Qwen 3 Coder 480B Turbo

Turbo variant of Qwen3 Coder 480B, optimized for faster inference on code tasks.

Beta

Modalities

In / out price

$0.35 / $1.5

per 1M

Context

256K

Max output

66K

Released

Jan 27, 2026

Updated

Jul 17, 2026

Privacy

2 / 3

Private routing

Private tier

Prompt and response content is not retained after the request.
Request content is visible to the inference runtime while it is being processed.

Moderation

Not specified

No model-level moderation classification is recorded in this catalog.

Data retention

Zero retention

The provider reports that request content is discarded after inference.

Streaming

Tool calling

JSON/schema

Web search

Code optimized

Prompt caching

Anonrouter hosted

Routed through AnonRouter's gateway with metadata-only logging.

Provider direct

Requests egress directly to the provider runtime.

USD per 1M tokens from the Venice models API.

1 route

30d