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 |
|---|---|---|---|---|
| Qwen3 32B and another 1 | Alibaba (Qwen) | $0.29 | $0.59 | $0.37 |
| GPT OSS Safeguard 20B and another 1 | OpenAI | $0.08 | $0.3 | $0.13 |
| Kimi K2 0905 deprecated | Moonshot AI (Kimi) | $1 | $3 | $1.5 |
| GPT OSS 120B and another 1 | OpenAI | $0.15 | $0.6 | $0.26 |
| GPT OSS 20B and another 1 | OpenAI | $0.08 | $0.3 | $0.13 |
| Llama 4 Scout 17B 16E Instruct and another 1 | Meta AI | $0.11 | $0.34 | $0.17 |
| Llama Guard 4 12B | Meta AI | $0.2 | $0.2 | $0.2 |
| Llama 4 Maverick 17b 128e Instruct | Meta AI | $0.2 | $0.6 | $0.3 |
| Meta Llama 3.3 70B Versatile and another 1 | Meta AI | $0.59 | $0.79 | $0.64 |
| Meta Llama Prompt Guard 2 22M | Meta AI | $0.03 | $0.03 | $0.03 |
| Meta Llama Prompt Guard 2 86M | Meta AI | $0.04 | $0.04 | $0.04 |
| Meta Llama 3.1 8B Instant and another 1 | Meta AI | $0.05 | $0.08 | $0.06 |
| Gemma 7B IT | Google DeepMind | $0.05 | $0.08 | $0.06 |
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.