AIHubMix relay pricing and ratios
AIHubMix currently has 717 model price rows with 49% cache price coverage.
| Model | Ratio | Input | Output | Cache read |
|---|---|---|---|---|
| llama3-groq-70b-8192-tool-use-preview | - | Free USD/M tokens | Free USD/M tokens | Not listed |
| mistralai/mistral-7b-instruct:free | - | Free USD/M tokens | Free USD/M tokens | Not listed |
| llama3-groq-8b-8192-tool-use-preview | - | Free USD/M tokens | Free USD/M tokens | Not listed |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-7B | 0.01x | 0.01 USD/M tokens | 0.01 USD/M tokens | Not listed |
| gemini-embedding-exp-03-07 | 0.01x | 0.02 USD/M tokens | 0.02 USD/M tokens | Not listed |
| DeepSeek OCR | 0.38x | 0.02 USD/M tokens | 0.02 USD/M tokens | Not listed |
| text-embedding-004 | 0.01x | 0.02 USD/M tokens | 0.02 USD/M tokens | Not listed |
| meta-llama/llama-3.2-11b-vision-instruct:free | 1.00x | 0.02 USD/M tokens | 0.02 USD/M tokens | Not listed |
| meta-llama/llama-3.2-3b-instruct:free | 1.00x | 0.02 USD/M tokens | 0.02 USD/M tokens | Not listed |
| meta-llama/llama-3.1-405b-instruct:free | 1.00x | 0.02 USD/M tokens | 0.02 USD/M tokens | Not listed |
| meta-llama/llama-3.1-70b-instruct:free | 1.00x | 0.02 USD/M tokens | 0.02 USD/M tokens | Not listed |
| meta-llama/llama-3.1-8b-instruct:free | 1.00x | 0.02 USD/M tokens | 0.02 USD/M tokens | Not listed |
| text-embedding-3-small | 1.00x | 0.02 USD/M tokens | 0.02 USD/M tokens | Not listed |
| google/gemma-2-9b-it:free | 1.00x | 0.02 USD/M tokens | 0.02 USD/M tokens | Not listed |
| tngtech/DeepSeek-R1T-Chimera | 1.00x | 0.02 USD/M tokens | 0.02 USD/M tokens | Not listed |
| omni-moderation-latest | 0.10x | 0.02 USD/M tokens | 0.02 USD/M tokens | Not listed |
| jina-embeddings-v5-text-small | 1.00x | 0.05 USD/M tokens | Free USD/M tokens | Not listed |
| jina-embeddings-v5-text-nano | 1.00x | 0.05 USD/M tokens | Free USD/M tokens | Not listed |
| BAAI/bge-reranker-v2-m3 | 0.78x | 0.03 USD/M tokens | 0.03 USD/M tokens | Not listed |
| BAAI/bge-large-zh-v1.5 | 0.78x | 0.03 USD/M tokens | 0.03 USD/M tokens | Not listed |
| BAAI/bge-large-en-v1.5 | 0.16x | 0.03 USD/M tokens | 0.03 USD/M tokens | Not listed |
| glm-ocr | 1.00x | 0.03 USD/M tokens | 0.03 USD/M tokens | Not listed |
| ernie-4.5-0.3b | 0.11x | 0.01 USD/M tokens | 0.05 USD/M tokens | Not listed |
| qwen3-embedding-8b | 1.00x | 0.07 USD/M tokens | Free USD/M tokens | Not listed |
| qwen3-embedding-0.6b | 1.00x | 0.07 USD/M tokens | Free USD/M tokens | Not listed |
| cohere-rerank-v4.0-pro | 1.00x | 0.07 USD/M tokens | Free USD/M tokens | 0.07 USD/M tokens |
| cohere-rerank-v4.0-fast | 1.00x | 0.07 USD/M tokens | Free USD/M tokens | 0.07 USD/M tokens |
| bce-reranker-base | 1.00x | 0.07 USD/M tokens | Free USD/M tokens | Not listed |
| coding-glm-4.5-air | 1.00x | 0.01 USD/M tokens | 0.08 USD/M tokens | Not listed |
| THUDM/GLM-4-9B-0414 | 0.03x | 0.05 USD/M tokens | 0.05 USD/M tokens | Not listed |
| jina-embeddings-v4 | 0.01x | 0.05 USD/M tokens | 0.05 USD/M tokens | Not listed |
| jina-reranker-v3.5 | 1.00x | 0.05 USD/M tokens | 0.05 USD/M tokens | Not listed |
| jina-reranker-v3 | 1.00x | 0.05 USD/M tokens | 0.05 USD/M tokens | Not listed |
| jina-embeddings-v3 | 0.01x | 0.05 USD/M tokens | 0.05 USD/M tokens | Free USD/M tokens |
| jina-embeddings-v2-base-code | 0.00x | 0.05 USD/M tokens | 0.05 USD/M tokens | Not listed |
| jina-colbert-v2 | 0.00x | 0.05 USD/M tokens | 0.05 USD/M tokens | Not listed |
| jina-clip-v2 | 0.00x | 0.05 USD/M tokens | 0.05 USD/M tokens | Not listed |
| THUDM/GLM-Z1-9B-0414 | 0.03x | 0.05 USD/M tokens | 0.05 USD/M tokens | Not listed |
| jina-deepsearch-v1 | 0.19x | 0.05 USD/M tokens | 0.05 USD/M tokens | Not listed |
| jina-search | 1.00x | 0.05 USD/M tokens | 0.05 USD/M tokens | Not listed |
| jina-reranker-m0 | 0.00x | 0.05 USD/M tokens | 0.05 USD/M tokens | Not listed |
| jina-reader | 1.00x | 0.05 USD/M tokens | 0.05 USD/M tokens | Not listed |
| embed-v-4-0 | 1.00x | 0.12 USD/M tokens | Free USD/M tokens | 0.12 USD/M tokens |
| coding-glm-5.3-flash | 1.00x | 0.03 USD/M tokens | 0.10 USD/M tokens | 0.01 USD/M tokens |
| qwen-turbo-2025-04-28 | 0.10x | 0.05 USD/M tokens | 0.09 USD/M tokens | Free USD/M tokens |
| qwen-turbo-2024-11-01 | 0.10x | 0.05 USD/M tokens | 0.09 USD/M tokens | Not listed |
| tao-8k | 1.00x | 0.07 USD/M tokens | 0.07 USD/M tokens | Not listed |
| qwen3.7-flash | 0.15x | 0.03 USD/M tokens | 0.11 USD/M tokens | 0.01 USD/M tokens |
| qwen3-embedding-4b | 1.00x | 0.07 USD/M tokens | 0.07 USD/M tokens | Not listed |
| qwen-turbo-latest | 0.10x | 0.05 USD/M tokens | 0.09 USD/M tokens | 0.01 USD/M tokens |
| qwen-turbo | 0.10x | 0.05 USD/M tokens | 0.09 USD/M tokens | 0.01 USD/M tokens |
| embedding-3 | 1.00x | 0.07 USD/M tokens | 0.07 USD/M tokens | Not listed |
| embedding-2 | 1.00x | 0.07 USD/M tokens | 0.07 USD/M tokens | Not listed |
| bge-large-zh | 1.00x | 0.07 USD/M tokens | 0.07 USD/M tokens | Not listed |
| bge-large-en | 1.00x | 0.07 USD/M tokens | 0.07 USD/M tokens | Not listed |
| groq-llama-3.1-8b-instant | 1.00x | 0.06 USD/M tokens | 0.09 USD/M tokens | Not listed |
| Doubao-1.5-lite-32k | 1.00x | 0.05 USD/M tokens | 0.10 USD/M tokens | 0.01 USD/M tokens |
| THUDM/GLM-4-32B-0414 | 0.03x | 0.08 USD/M tokens | 0.08 USD/M tokens | Not listed |
| text-embedding-v4 | 0.12x | 0.08 USD/M tokens | 0.08 USD/M tokens | Not listed |
| Qwen/Qwen2-7B-Instruct | 0.00x | 0.08 USD/M tokens | 0.08 USD/M tokens | Not listed |
| THUDM/GLM-Z1-32B-0414 | 0.03x | 0.08 USD/M tokens | 0.08 USD/M tokens | Not listed |
| Doubao-lite-32k | 0.20x | 0.06 USD/M tokens | 0.12 USD/M tokens | 0.01 USD/M tokens |
| Doubao-lite-4k | 0.20x | 0.06 USD/M tokens | 0.12 USD/M tokens | 0.06 USD/M tokens |
| agnes-2.5-flash | 1.00x | 0.03 USD/M tokens | 0.15 USD/M tokens | Not listed |
| deepseek-ai/DeepSeek-Prover-V2-671B | 1.00x | 0.10 USD/M tokens | 0.10 USD/M tokens | Not listed |
| llama2-7b-2048 | 1.00x | 0.10 USD/M tokens | 0.10 USD/M tokens | Not listed |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-14B | 0.03x | 0.10 USD/M tokens | 0.10 USD/M tokens | Not listed |
| gemini-embedding-2 | 1.00x | 0.20 USD/M tokens | Free USD/M tokens | 0.20 USD/M tokens |
| THUDM/GLM-4.1V-9B-Thinking | 0.10x | 0.10 USD/M tokens | 0.10 USD/M tokens | Free USD/M tokens |
| Pro/THUDM/GLM-4.1V-9B-Thinking | 0.02x | 0.04 USD/M tokens | 0.16 USD/M tokens | Free USD/M tokens |
| glm-4-flash | 0.21x | 0.10 USD/M tokens | 0.10 USD/M tokens | Not listed |
| cc-minimax-m3 | 1.00x | 0.10 USD/M tokens | 0.10 USD/M tokens | Not listed |
| mm-minimax-m2.7-highspeed | 1.00x | 0.10 USD/M tokens | 0.10 USD/M tokens | Not listed |
| cc-minimax-m2.7-highspeed | 1.00x | 0.10 USD/M tokens | 0.10 USD/M tokens | Not listed |
| cc-minimax-m2.7 | 1.00x | 0.10 USD/M tokens | 0.10 USD/M tokens | Not listed |
| cc-minimax-m2.5-highspeed | 1.00x | 0.10 USD/M tokens | 0.10 USD/M tokens | Not listed |
| cc-minimax-m2.5 | 1.00x | 0.10 USD/M tokens | 0.10 USD/M tokens | Not listed |
| cc-minimax-m2.1 | 1.00x | 0.10 USD/M tokens | 0.10 USD/M tokens | Not listed |
| text-embedding-ada-002 | 0.75x | 0.10 USD/M tokens | 0.10 USD/M tokens | Not listed |
| cc-minimax-m2 | 1.00x | 0.10 USD/M tokens | 0.10 USD/M tokens | Not listed |
| text-embedding-v1 | 0.05x | 0.10 USD/M tokens | 0.10 USD/M tokens | Not listed |
| doubao-embedding-large-text-240915 | 7.00x | 0.10 USD/M tokens | 0.10 USD/M tokens | Not listed |
| qwen-flash-2025-07-28 | 1.00x | 0.02 USD/M tokens | 0.20 USD/M tokens | 0.02 USD/M tokens |
| nvidia-nemotron-nano-9b-v2 | 1.00x | 0.04 USD/M tokens | 0.18 USD/M tokens | Not listed |
| qwen3-reranker-8b | 1.00x | 0.11 USD/M tokens | 0.11 USD/M tokens | Not listed |
| qwen3-reranker-4b | 1.00x | 0.11 USD/M tokens | 0.11 USD/M tokens | Not listed |
| qwen3-reranker-0.6b | 1.00x | 0.11 USD/M tokens | 0.11 USD/M tokens | Not listed |
| qwen-flash | 0.08x | 0.02 USD/M tokens | 0.20 USD/M tokens | 0.02 USD/M tokens |
| gte-rerank-v2 | 0.14x | 0.11 USD/M tokens | 0.11 USD/M tokens | Not listed |
| qwen3-vl-flash-2026-01-22 | 0.00x | 0.02 USD/M tokens | 0.21 USD/M tokens | 0.02 USD/M tokens |
| qwen3-vl-flash | 0.03x | 0.02 USD/M tokens | 0.21 USD/M tokens | Free USD/M tokens |
| AiHubmix-Phi-4-mini-reasoning | 1.00x | 0.12 USD/M tokens | 0.12 USD/M tokens | Not listed |
| coding-xiaomi-mimo-v2.5 | 1.00x | 0.08 USD/M tokens | 0.16 USD/M tokens | Free USD/M tokens |
| text-embedding-3-large | 0.98x | 0.13 USD/M tokens | 0.13 USD/M tokens | Not listed |
| coding-glm-5.3 | 1.00x | 0.06 USD/M tokens | 0.22 USD/M tokens | 0.02 USD/M tokens |
| coding-glm-5.2 | 1.00x | 0.06 USD/M tokens | 0.22 USD/M tokens | Not listed |
| coding-glm-5.1 | 1.00x | 0.06 USD/M tokens | 0.22 USD/M tokens | Not listed |
| cc-glm-5.1 | 1.00x | 0.06 USD/M tokens | 0.22 USD/M tokens | Not listed |
| coding-glm-5-turbo | 1.00x | 0.06 USD/M tokens | 0.22 USD/M tokens | Not listed |
| coding-glm-5 | 1.00x | 0.06 USD/M tokens | 0.22 USD/M tokens | Not listed |
| cc-glm-5-turbo | 1.00x | 0.06 USD/M tokens | 0.22 USD/M tokens | Not listed |
| cc-glm-5 | 1.00x | 0.06 USD/M tokens | 0.22 USD/M tokens | Not listed |
| coding-glm-4.7 | 1.00x | 0.06 USD/M tokens | 0.22 USD/M tokens | 0.01 USD/M tokens |
| cc-glm-4.7 | 1.00x | 0.06 USD/M tokens | 0.22 USD/M tokens | Not listed |
| coding-glm-4.6 | 1.00x | 0.06 USD/M tokens | 0.22 USD/M tokens | 0.01 USD/M tokens |
| cc-glm-4.6 | 1.00x | 0.06 USD/M tokens | 0.22 USD/M tokens | Not listed |
| gme-qwen2-vl-2b-instruct | 1.00x | 0.14 USD/M tokens | 0.14 USD/M tokens | Not listed |
| gemini-embedding-001 | 0.01x | 0.15 USD/M tokens | 0.15 USD/M tokens | Not listed |
| qianfan-ocr | 1.00x | 0.06 USD/M tokens | 0.25 USD/M tokens | Not listed |
| qwen3.5-flash | 0.00x | 0.03 USD/M tokens | 0.28 USD/M tokens | Free USD/M tokens |
| doubao-seed-2-0-mini-260428 | 0.15x | 0.03 USD/M tokens | 0.28 USD/M tokens | 0.01 USD/M tokens |
| deepseek-ai/deepseek-llm-67b-chat | 1.00x | 0.16 USD/M tokens | 0.16 USD/M tokens | Not listed |
| deepseek-ai/deepseek-vl2 | 0.05x | 0.16 USD/M tokens | 0.16 USD/M tokens | Not listed |
| Qwen/QwQ-32B-Preview | 1.00x | 0.16 USD/M tokens | 0.16 USD/M tokens | Not listed |
| Qwen/Qwen2.5-Coder-32B-Instruct | 0.03x | 0.16 USD/M tokens | 0.16 USD/M tokens | Not listed |
| Doubao Seed 2.0 Mini | 0.53x | 0.03 USD/M tokens | 0.30 USD/M tokens | 0.01 USD/M tokens |
| deepinfra-nvidia-nemotron-3-nano-30b-a3b2 | 1.00x | 0.07 USD/M tokens | 0.26 USD/M tokens | Not listed |
| nvidia-nemotron-3-nano-30b-a3b | 1.00x | 0.07 USD/M tokens | 0.26 USD/M tokens | Not listed |
| ernie-4.5 | 1.00x | 0.07 USD/M tokens | 0.27 USD/M tokens | Not listed |
| inclusionAI/Ling-mini-2.0 | 0.14x | 0.07 USD/M tokens | 0.27 USD/M tokens | Not listed |