Qwen

Qwen3-Coder-480B-A35B

Qwen's largest open-weight coding MoE (480B total, 35B active), available across inference gateways for agentic coding.

ActiveReleased July 22, 2025Available from 3 providers
Tool callingCan invoke external tools and APIs (function calling) mid-response.Structured outputCan return JSON or schema-constrained responses instead of free text.ReasoningUses extended thinking / chain-of-thought for harder multi-step problems.Effort controlLets you dial thinking depth (low / medium / high) to trade cost for quality.Fine-tuningSupports training a custom variant on your own data (vendor fine-tune API or self-hosted open weights).

Source: Qwen (Alibaba Model Studio) pricing, Qwen models, Metadata verification, Field resolution verification

Price per 1M tokens
$2 in / $2 out
Context window262,144
Max output65,536
Input
  • Text
Output
  • Text
Priced across3 providers

Pricing

Every billing leg from the live catalog, in USD per 1M tokens.

Billing legRate
Input$2 / M
Output$2 / M

Cost calculator

Billing-grade math over the rate card above, including the thinking tokens most estimates miss.

Estimated monthly cost
$440
at current list prices
Fresh input$400
Output$40.00
Track this automatically →

Compare providers

The same model, priced across every platform that serves it. Lowest combined in/out rate is flagged.

PlatformRegionInput / MOutput / MBatchAccess
Together AI
-$2$2-Direct
AWS BedrockLowest
$0.45$1.8✓Direct
AWS Bedrock
-$0.54$2.18-Direct

Some hosts price by region. Shown rates match the selected region.

Price history

Has this model gotten cheaper or more expensive?

No changePriced at $2 / $2 per 1M since May 21, 2026.

More from Qwen

Other models from the same provider.

Stop estimating. Track it.

SuperPenguin meters every Qwen3-Coder-480B-A35B call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.

Get started free

Rates are generated from SuperPenguin's live pricing catalog.