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 |
|---|---|---|---|---|
| GLM 5.2 | Zhipu AI / Z.ai | $1.8 | $5.5 | $2.73 |
| Mistral Medium 3.5 and another 1 | Mistral AI | $1.5 | $7.5 | $3 |
| Qwen3.6 35B-A3B and another 1 | Alibaba (Qwen) | $0.25 | $1.5 | $0.56 |
| Gemma 4 26B A4B IT and another 1 | Google DeepMind | $0.25 | $0.5 | $0.31 |
| Qwen3.5 397B-A17B and another 1 | Alibaba (Qwen) | $0.6 | $3.6 | $1.35 |
| Devstral 2 | Mistral AI | $0.4 | $2 | $0.8 |
| GPT OSS 120B and another 1 | OpenAI | $0.15 | $0.6 | $0.26 |
| Qwen3-Coder 30B-A3B Instruct and another 1 | Alibaba (Qwen) | $0.2 | $0.8 | $0.35 |
| Qwen3 235B A22B Instruct 2507 and another 1 | Alibaba (Qwen) | $0.75 | $2.25 | $1.13 |
| Voxtral Small 24B | Mistral AI | $0.15 | $0.35 | $0.2 |
| Mistral Small 3.2 and another 1 | Mistral AI | $0.15 | $0.35 | $0.2 |
| Gemma 3 27B | Google DeepMind | $0.25 | $0.5 | $0.31 |
| Llama 3.3 70B Instruct and another 1 | Meta AI | $0.9 | $0.9 | $0.9 |
| Pixtral 12B and another 1 | Mistral AI | $0.2 | $0.2 | $0.2 |
| Holo2 30B A3B | H Company | $0.3 | $0.7 | $0.4 |
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.