Is Qwen3 Coder 480B A35B available on FastMetal?

Not at the moment. Qwen3 VL 235B A22B Instruct, from the same lab, is available on the FastMetal API today.

What is the context window of Qwen3 Coder 480B A35B?

262,144 tokens, shared between the prompt and the response.

How does Qwen3 Coder 480B A35B rank?

#153 on the public arena's Japanese board (ELO 1,327). Ranks move as the leaderboard is updated.

Back to Models

Qwen

qwen/qwen3-coder

Not Available

Qwen3 Coder 480B A35B

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. The model features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts). Pricing for the Alibaba endpoints varies by context length. Once a request is greater than 128k input tokens, the higher pricing is used.

7/23/2025

262,144 tokens

#132 Code (Overall)

Specifications

Modalities

Input

text

Output

text

Supported Parameters

frequency_penalty

logit_bias

max_tokens

min_p

presence_penalty

repetition_penalty

response_format

seed

stop

structured_outputs

temperature

tool_choice

tools

top_k

top_p

Data policy

Prompt retention: Unknown — we could not confirm
Training: Unknown — not declared

"Unknown" does not mean "safe". It means we could not confirm it.

Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.

Frequently asked questions

Is Qwen3 Coder 480B A35B available on FastMetal?: Not at the moment. Qwen3 VL 235B A22B Instruct, from the same lab, is available on the FastMetal API today.
What is the context window of Qwen3 Coder 480B A35B?: 262,144 tokens, shared between the prompt and the response.
How does Qwen3 Coder 480B A35B rank?: #153 on the public arena's Japanese board (ELO 1,327). Ranks move as the leaderboard is updated.

Leaderboard

Text

spanishELO: 1,387

#167

russianELO: 1,392

#162

CodingELO: 1,457

#150

MathELO: 1,376

#195

Creative WritingELO: 1,362

#168

Instruction FollowingELO: 1,383

#172

Hard PromptsELO: 1,414

#175

Multi-TurnELO: 1,397

#170

OverallELO: 1,388

#182

JapaneseELO: 1,327

#153

ChineseELO: 1,405

#182

KoreanELO: 1,326

#166

EnglishELO: 1,396

#188

frenchELO: 1,430

#136

germanELO: 1,353

#179

Code

OverallELO: 1,275

#132

Rankings: LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, snapshot 2026-10-22; category names mapped and ratings rounded by FastMetal.

Models you can use on FastMetal

Qwen3 VL 235B A22B Instruct