | $0.0204 | $0.0323 | 287 tok/s | 1 | — | |
| mistral-saba | public | $0.2152 | $0.6457 | 287 tok/s | 1 | — | |
| mistral-small-24b-instruct-2501 | public | $0.0538 | $0.0861 | 287 tok/s | 1 | — | |
| mistral-small-2603 | private | $0.1913 | $0.765 | — | 1 | — | |
| mistral-small-2603 | public | $0.1614 | $0.6457 | 287 tok/s | 1 | — | |
| mistral-small-3.1-24b | public | $0.3777 | $0.5972 | 287 tok/s | 1 | — | |
| mistral-small-3.2-24b | private | $0.0956 | $0.255 | — | 1 | — | |
| mistral-small-3.2-24b | public | $0.0541 | $0.1444 | — | 2 | −28% | |
| mistral-small-4 | public | $0.0984 | $0.3937 | — | 1 | — | |
| mixtral-8x22b | public | $2.15 | $6.46 | 287 tok/s | 1 | — | |
| morph-v3-fast | public | $0.8609 | $1.29 | 287 tok/s | 1 | — | |
| morph-v3-large | public | $0.9685 | $2.04 | 287 tok/s | 1 | — | |
| muse-spark-1.1 | public | $1.35 | $4.57 | 287 tok/s | 1 | — | |
| mythomax-l2-13b | public | $0.0646 | $0.0646 | 287 tok/s | 1 | — | |
| nemotron-3-nano-30b-a3b | private | $0.0765 | $0.306 | — | 1 | — | |
| nemotron-3-nano-30b-a3b | public | $0.0538 | $0.2152 | 287 tok/s | 1 | — | |
| nemotron-3-super-120b-a12b | public | $0.1776 | $0.3847 | 287 tok/s | 1 | — | |
| nemotron-3-ultra-550b-a55b | private | $0.6375 | $3.19 | — | 1 | — | |
| nemotron-3-ultra-550b-a55b | public | $0.5381 | $2.37 | 287 tok/s | 1 | — | |
| nex-n2-mini | public | $0.0269 | $0.1076 | 287 tok/s | 1 | — | |
| nex-n2-pro | public | $0.269 | $1.08 | 287 tok/s | 1 | — | |
| nova-2-lite-v1 | public | $0.3228 | $2.69 | 287 tok/s | 1 | — | |
| nova-lite-v1 | public | $0.0646 | $0.2583 | 287 tok/s | 1 | — | |
| nova-micro-v1 | public | $0.0377 | $0.1507 | 287 tok/s | 1 | — | |
| nova-premier-v1 | public | $2.69 | $13.45 | 287 tok/s | 1 | — | |
| nova-pro-v1 | public | $0.8609 | $3.44 | 287 tok/s | 1 | — | |
| nvidia-nemotron-3-nano-30b | public | $0.0394 | $0.1575 | — | 1 | — | |
| o1 | public | $16.14 | $64.57 | 287 tok/s | 1 | — | |
| o1-pro | public | $161 | $646 | 287 tok/s | 1 | — | |
| o3 | public | $2.15 | $8.61 | 287 tok/s | 1 | — | |
| o3-mini | public | $1.18 | $4.73 | 287 tok/s | 1 | — | |
| o3-mini-high | public | $1.18 | $4.73 | 287 tok/s | 1 | — | |
| o3-pro | public | $21.52 | $86.09 | 287 tok/s | 1 | — | |
| o4-mini | public | $1.18 | $4.73 | 287 tok/s | 1 | — | |
| o4-mini-high | public | $1.18 | $4.73 | 287 tok/s | 1 | — | |
| olafangensan-glm-4.7-flash-heretic | private | $0.0714 | $0.408 | — | 1 | — | |
| olmo-3-32b-think | public | $0.1614 | $0.5381 | 287 tok/s | 1 | — | |
| openai-gpt-56-luna | anonymous | $1.27 | $7.65 | — | 1 | — | |
| openai-gpt-56-luna-pro | anonymous | $1.27 | $7.65 | — | 1 | — | |
| openai-gpt-56-sol | anonymous | $6.38 | $38.25 | — | 1 | — | |
| openai-gpt-56-sol-pro | anonymous | $6.38 | $38.25 | — | 1 | — | |
| openai-gpt-56-terra | anonymous | $3.19 | $19.12 | — | 1 | — | |
| openai-gpt-56-terra-pro | anonymous | $3.19 | $19.12 | — | 1 | — | |
| opus-4.5 | public | $3.15 | $15.75 | — | 1 | — | |
| opus-4.6 | public | $3.15 | $15.75 | — | 1 | — | |
| opus-4.7 | public | $3.15 | $15.75 | — | 1 | — | |
| opus-4.8 | public | $3.15 | $15.75 | — | 1 | — | |
| palmyra-x5 | public | $0.6457 | $6.46 | 287 tok/s | 1 | — | |
| perceptron-mk1 | public | $0.1614 | $1.61 | 287 tok/s | 1 | — | |
| phi-4 | public | $0.0753 | $0.1507 | 287 tok/s | 1 | — | |
| qwen-2.5-72b | public | $0.3874 | $0.4304 | 287 tok/s | 1 | — | |
| qwen-2.5-7b | public | $0.0289 | $0.0751 | — | 2 | −43% | |
| qwen-2.5-7b | encrypted (tee) | $0.0189 | $0.0491 | — | 2 | −63% | |
| qwen-2.5-coder-32b | public | $0.7102 | $1.08 | 287 tok/s | 1 | — | |
| qwen-3-235b-a22b-instruct-2507 | public | $0.0788 | $0.3937 | — | 1 | — | |
| qwen-3-235b-a22b-thinking-2507 | public | $0.2362 | $1.84 | — | 1 | — | |
| qwen-3-coder-480b-turbo | public | $0.1837 | $0.7875 | — | 1 | — | |
| qwen-3-next-80b | public | $0.1837 | $0.9975 | — | 1 | — | |
| qwen-3.5-35b-a3b | public | $0.1641 | $0.6562 | — | 1 | — | |
| qwen-3.5-397b | public | $0.3937 | $2.36 | — | 1 | — | |
| qwen-3.5-9b | public | $0.0525 | $0.0788 | — | 1 | — | |
| qwen-3.6-27b | public | $0.1706 | $1.71 | — | 1 | — | |
| qwen-3.6-plus-uncensored | public | $0.3281 | $1.97 | — | 1 | — | |
| qwen-3.7-plus | public | $0.2625 | $1.05 | — | 1 | — | |
| qwen-3.8-max | anonymous | $2.55 | $7.65 | — | 1 | — | |
| qwen-plus | public | $0.2798 | $0.8394 | 287 tok/s | 1 | — | |
| qwen-plus-2025.07-28 | public | $0.2798 | $0.8394 | 287 tok/s | 1 | — | |
| qwen-plus-2025.07-28:thinking | public | $0.4304 | $1.29 | 287 tok/s | 1 | — | |
| qwen2.5-vl-72b | public | $0.269 | $0.8071 | 287 tok/s | 1 | — | |
| qwen3-14b | public | $0.1076 | $0.2367 | 287 tok/s | 1 | — | |
| qwen3-235b-a22b | public | $0.0097 | $0.0386 | — | 2 | −98% | |
| qwen3-235b-a22b-2507 | private | $0.153 | $0.765 | — | 1 | — | |
| qwen3-235b-a22b-2507 | public | $0.0968 | $0.5919 | 287 tok/s | 1 | — | |
| qwen3-235b-a22b-thinking-2507 | private | $0.459 | $3.57 | — | 1 | — | |
| qwen3-235b-a22b-thinking-2507 | public | $0.2475 | $2.48 | 287 tok/s | 1 | — | |
| qwen3-235b-thinking | public | $0.4725 | $3.67 | — | 1 | — | |
| qwen3-30b-a3b | public | $0.1097 | $0.3985 | — | 2 | −21% | |
| qwen3-30b-a3b | encrypted (tee) | $0.0453 | $0.1888 | — | 2 | −63% | |
| qwen3-30b-a3b-instruct-2507 | public | $0.0518 | $0.2077 | 287 tok/s | 1 | — | |
| qwen3-30b-a3b-thinking-2507 | public | $0.2152 | $2.58 | 287 tok/s | 1 | — | |
| qwen3-32b | public | $0.0861 | $0.3013 | 287 tok/s | 1 | — | |
| qwen3-8b | public | $0.1259 | $0.4896 | 287 tok/s | 1 | — | |
| qwen3-coder | public | $0.3228 | $1.08 | 287 tok/s | 1 | — | |
| qwen3-coder-30b-a3b | public | $0.0753 | $0.3013 | 287 tok/s | 1 | — | |
| qwen3-coder-480b-a35b-instruct-turbo | private | $0.357 | $1.53 | — | 1 | — | |
| qwen3-coder-480b-turbo | public | $0.231 | $1.05 | — | 1 | — | |
| qwen3-coder-flash | public | $0.2098 | $1.05 | 287 tok/s | 1 | — | |
| qwen3-coder-next | public | $0.1291 | $0.8609 | 287 tok/s | 1 | — | |
| qwen3-coder-next-80b | public | $0.0945 | $1.16 | — | 1 | — | |
| qwen3-coder-plus | public | $0.6995 | $3.50 | 287 tok/s | 1 | — | |
| qwen3-max | public | $0.8394 | $4.20 | 287 tok/s | 1 | — | |
| qwen3-max-thinking | public | $0.8394 | $4.20 | 287 tok/s | 1 | — | |
| qwen3-next-80b | private | $0.357 | $1.94 | — | 1 | — | |
| qwen3-next-80b-a3b | public | $0.1049 | $0.8394 | 287 tok/s | 1 | — | |
| qwen3-next-80b-a3b-thinking | public | $0.1614 | $1.29 | 287 tok/s | 1 | — | |
| qwen3-vl-235b | public | $0.1313 | $0.7875 | — | 1 | — | |
| qwen3-vl-235b-a22b | private | $0.2142 | $1.94 | — | 1 | — | |
| qwen3-vl-235b-a22b | public | $0.2798 | $1.12 | 287 tok/s | 1 | — | |
| qwen3-vl-235b-a22b-thinking | public | $1.05 | $4.25 | 287 tok/s | 1 | — | |
| qwen3-vl-30b-a3b | public | $0.1399 | $0.5596 | 287 tok/s | 1 | — | |
| qwen3-vl-30b-a3b | encrypted (tee) | $0.0491 | $0.1964 | — | 2 | −63% | |
| qwen3-vl-30b-a3b-thinking | public | $0.3121 | $1.08 | 287 tok/s | 1 | — | |
| qwen3-vl-32b | public | $0.1119 | $0.4477 | 287 tok/s | 1 | — | |
| qwen3-vl-8b | public | $0.1259 | $0.4896 | 287 tok/s | 1 | — | |
| qwen3-vl-8b-thinking | public | $0.1937 | $2.26 | 287 tok/s | 1 | — | |
| qwen3.5-122b-a10b | public | $0.2798 | $2.24 | 287 tok/s | 1 | — | |
| qwen3.5-27b | public | $0.2098 | $1.68 | 287 tok/s | 1 | — | |
| qwen3.5-35b-a3b | private | $0.3187 | $1.27 | — | 1 | — | |
| qwen3.5-35b-a3b | public | $0.1507 | $1.08 | 287 tok/s | 1 | — | |
| qwen3.5-397b-a17b | anonymous | $0.765 | $4.59 | — | 1 | — | |
| qwen3.5-397b-a17b | public | $0.4197 | $2.52 | 287 tok/s | 1 | — | |
| qwen3.5-9b | private | $0.102 | $0.153 | — | 1 | — | |
| qwen3.5-9b | public | $0.1076 | $0.1614 | 287 tok/s | 1 | — | |
| qwen3.5-flash-02.23 | public | $0.0699 | $0.2798 | 287 tok/s | 1 | — | |
| qwen3.5-plus-02.15 | public | $0.2798 | $1.68 | 287 tok/s | 1 | — | |
| qwen3.5-plus-20260420 | public | $0.3228 | $1.94 | 287 tok/s | 1 | — | |
| qwen3.6-27b | private | $0.3529 | $3.53 | — | 1 | — | |
| qwen3.6-27b | public | $0.3228 | $2.15 | 287 tok/s | 1 | — | |
| qwen3.6-35b-a3b | private | $0.102 | $1.02 | — | 1 | — | |
| qwen3.6-35b-a3b | public | $0.1055 | $1.02 | 287 tok/s | 1 | — | |
| qwen3.6-35b-a3b-uncensored | encrypted (tee) | $0.1435 | $0.7101 | — | 2 | −63% | |
| qwen3.6-flash | public | $0.2018 | $1.21 | 287 tok/s | 1 | — | |
| qwen3.6-max-preview | public | $1.11 | $6.63 | 287 tok/s | 1 | — | |
| qwen3.6-plus | anonymous | $0.6375 | $3.83 | — | 1 | — | |
| qwen3.6-plus | public | $0.3497 | $2.10 | 287 tok/s | 1 | — | |
| qwen3.7-flash | public | $0.0323 | $0.1399 | 287 tok/s | 1 | — | |
| qwen3.7-max | anonymous | $2.75 | $8.21 | — | 1 | — | |
| qwen3.7-max | public | $1.59 | $4.76 | 287 tok/s | 1 | — | |
| qwen3.7-plus | anonymous | $0.51 | $2.04 | — | 1 | — | |
| qwen3.7-plus | public | $0.3444 | $1.38 | 287 tok/s | 1 | — | |
| qwen3.8-max | public | $2.15 | $6.46 | 287 tok/s | 1 | — | |
| qwen35b | public | $0.0063 | $0.021 | — | 1 | — | |
| qwencoder | public | $0.0063 | $0.021 | — | 1 | — | |
| reka-edge | public | $0.1076 | $0.1076 | 287 tok/s | 1 | — | |
| reka-flash-3 | public | $0.1076 | $0.2152 | 287 tok/s | 1 | — | |
| relace-apply-3 | public | $0.9147 | $1.35 | 287 tok/s | 1 | — | |
| relace-search | public | $1.08 | $3.23 | 287 tok/s | 1 | — | |
| remm-slerp-l2-13b | public | $0.4842 | $0.6995 | 287 tok/s | 1 | — | |
| ring-2.6.1t | public | $0.0807 | $0.6726 | 287 tok/s | 1 | — | |
| rocinante-12b | public | $0.269 | $0.5381 | 287 tok/s | 1 | — | |
| seed-1.6 | public | $0.269 | $2.15 | 287 tok/s | 1 | — | |
| seed-1.6-flash | public | $0.0807 | $0.3228 | 287 tok/s | 1 | — | |
| seed-2.0-lite | public | $0.269 | $2.15 | 287 tok/s | 1 | — | |
| seed-2.0-mini | public | $0.1076 | $0.4304 | 287 tok/s | 1 | — | |
| seed-2.1-turbo | anonymous | $0.6375 | $3.19 | — | 1 | — | |
| skyfall-36b-v2 | public | $0.5919 | $0.8609 | 287 tok/s | 1 | — | |
| solar-pro-3 | public | $0.1614 | $0.6457 | 287 tok/s | 1 | — | |
| sonar | public | $1.08 | $1.08 | 287 tok/s | 1 | — | |
| sonar-deep-research | public | $2.15 | $8.61 | 287 tok/s | 1 | — | |
| sonar-pro | public | $3.23 | $16.14 | 287 tok/s | 1 | — | |
| sonar-pro-search | public | $3.23 | $16.14 | 287 tok/s | 1 | — | |
| sonar-reasoning-pro | public | $2.15 | $8.61 | 287 tok/s | 1 | — | |
| sonnet-4.5 | public | $1.97 | $9.84 | — | 1 | — | |
| sonnet-4.6 | public | $1.89 | $9.45 | — | 1 | — | |
| step-3.5-flash | public | $0.1076 | $0.3228 | 287 tok/s | 1 | — | |
| step-3.7-flash | public | $0.2152 | $1.24 | 287 tok/s | 1 | — | |
| trinity-large-thinking | public | $0.1805 | $0.6497 | — | 2 | −20% | |
| ui-tars-1.5-7b | public | $0.1076 | $0.2152 | 287 tok/s | 1 | — | |
| unslopnemo-12b | public | $0.4304 | $0.4304 | 287 tok/s | 1 | — | |
| venice-role-play-uncensored | public | $0.2625 | $1.05 | — | 1 | — | |
| venice-uncensored-1.1 | public | $0.1313 | $0.6038 | — | 1 | — | |
| venice-uncensored-1.2 | private | $0.204 | $0.918 | — | 1 | — | |
| venice-uncensored-1.2 | public | $0.1155 | $0.5198 | — | 1 | −43% | |
| venice-uncensored-24b | encrypted (tee) | $0.0944 | $0.4343 | — | 2 | −63% | |
| venice-uncensored-role-play | private | $0.51 | $2.04 | — | 1 | — | |
| virtuoso-large | public | $0.8071 | $1.29 | 287 tok/s | 1 | — | |
| voxtral-small-24b-2507 | public | $0.1076 | $0.3228 | 287 tok/s | 1 | — | |
| weaver | public | $0.5381 | $0.8071 | 287 tok/s | 1 | — | |
| wizardlm-2.8x22b | public | $0.6672 | $0.6672 | 287 tok/s | 1 | — | |
| z-ai-glm-5v-turbo | anonymous | $1.53 | $5.10 | — | 1 | — |