# Qwen3 32B API prices

Qwen3 32B (qwen) — 131k context, 41k max output.
17 metered per-token offers from 19 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Deep Infra | $0.08 | $0.28 | — | 41k |
| Kilo Gateway | $0.08 | $0.28 | — | 41k |
| OpenRouter | $0.08 | $0.28 | — | 131k |
| OVHcloud AI Endpoints | $0.09 | $0.25 | — | 33k |
| Abacus | $0.09 | $0.29 | — | 131k |
| Cortecs | $0.089 | $0.312 | — | 32k |
| Jiekou.AI | $0.1 | $0.45 | — | 41k |
| NovitaAI | $0.1 | $0.45 | — | 41k |
| Amazon Bedrock | $0.15 | $0.6 | — | 33k |
| Merge Gateway | $0.15 | $0.6 | — | 131k |
| DigitalOcean | $0.25 | $0.55 | — | 33k |
| Helicone | $0.29 | $0.59 | — | 131k |
| Hugging Face | $0.29 | $0.59 | — | 131k |
| DevPass (LLM Gateway) | $0.36 | $0.87 | — | 41k |
| Alibaba (China) | $0.287 | $1.147 | — | 131k |
| Pioneer | $0.9 | $0.9 | $0.9 | 131k |
| Alibaba | $0.7 | $2.8 | — | 131k |

## Summary

- Cheapest input: $0.08 per 1M tokens (Deep Infra)
- Cheapest output: $0.25 per 1M tokens (OVHcloud AI Endpoints)
- First-party: $2.8 per 1M output tokens (Alibaba)
- Free offers: iFlow
- Subscription plans (not per-token): none
- Released: 2025-04
- Inputs: text

HTML page: https://llmprice.gitlab.io/models/qwen3-32b/
Full dataset: https://llmprice.gitlab.io/data/catalog.json