# Qwen3 Coder 480B A35B Instruct API prices

Qwen3 Coder 480B A35B Instruct (qwen) — 262k context, 262k max output.
16 metered per-token offers from 17 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| submodel | $0.2 | $0.8 | — | 262k |
| Abacus | $0.29 | $1.2 | — | 262k |
| Jiekou.AI | $0.29 | $1.2 | — | 262k |
| LLM Gateway | $0.22 | $1.8 | $0.022 | 262k |
| Merge Gateway | $0.22 | $1.8 | — | 131k |
| DevPass (LLM Gateway) | $0.38 | $1.55 | — | 262k |
| LLM Gateway | $0.38 | $1.55 | — | 262k |
| NovitaAI | $0.38 | $1.55 | — | 262k |
| Amazon Bedrock | $0.45 | $1.8 | — | 131k |
| Charm Hyper | $0.445 | $2.145 | $0.2225 | 106k |
| 302.AI | $0.86 | $3.43 | — | 262k |
| Alibaba (China) | $0.861 | $3.441 | — | 262k |
| Hugging Face | $2 | $2 | — | 262k |
| Alibaba | $1.5 | $7.5 | — | 262k |
| Eden AI | $1.5 | $7.5 | — | 262k |
| Vercel AI Gateway | $1.5 | $7.5 | $0.3 | 262k |

## Summary

- Cheapest input: $0.2 per 1M tokens (submodel)
- Cheapest output: $0.8 per 1M tokens (submodel)
- First-party: $7.5 per 1M output tokens (Alibaba)
- Free offers: Nvidia
- Subscription plans (not per-token): none
- Released: 2025-04
- Inputs: text

HTML page: https://llmprice.gitlab.io/models/qwen3-coder-480b-a35b-instruct/
Full dataset: https://llmprice.gitlab.io/data/catalog.json