Qwen: Qwen3 Coder 480B A35B

Name: Qwen: Qwen3 Coder 480B A35B
Author: OpenRouter

code480B / 35B

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

Context

262K

Max output

66K

Input price

$0.3/1M tokens

Output price

$1/1M tokens

Capabilities

Show unsupported (5)

Reasoning & Interaction

Tool Calling

Output Control

Structured Output

JSON Mode

Details

Model IDqwen/qwen3-coder

ProviderOpenRouter

CreatorQwen

Familyqwen3

License—

Status—

Typecode

Input modalitiestext

Output modalitiestext

Open weight—

Parameters480B / 35B

Architecture—

Context window262K tokens

Max input—

Max output66K tokens

Reasoning tokens—

Knowledge cutoff—

Release date2025-07-23

Sourceofficial

Tools

Function Callingfunction_calling

Call external functions and APIs

Pricing

Input

$0.3

Output

Cache write

—

Cache read

$0.1

Batch in

—

Batch out

—

Family Comparison: qwen3

Model	Caps	Perf	Speed	Context	Max out	Pricing
Qwen: Qwen3 4B (free)	RTJJM	—	—	41K	—	—
Qwen: Qwen3 Coder 480B A35B (free)	T	—	—	1.0M	262K	—
Qwen: Qwen3 Next 80B A3B Instruct (free)	TJJM	—	—	262K	—	—
Qwen: Qwen3 Coder 30B A3B Instruct	RTJJMSBF	—	—	262K	236K	$0.07$0.28
Qwen: Qwen3 32B	RTJJMSBF	—	—	131K	16K	$0.08$0.28
Qwen: Qwen3 235B A22B Instruct 2507	RTJJMSBF	—	—	262K	16K	$0.09$0.55
Qwen: Qwen3 Next 80B A3B Instruct	RTJJMSBF	—	—	262K	16K	$0.09$1.1
Qwen: Qwen3 30B A3B Instruct 2507	RTJJMSBF	—	—	262K	236K	$0.1$0.3
Qwen: Qwen3 VL 32B Instruct	RTJJMSF	—	—	131K	33K	$0.1$0.42
Qwen: Qwen3 8B	RTJJMSBF	—	—	131K	8K	$0.12$0.46
Qwen: Qwen3 14B	RTJJMSBF	—	—	41K	16K	$0.12$0.24
Qwen: Qwen3 30B A3B	RTJJMSBF	—	—	41K	16K	$0.12$0.5
Qwen: Qwen3 Coder Next	RTJJMSBF	—	—	262K	236K	$0.12$0.8
Qwen: Qwen3 Next 80B A3B Thinking	RTJJMSBF	—	—	262K	236K	$0.15$1.2
Qwen: Qwen3 VL 30B A3B Instruct	RTJJMSF	—	—	262K	16K	$0.15$0.6
Qwen: Qwen3 VL 8B Thinking	RTJJMSF	—	—	131K	33K	$0.18$2.1
Qwen: Qwen3 Coder Flash	RTJJMSBF	—	—	1M	66K	$0.2$0.98
Qwen: Qwen3 30B A3B Thinking 2507	RTJJMSBF	—	—	82K	33K	$0.2$2.4
Qwen: Qwen3 VL 235B A22B Instruct	RTJJMSF	—	—	262K	33K	$0.21$1.9
Qwen: Qwen3 VL 8B Instruct	RTJJMSF	—	—	262K	236K	$0.25$0.75
Qwen: Qwen3 VL 30B A3B Thinking	RTJJMSF	—	—	262K	236K	$0.29$1
Qwen: Qwen3 Coder 480B A35B	TJJM	—	—	262K	66K	$0.3$1
Qwen: Qwen3 VL 235B A22B Thinking	RTJJMSF	—	—	131K	33K	$0.4$4
Qwen: Qwen3 235B A22B Thinking 2507	RTJJMSBF	—	—	128K	16K	$0.45$3.5
Qwen: Qwen3 Coder Plus	RTJJMSBF	—	—	1M	66K	$0.65$3.25
Qwen: Qwen3 Max Thinking	RTJJM	—	—	262K	66K	$0.78$3.9
Qwen: Qwen3 Max	RTJJMSBF	—	—	262K	66K	$0.78$3.9

API

GET/v1/models/openrouter/qwen/qwen3-coder

Qwen: Qwen3 Coder 480B A35B

qwen/qwen3-coder

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

Changes · 11 entries

qwen/qwen3-coderupdateca7a400Nov 2, 2026, 03:02 AM

pricinginput$0.22→$0.3output$1.8→$1cached input$0.022→$0.1

qwen/qwen3-coderupdate97fe10eJul 25, 2026, 09:55 AM

pricinginput$0.38→$0.3output$1.55→$1

qwen/qwen3-coderupdatebf78dcfJul 25, 2026, 05:49 AM

context_window1048576→262144

pricinginput$0.3→$0.38output$1→$1.55

qwen/qwen3-coderupdate20c73acJul 17, 2026, 02:34 AM

pricinginput$0.22→$0.3output$1.8→$1cached input$0.022→$0.1

qwen/qwen3-coderupdate73d11c6May 18, 2026, 03:39 AM

context_window262144→1048576

qwen/qwen3-coderupdateda3af4aApr 26, 2026, 07:37 PM

pricingoutput$1→$1.8

qwen/qwen3-coderupdatec8065d6Apr 25, 2026, 10:39 AM

max_output_tokens65536

qwen/qwen3-coderupdate1cd659eMar 24, 2026, 04:19 AM

capabilitiesjson modeyes

qwen/qwen3-coderupdate2b100acMar 23, 2026, 05:30 AM

parameters480

active_parameters35

release_date2025-07-23

taglineQwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (M...

tools["function_calling"]

qwen/qwen3-coderupdate7a4f1f6Mar 22, 2026, 05:43 AM

model_typecode

qwen/qwen3-codercreate7f5c66fMar 21, 2026, 05:16 AM