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 |
|---|---|---|---|---|
| Hermes 3 70B | Nous Research | $0.12 | $0.3 | $0.17 |
| DeepSeek Reasoner | DeepSeek | $0.4 | $0.4 | $0.4 |
| Kimi K2 Instruct | Moonshot AI (Kimi) | $2 | $2 | $2 |
| DeepSeek R1 0528 | DeepSeek | $0.25 | $0.25 | $0.25 |
| Qwen 3 235b A22B | Alibaba (Qwen) | $2 | $2 | $2 |
| Qwen: QwQ 32B | Alibaba (Qwen) | $0.2 | $0.2 | $0.2 |
| DeepSeek Chat 0324 | DeepSeek | $0.4 | $0.4 | $0.4 |
| DeepSeek V3 | DeepSeek | $0.2 | $0.2 | $0.2 |
| Llama 3.3 70B Instruct | Meta AI | $0.12 | $0.3 | $0.17 |
| Qwen2.5 Coder 32b Instruct | Alibaba (Qwen) | $0.12 | $0.3 | $0.17 |
| Llama 3.2 3B Instruct | Meta AI | $0.12 | $0.3 | $0.17 |
| Qwen2.5 72B Instruct | Alibaba (Qwen) | $0.12 | $0.3 | $0.17 |
| Llama 3.1 405B Instruct | Meta AI | $0.12 | $0.3 | $0.17 |
| Llama 3.1 70B | Meta AI | $0.12 | $0.3 | $0.17 |
| Llama 3.1 8B | Meta AI | $0.12 | $0.3 | $0.17 |
| Llama 3 70B Instruct | Meta AI | $0.12 | $0.3 | $0.17 |
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.