What this provider sells and at what price. A price belongs to the offer, not the model: at another provider the same model may cost several times more or less.
| Model | Developer | Input, $/1M | Output, $/1M | Blended, $/1M |
|---|---|---|---|---|
| Qwen3.6 27B | Alibaba (Qwen) | $0.47 | $3.19 | $1.15 |
| Qwen3.5 9B | Alibaba (Qwen) | $0.12 | $0.18 | $0.14 |
| Qwen3.5 397B-A17B | Alibaba (Qwen) | $0.71 | $4.25 | $1.6 |
| Qwen3 32B and another 1 | Alibaba (Qwen) | $0.08 | $0.23 | $0.12 |
| Mixtral 8x7B | Mistral AI | $0.63 | $0.63 | $0.63 |
| GPT OSS 120B and another 1 | OpenAI | $0.08 | $0.4 | $0.16 |
| GPT OSS 20B and another 1 | OpenAI | $0.04 | $0.15 | $0.07 |
| Qwen3-Coder 30B-A3B Instruct | Alibaba (Qwen) | $0.07 | $0.26 | $0.12 |
| Mistral Small 3.2 and another 1 | Mistral AI | $0.09 | $0.28 | $0.14 |
| Mistral 7B Instruct V0.3 and another 1 | Mistral AI | $0.1 | $0.1 | $0.1 |
| DeepSeek R1 Distill Llama 70B | DeepSeek | $0.67 | $0.67 | $0.67 |
| Qwen2.5 VL 72B Instruct and another 1 | Alibaba (Qwen) | $0.91 | $0.91 | $0.91 |
| Llama 3.3 70B Instruct and another 1 | Meta AI | $0.67 | $0.67 | $0.67 |
| Qwen2.5 Coder 32b Instruct | Alibaba (Qwen) | $0.87 | $0.87 | $0.87 |
| Llama 3.1 70B | Meta AI | $0.67 | $0.67 | $0.67 |
| Llama 3.1 8B | Meta AI | $0.1 | $0.1 | $0.1 |
| Mistral Nemo and another 1 | Mistral AI | $0.13 | $0.13 | $0.13 |
| Mamba Codestral 7B V0.1 | Mistral AI | $0.19 | $0.19 | $0.19 |
These are this provider’s prices, not the market’s best: the same model may cost differently at another provider. The blended price uses a three-input-tokens-to-one-output scheme — the way to compare models whose output costs several times more than input. Only the base per-token rate counts, without batch or discounted tiers; input and output come from one price list, not two minimums from different ones.