Enterprise DNAEnterprise DNA
Qwen logo

Models · Best coding

Qwen3 Coder 480B A35B

by Qwen

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team.

Visit Qwen ↗

Our verdict

Not reviewed yet

We have not reviewed Qwen3 Coder 480B A35B yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About Qwen3 Coder 480B A35B

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team.

Best for

Dedicated coding agents on a budget

Use cases

  • code completion agents
  • PR drafts
  • test generation

Enterprise DNA angle

Omni can run Qwen Coder as the coding specialist beside a generalist planner model.

Notes

Qwen3 Coder 480B A35B is listed in the EDNA Models directory from the OpenRouter catalogue.

Pros

  • Coding-specialist Qwen line at competitive cost
  • Strong open-weight-adjacent option via OpenRouter

Cons

  • Narrower generalist quality than frontier closed models
  • Endpoint quality can vary

Key facts

What we have checked

Input price
$0.300 per million tokens
Checked OpenRouter models API
Output price
$1.00 per million tokens
Checked OpenRouter models API
Price on deepinfra
$0.100 per million cached input tokens
Checked OpenRouter models API
Price on deepinfra
$0.300 per million input tokens
Checked OpenRouter models API
Price on deepinfra
$1.00 per million output tokens
Checked OpenRouter models API
Price on google-vertex
$0.220 per million input tokens
Checked OpenRouter models API
Price on google-vertex
$1.80 per million output tokens
Checked OpenRouter models API
Price on venice
$0.040 per million cached input tokens
Checked OpenRouter models API
Price on venice
$0.350 per million input tokens
Checked OpenRouter models API
Terminal bench
27.2% (for 31 July 2025)
Checked Epoch AI (CC BY 4.0)
Gso bench
4.9% (for 31 July 2025)
Checked Epoch AI (CC BY 4.0)
Weirdml
41.2% (for 31 July 2025)
Checked Epoch AI (CC BY 4.0)

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

API access

How to call it

Call via OpenRouter with model id `qwen/qwen3-coder`.

  • openrouter · qwen/qwen3-coder · Docs

OpenRouter id: qwen/qwen3-coder

Price

What Qwen3 Coder 480B A35B costs, over time

Input price

$0.300 to $0.300

US dollars per million input tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Output price

$1.00 to $1.00

US dollars per million output tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Prices by host

HostPriceOver timeChecked
deepinfraCached input$0.100 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraInput$0.300 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraOutput$1.00 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
google-vertexInput$0.220 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
google-vertexOutput$1.80 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
veniceCached input$0.040 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
veniceInput$0.350 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
veniceOutput$1.50 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much Qwen3 Coder 480B A35B is used

Tokens served a day

1.4B to 1.5B

tokens a day on OpenRouter. 19 Sept 2026 to 10 Nov 2026, 53 readings.

Source: OpenRouter model activity (748 of 748 series). Checked .

Scores

How Qwen3 Coder 480B A35B scores

Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.

ScoreValueSourceChecked
Artificial Analysis Intelligence Index11.9indexAs of 26 Oct 2026Artificial Analysis via OpenRouter
Design Arena rating (Elo)1,155EloAs of 10 Nov 2026Design Arena via OpenRouter
Gso bench (best-across-versions)4.9percentAs of 31 July 2025Epoch AI (CC BY 4.0)
Terminal bench (best-across-versions)27.2percentAs of 31 July 2025Epoch AI (CC BY 4.0)
Weirdml (best-across-versions)41.2percentAs of 31 July 2025Epoch AI (CC BY 4.0)

Sources

Where this comes from

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

  1. Price changed

    output per mtok: 1.8 to 1

    Source: OpenRouter models API

  2. Price changed

    input per mtok: 0.22 to 0.3

    Source: OpenRouter models API

USAGE / OPENROUTER

How much Qwen3 Coder 480B A35B is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
11.6B ▲7.9%
Requests, last 7 days
587K
Tool calls, last 7 days
319K
Average cost per request
23.5¢
Price per million tokens
$0.3 in · $1 out
02.5B5B19 Sept: 1.4B tokens, 92.9K requests20 Sept: 1.8B tokens, 92.8K requests21 Sept: 2B tokens, 82.8K requests22 Sept: 2.4B tokens, 100K requests23 Sept: 2.5B tokens, 122K requests24 Sept: 1.7B tokens, 117K requests25 Sept: 2.7B tokens, 189K requests26 Sept: 1.7B tokens, 213K requests27 Sept: 1.6B tokens, 80.2K requests28 Sept: 1.6B tokens, 107K requests29 Sept: 1.4B tokens, 123K requests30 Sept: 1.4B tokens, 81.5K requests1 Oct: 2.7B tokens, 155K requests2 Oct: 2.4B tokens, 114K requests3 Oct: 1.9B tokens, 88.8K requests4 Oct: 1.6B tokens, 68.6K requests5 Oct: 1.5B tokens, 70.5K requests6 Oct: 1.7B tokens, 86.4K requests7 Oct: 2.1B tokens, 124K requests8 Oct: 2.7B tokens, 97.2K requests9 Oct: 2.4B tokens, 115K requests10 Oct: 1.3B tokens, 99K requests11 Oct: 1.8B tokens, 118K requests12 Oct: 2.1B tokens, 108K requests13 Oct: 2.4B tokens, 116K requests14 Oct: 2.5B tokens, 93K requests15 Oct: 2.4B tokens, 117K requests16 Oct: 3.1B tokens, 88.8K requests17 Oct: 2.3B tokens, 74.4K requests18 Oct: 3.4B tokens, 184K requests19 Oct: 2.2B tokens, 101K requests20 Oct: 1.9B tokens, 79.4K requests21 Oct: 1.7B tokens, 91.1K requests22 Oct: 1.5B tokens, 57K requests23 Oct: 1.1B tokens, 55.5K requests24 Oct: 1.2B tokens, 42.3K requests25 Oct: 1.7B tokens, 48.7K requests26 Oct: 1.6B tokens, 89.6K requests27 Oct: 1.8B tokens, 86.6K requests28 Oct: 1.8B tokens, 77.6K requests29 Oct: 1.9B tokens, 67K requests30 Oct: 1.9B tokens, 71.1K requests31 Oct: 1.2B tokens, 52.8K requests1 Nov: 783M tokens, 42.3K requests2 Nov: 1.5B tokens, 57.2K requests3 Nov: 1.8B tokens, 88.5K requests4 Nov: 1.7B tokens, 88.4K requests5 Nov: 2.9B tokens, 108K requests6 Nov: 1.7B tokens, 107K requests7 Nov: 1.4B tokens, 79.3K requests8 Nov: 1B tokens, 80K requests9 Nov: 1.3B tokens, 58.4K requests10 Nov: 1.5B tokens, 65.4K requests19 Sept3 Oct17 Oct31 Oct10 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with Qwen3 Coder 480B A35B.

Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-11. Hosting routes and app features can differ.

DeveloperQwen
Exact model identifierqwen/qwen3-coder
Inputtext
Outputtext
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Not established
Availability
available
Price basis
token
Licence verification
Apache 2.0, open weights
Context length
262K tokens
Knowledge cutoff
30 Jun 2025
Developer release date
Not established
First seen in the catalogue
23 Jul 2025
Listed retirement date
Not established
Inspect the sources and their scope
catalogue source ↗

qwen/qwen3-coder: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-11-11
openrouter.ai ↗

Source for first seen, tool calling, context length, input, knowledge cutoff, output, structured output.

Checked 2026-11-11
Licence source ↗

Licence declared in the Qwen/Qwen3-Coder-480B-A35B-Instruct model repository on Hugging Face, which holds the weights files. Read the licence terms before use.

Checked 2026-11-07
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Build an appWorkflow & starter prompt ↗Run a reliable agentWorkflow & starter prompt ↗

What would it cost?

Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.

Working out the cost...

Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗

Check the source

Price date: 10 Nov 2026, from OpenRouter models API. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Design Arena: 1155 (2026-11-09) ↗
Compare this model with alternatives →
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →