Yunwu relay pricing and ratios
Yunwu currently has 134 model price rows with 48% cache price coverage.
| Model | Ratio | Input | Output | Cache read |
|---|---|---|---|---|
| text-embedding-3-small | 0.50x | 0.01 USD/M tokens | 0.01 USD/M tokens | Not listed |
| BAAI/bge-reranker-v2-m3 | 0.26x | 0.01 USD/M tokens | 0.01 USD/M tokens | Not listed |
| glm-4.5-flash | 0.10x | 0.02 USD/M tokens | 0.08 USD/M tokens | Not listed |
| text-embedding-ada-002 | 0.45x | 0.06 USD/M tokens | 0.06 USD/M tokens | Not listed |
| text-embedding-3-large | 0.60x | 0.08 USD/M tokens | 0.08 USD/M tokens | Not listed |
| llama-3.3-70b | 0.08x | 0.06 USD/M tokens | 0.18 USD/M tokens | Not listed |
| gpt-5-nano-2025-08-07 | 0.60x | 0.03 USD/M tokens | 0.24 USD/M tokens | Free USD/M tokens |
| gpt-5-nano | 0.60x | 0.03 USD/M tokens | 0.24 USD/M tokens | Free USD/M tokens |
| Qwen/Qwen3-Reranker-0.6B | 0.73x | 0.14 USD/M tokens | 0.14 USD/M tokens | Not listed |
| Pro/BAAI/bge-reranker-v2-m3 | 1.00x | 0.14 USD/M tokens | 0.14 USD/M tokens | Not listed |
| gpt-4.1-nano-2025-04-14 | 0.60x | 0.06 USD/M tokens | 0.24 USD/M tokens | 0.02 USD/M tokens |
| gpt-4.1-nano | 0.60x | 0.06 USD/M tokens | 0.24 USD/M tokens | Not listed |
| gpt-4o-mini-2024-07-18 | 0.60x | 0.09 USD/M tokens | 0.36 USD/M tokens | 0.05 USD/M tokens |
| gpt-4o-mini | 0.60x | 0.09 USD/M tokens | 0.36 USD/M tokens | 0.05 USD/M tokens |
| gemini-2.5-flash-lite | 1.00x | 0.10 USD/M tokens | 0.40 USD/M tokens | 0.01 USD/M tokens |
| qwen-turbo | 0.35x | 0.18 USD/M tokens | 0.36 USD/M tokens | Not listed |
| glm-4-air | 0.22x | 0.30 USD/M tokens | 0.30 USD/M tokens | Not listed |
| gpt-5.4-nano | 0.60x | 0.12 USD/M tokens | 0.75 USD/M tokens | Not listed |
| glm-4-long | 0.33x | 0.18 USD/M tokens | 0.72 USD/M tokens | Not listed |
| glm-4-flash | 0.60x | 0.18 USD/M tokens | 0.72 USD/M tokens | Not listed |
| glm-4 | 0.46x | 0.18 USD/M tokens | 0.72 USD/M tokens | Not listed |
| gpt-5.6-luna | 0.14x | 0.16 USD/M tokens | 0.96 USD/M tokens | 0.02 USD/M tokens |
| gpt-4.1-mini-2025-04-14 | 0.60x | 0.24 USD/M tokens | 0.96 USD/M tokens | 0.06 USD/M tokens |
| gpt-4.1-mini | 0.60x | 0.24 USD/M tokens | 0.96 USD/M tokens | Not listed |
| gpt-5-mini-2025-08-07 | 0.60x | 0.15 USD/M tokens | 1.20 USD/M tokens | 0.02 USD/M tokens |
| gpt-5-mini | 0.60x | 0.15 USD/M tokens | 1.20 USD/M tokens | 0.02 USD/M tokens |
| gpt-5.4-nano-2026-03-17 | 1.00x | 0.20 USD/M tokens | 1.25 USD/M tokens | Not listed |
| qwen3-vl-flash | 0.25x | 0.15 USD/M tokens | 1.50 USD/M tokens | Not listed |
| qwen-flash | 0.56x | 0.15 USD/M tokens | 1.50 USD/M tokens | Not listed |
| qwen-plus | 0.37x | 0.48 USD/M tokens | 1.20 USD/M tokens | Not listed |
| gemini-3.1-flash-lite | 1.00x | 0.25 USD/M tokens | 1.50 USD/M tokens | 0.03 USD/M tokens |
| gemini-embedding-001 | 0.03x | 0.36 USD/M tokens | 1.44 USD/M tokens | Not listed |
| llama-3.3-70b-instruct | 0.38x | 1.08 USD/M tokens | 1.08 USD/M tokens | Not listed |
| qwen3.5-flash | 0.01x | 0.20 USD/M tokens | 2.00 USD/M tokens | Not listed |
| gemini-embedding-2-preview | 1.87x | 0.48 USD/M tokens | 1.92 USD/M tokens | Not listed |
| qwen3-vl-8b-instruct | 1.00x | 0.50 USD/M tokens | 2.00 USD/M tokens | Not listed |
| qwen3-8b | 0.70x | 0.50 USD/M tokens | 2.00 USD/M tokens | Not listed |
| gemini-2.5-flash | 1.00x | 0.30 USD/M tokens | 2.50 USD/M tokens | 0.03 USD/M tokens |
| mimo-v2.5 | 0.86x | 1.00 USD/M tokens | 2.00 USD/M tokens | 0.02 USD/M tokens |
| gpt-5.4-mini | 0.50x | 0.45 USD/M tokens | 2.70 USD/M tokens | 0.05 USD/M tokens |
| doubao-seed-2-0-mini-260428 | 1.50x | 0.30 USD/M tokens | 3.00 USD/M tokens | Not listed |
| o4-mini | 0.60x | 0.66 USD/M tokens | 2.64 USD/M tokens | 0.17 USD/M tokens |
| qwen-vl-max | 0.60x | 0.96 USD/M tokens | 2.40 USD/M tokens | Not listed |
| gemini-3-flash-preview | 0.75x | 0.50 USD/M tokens | 3.00 USD/M tokens | 0.05 USD/M tokens |
| grok-4.3 | 1.00x | 1.25 USD/M tokens | 2.50 USD/M tokens | Not listed |
| qwen3-30b-a3b-instruct-2507 | 0.99x | 0.75 USD/M tokens | 3.00 USD/M tokens | Not listed |
| qwen3-vl-30b-a3b-instruct | 0.99x | 0.75 USD/M tokens | 3.00 USD/M tokens | Not listed |
| llama-3.1-8b | 1.00x | 2.00 USD/M tokens | 2.00 USD/M tokens | Not listed |
| gemini-3.6-flash | 0.50x | 0.75 USD/M tokens | 3.75 USD/M tokens | 0.08 USD/M tokens |
| deepseek-v3.2-exp | 1.00x | 2.00 USD/M tokens | 3.00 USD/M tokens | 0.20 USD/M tokens |
| DeepSeek-V3.2 | 1.00x | 2.00 USD/M tokens | 3.00 USD/M tokens | Not listed |
| deepseek-chat | 1.00x | 2.00 USD/M tokens | 3.00 USD/M tokens | 0.50 USD/M tokens |
| gpt-5.4-mini-2026-03-17 | 1.00x | 0.75 USD/M tokens | 4.50 USD/M tokens | Not listed |
| qwen3.5-27b | 0.33x | 0.60 USD/M tokens | 4.80 USD/M tokens | Not listed |
| gpt-oss-120b | 0.22x | 1.10 USD/M tokens | 4.40 USD/M tokens | Not listed |
| qwen3.5-plus-2026-02-15 | 0.20x | 0.80 USD/M tokens | 4.80 USD/M tokens | Not listed |
| qwen3.5-plus | 1.00x | 0.80 USD/M tokens | 4.80 USD/M tokens | Not listed |
| claude-haiku-4-5-20251001 | 0.63x | 1.00 USD/M tokens | 5.00 USD/M tokens | 0.10 USD/M tokens |
| gpt-4.1-2025-04-14 | 0.60x | 1.20 USD/M tokens | 4.80 USD/M tokens | 0.30 USD/M tokens |
| gpt-4.1 | 0.60x | 1.20 USD/M tokens | 4.80 USD/M tokens | 0.60 USD/M tokens |
| gpt-3.5-turbo-0125 | 3.00x | 1.50 USD/M tokens | 4.50 USD/M tokens | Not listed |
| gpt-3.5-turbo | 3.00x | 1.50 USD/M tokens | 4.50 USD/M tokens | Not listed |
| o3-2025-04-16 | 0.60x | 1.20 USD/M tokens | 4.80 USD/M tokens | 0.30 USD/M tokens |
| glm-4.6 | 0.30x | 1.20 USD/M tokens | 4.80 USD/M tokens | Not listed |
| doubao-seed-2-0-lite-260428 | 1.50x | 0.90 USD/M tokens | 5.40 USD/M tokens | Not listed |
| gemini-3.5-flash-lite | 2.40x | 0.72 USD/M tokens | 6.00 USD/M tokens | 0.07 USD/M tokens |
| gpt-5.1-2025-11-13 | 0.60x | 0.75 USD/M tokens | 6.00 USD/M tokens | 0.08 USD/M tokens |
| GPT-5.1 Codex | 0.60x | 0.75 USD/M tokens | 6.00 USD/M tokens | 0.08 USD/M tokens |
| GPT-5.1 | 0.60x | 0.75 USD/M tokens | 6.00 USD/M tokens | 0.08 USD/M tokens |
| gpt-5-2025-08-07 | 0.60x | 0.75 USD/M tokens | 6.00 USD/M tokens | 0.08 USD/M tokens |
| gpt-5-chat-latest | 0.60x | 0.75 USD/M tokens | 6.00 USD/M tokens | 0.08 USD/M tokens |
| GPT-5 Codex | 0.60x | 0.75 USD/M tokens | 6.00 USD/M tokens | 0.08 USD/M tokens |
| GPT-5 | 0.60x | 0.75 USD/M tokens | 6.00 USD/M tokens | 0.08 USD/M tokens |
| gpt-4o-2024-11-20 | 0.60x | 1.50 USD/M tokens | 6.00 USD/M tokens | 0.75 USD/M tokens |
| gpt-4o-2024-08-06 | 0.60x | 1.50 USD/M tokens | 6.00 USD/M tokens | 0.75 USD/M tokens |
| gpt-4o-transcribe | 0.60x | 1.50 USD/M tokens | 6.00 USD/M tokens | Not listed |
| gpt-4o | 0.60x | 1.50 USD/M tokens | 6.00 USD/M tokens | 0.75 USD/M tokens |
| qwen3-coder-30b-a3b-instruct | 1.00x | 1.50 USD/M tokens | 6.00 USD/M tokens | Not listed |
| qwen3-max | 0.21x | 1.50 USD/M tokens | 6.00 USD/M tokens | Not listed |
| grok-4.5 | 1.00x | 2.00 USD/M tokens | 6.00 USD/M tokens | 0.50 USD/M tokens |
| qwen3.5-397b-a17b | 0.40x | 1.20 USD/M tokens | 7.20 USD/M tokens | Not listed |
| gpt-5.3-codex | 0.24x | 1.05 USD/M tokens | 8.40 USD/M tokens | 0.11 USD/M tokens |
| gpt-5.2 | 0.60x | 1.05 USD/M tokens | 8.40 USD/M tokens | 0.11 USD/M tokens |
| deepseek-v3.1 | 0.60x | 2.40 USD/M tokens | 7.20 USD/M tokens | Not listed |
| qwen3.7-plus | 0.07x | 2.00 USD/M tokens | 8.00 USD/M tokens | 0.40 USD/M tokens |
| qwen3-235b-a22b-instruct-2507 | 1.00x | 2.00 USD/M tokens | 8.00 USD/M tokens | Not listed |
| qwen3-vl-235b-a22b-instruct | 1.00x | 2.00 USD/M tokens | 8.00 USD/M tokens | Not listed |
| qwen3-vl-32b-instruct | 1.00x | 2.00 USD/M tokens | 8.00 USD/M tokens | Not listed |
| gpt-5.4 | 0.60x | 1.50 USD/M tokens | 9.00 USD/M tokens | 0.15 USD/M tokens |
| gemini-3.5-flash | 1.00x | 1.50 USD/M tokens | 9.00 USD/M tokens | 0.15 USD/M tokens |
| MiniMax-M3 | 0.07x | 2.10 USD/M tokens | 8.40 USD/M tokens | 0.42 USD/M tokens |
| MiniMax-M2.7 | 1.00x | 2.10 USD/M tokens | 8.40 USD/M tokens | Not listed |
| grok-4 | 0.60x | 1.80 USD/M tokens | 9.00 USD/M tokens | Not listed |
| gpt-5.6-terra | 0.56x | 1.60 USD/M tokens | 9.60 USD/M tokens | 0.16 USD/M tokens |
| gemini-2.5-pro | 0.02x | 1.25 USD/M tokens | 10.00 USD/M tokens | 0.13 USD/M tokens |
| claude-sonnet-5 | 0.67x | 2.00 USD/M tokens | 10.00 USD/M tokens | 0.20 USD/M tokens |
| deepseek-v4-flash | 1.00x | 3.00 USD/M tokens | 9.00 USD/M tokens | 0.10 USD/M tokens |
| deepseek-r1 | 0.60x | 2.40 USD/M tokens | 9.60 USD/M tokens | Not listed |
| deepseek-reasoner | 0.60x | 2.40 USD/M tokens | 9.60 USD/M tokens | 0.60 USD/M tokens |
| gpt-4o-2024-05-13 | 0.60x | 3.00 USD/M tokens | 9.00 USD/M tokens | Not listed |
| qwen3-coder-plus | 0.08x | 2.40 USD/M tokens | 9.60 USD/M tokens | Not listed |
| qwen-max | 0.90x | 2.40 USD/M tokens | 9.60 USD/M tokens | Not listed |
| qwen3.6-35b-a3b | 1.00x | 1.80 USD/M tokens | 10.80 USD/M tokens | Not listed |
| doubao-seed-1-8-251228 | 1.50x | 1.20 USD/M tokens | 12.00 USD/M tokens | Not listed |
| gemini-3.1-pro-preview | 0.03x | 2.00 USD/M tokens | 12.00 USD/M tokens | 0.20 USD/M tokens |
| gemini-3-pro-preview | 0.03x | 2.00 USD/M tokens | 12.00 USD/M tokens | 0.20 USD/M tokens |
| qwen3.6-plus | 0.09x | 2.00 USD/M tokens | 12.00 USD/M tokens | Not listed |
| claude-sonnet-4-6 | 0.63x | 3.00 USD/M tokens | 15.00 USD/M tokens | 0.30 USD/M tokens |
| claude-sonnet-4-5-20250929 | 1.00x | 3.00 USD/M tokens | 15.00 USD/M tokens | 0.30 USD/M tokens |
| kimi-k2 | 1.00x | 4.00 USD/M tokens | 16.00 USD/M tokens | Not listed |
| gpt-5.5 | 0.27x | 3.00 USD/M tokens | 18.00 USD/M tokens | 0.30 USD/M tokens |
| gpt-chat-latest | 0.60x | 3.00 USD/M tokens | 18.00 USD/M tokens | Not listed |
| glm-5 | 0.15x | 4.00 USD/M tokens | 18.00 USD/M tokens | Not listed |
| gpt-4-turbo | 0.60x | 6.00 USD/M tokens | 18.00 USD/M tokens | Not listed |
| kimi-k2.5 | 1.00x | 4.00 USD/M tokens | 21.00 USD/M tokens | Not listed |
| gpt-5.6-sol | 0.70x | 4.00 USD/M tokens | 24.00 USD/M tokens | 0.40 USD/M tokens |
| gpt-image-2 | 0.08x | 4.00 USD/M tokens | 24.00 USD/M tokens | Not listed |
| qwen3.7-max | 0.60x | 7.20 USD/M tokens | 21.60 USD/M tokens | Not listed |
| claude-opus-4-8 | 0.63x | 5.00 USD/M tokens | 25.00 USD/M tokens | 0.50 USD/M tokens |
| claude-opus-4-6 | 0.63x | 5.00 USD/M tokens | 25.00 USD/M tokens | 0.50 USD/M tokens |