Context Length

Free Tier64k tokens
Paid Tiers128k tokens

Speed

~2000
tokens/sec

Input / Output

Input Formats JSON, plain text
Output FormatsJSON, plain text, structured

Pricing

Input
$2.00 / M tokens
Output
$2.00 / M tokens
Exploration pricing shown above is per million tokens. For volume discounts and enterprise features, see our pricing page.

Model Notes

Model ID: qwen-3-coder-480b
This model supports only non-thinking mode. It will not generate <think></think> tags.
Tool calling with strict: true (constrained decoding) is not yet supported - standard tool calling remains fully functional.
We recommend setting temperature=0.7 and top_p=0.8.

Rate Limits

TierRequests/minInput Tokens/minOutput Tokens/minDaily Tokens
Free10150k8k/request1M

Endpoints

Chat Completions
Completions

Features

Streaming
Structured Outputs
Tool Calling
Multi-Turn Tool Calling

Need Higher Limits?

Reach out for custom pricing with our Enterprise tier for higher rate limits and dedicated support.Contact Sales