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 |
|---|---|---|---|---|
| Gemma 4 31B | Google DeepMind | $0.38 | $1.15 | $0.57 |
| MiniMax M2.7 | MiniMax | $0.6 | $2.4 | $1.05 |
| Qwen3 32B | Alibaba (Qwen) | $0.4 | $0.8 | $0.5 |
| DeepSeek Reasoner | DeepSeek | $5 | $7 | $5.5 |
| DeepSeek V3.2 | DeepSeek | $3 | $4.5 | $3.38 |
| DeepSeek V3.1 | DeepSeek | $3 | $4.5 | $3.38 |
| GPT OSS 120B | OpenAI | $0.22 | $0.59 | $0.31 |
| Qwen: QwQ 32B | Alibaba (Qwen) | $0.5 | $1 | $0.63 |
| Llama 4 Scout 17B 16E Instruct | Meta AI | $0.4 | $0.7 | $0.48 |
| Llama 4 Maverick 17b 128e Instruct | Meta AI | $0.63 | $1.8 | $0.92 |
| DeepSeek Chat 0324 | DeepSeek | $3 | $4.5 | $3.38 |
| DeepSeek R1 Distill Llama 70B | DeepSeek | $0.7 | $1.4 | $0.88 |
| Llama Guard 3 8B | Meta AI | $0.3 | $0.3 | $0.3 |
| Llama 3.3 70B Instruct | Meta AI | $0.6 | $1.2 | $0.75 |
| Llama 3.2 1b Instruct | Meta AI | $0.04 | $0.08 | $0.05 |
| Llama 3.2 3B Instruct | Meta AI | $0.08 | $0.16 | $0.1 |
| Llama 3.1 405B Instruct | Meta AI | $5 | $10 | $6.25 |
| Llama 3.1 8B | Meta AI | $0.1 | $0.2 | $0.13 |
| Qwen2 Audio 7B Instruct deprecated | Alibaba (Qwen) | $0.5 | $100 | $25.38 |
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.