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 |
|---|---|---|---|---|
| Kimi K2 Thinking | Moonshot AI (Kimi) | $0.55 | $2.25 | $0.98 |
| GLM 4.6 | Zhipu AI / Z.ai | $0.4 | $1.75 | $0.74 |
| Magistral Small 2506 | Mistral AI | $0.5 | $1.5 | $0.75 |
| Kimi K2 0905 deprecated | Moonshot AI (Kimi) | $0.39 | $1.9 | $0.77 |
| GPT OSS 120B | OpenAI | $0.04 | $0.4 | $0.13 |
| GPT OSS 20B | OpenAI | $0.03 | $0.14 | $0.06 |
| Mistral Devstral Small 2505 | Mistral AI | $0.05 | $0.22 | $0.09 |
| Qwen3 235B A22B Thinking-2507 deprecated | Alibaba (Qwen) | $0.11 | $0.6 | $0.23 |
| DeepSeek R1 0528 | DeepSeek | $2 | $8.75 | $3.69 |
| Llama 4 Maverick 17b 128e Instruct | Meta AI | $0.15 | $0.6 | $0.26 |
| Qwen2.5 VL 32B Instruct | Alibaba (Qwen) | $0.05 | $0.22 | $0.09 |
| Qwen 3 Coder 480B | Alibaba (Qwen) | $0.22 | $0.95 | $0.4 |
| Llama 3.3 70B Instruct | Meta AI | $0.13 | $0.38 | $0.19 |
| Qwen3 Next 80B A3B Instruct | Alibaba (Qwen) | $0.1 | $0.8 | $0.28 |
| Mistral Large Instruct 2411 | Mistral AI | $2 | $6 | $3 |
| Llama 3.2 90B Vision Instruct | Meta AI | $0.35 | $0.4 | $0.36 |
| Mistral Nemo | Mistral AI | $0.02 | $0.04 | $0.03 |
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.