# Qwen2.5 7B Instruct API prices

Qwen2.5 7B Instruct (qwen) — 131k context, 32k max output.
4 metered per-token offers from 4 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| NovitaAI | $0.07 | $0.07 | — | 32k |
| Alibaba (China) | $0.072 | $0.144 | — | 131k |
| OpenRouter | $0.1 | $0.2 | — | 33k |
| Alibaba | $0.175 | $0.7 | — | 131k |

## Summary

- Cheapest input: $0.07 per 1M tokens (NovitaAI)
- Cheapest output: $0.07 per 1M tokens (NovitaAI)
- First-party: $0.7 per 1M output tokens (Alibaba)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2024-09
- Inputs: text

HTML page: https://llmprice.gitlab.io/models/qwen2-5-7b-instruct/
Full dataset: https://llmprice.gitlab.io/data/catalog.json