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 |
|---|---|---|---|---|
| Llama 3.2 3B | Meta AI | $0.04 | $0.08 | $0.05 |
| Llama 3.1 8B Instruct | Meta AI | $0.03 | $0.05 | $0.04 |
| Qwen 3 8B | Alibaba (Qwen) | $0.04 | $0.14 | $0.07 |
| CodeLlama 7B | Meta AI | $0.06 | $0.12 | $0.08 |
| DeepSeek Coder 6.7B | DeepSeek | $0.06 | $0.12 | $0.08 |
| DeepSeek R1 7B Qwen | DeepSeek | $0.08 | $0.15 | $0.1 |
| DeepSeek R1 8B | DeepSeek | $0.1 | $0.2 | $0.13 |
| Dolphin3 8B | Meta AI | $0.08 | $0.15 | $0.1 |
| Gemma3 4B | Google DeepMind | $0.03 | $0.08 | $0.04 |
| Llava 7B | Meta AI | $0.1 | $0.2 | $0.13 |
| Mistral 7B V0.3 | Mistral AI | $0.1 | $0.15 | $0.11 |
| Openthinker 7B | Meta AI | $0.08 | $0.15 | $0.1 |
| Qwen2.5 Coder 7B | Alibaba (Qwen) | $0.06 | $0.12 | $0.08 |
| Qwen3 VL 8B | Alibaba (Qwen) | $0.15 | $0.55 | $0.25 |
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.