How much does Qwen3 Coder 480B A35B (free) cost via API?

It's free: $0 per 1M input tokens and $0 per 1M output tokens from the provider, and OpenKey's flat 3% fee on $0 still comes out to $0. There's no cost calculation to do here — both prompt and completion pricing are zero.

What is Qwen3 Coder 480B A35B's context window?

It's 1,048,576 tokens, larger than 90% of models in OpenKey's catalog. That's enough to hold entire codebases or long document sets in a single request, and the model can generate up to 262,000 completion tokens back.

Is Qwen3 Coder 480B A35B free to use?

Yes — this is the free variant, with provider pricing of $0 per 1M tokens for both input and output. It's one of 25 free models currently listed on OpenKey.

Does Qwen3 Coder 480B A35B support tool calling?

Yes, it supports both `tools` and `tool_choice` parameters, along with `frequency_penalty`, `presence_penalty`, `temperature`, `top_k`, and `top_p`. It does not take image or audio input — it's text-to-text only.

What is Qwen3 Coder 480B A35B's knowledge cutoff?

Its knowledge cutoff is June 30, 2025, and it was released July 23, 2025. That makes it one of the more recently trained models in the Qwen lineup on OpenKey.

Qwen3 Coder 480B A35B (free)

qwenqwen3-coder:free

Free

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...

Try in playground Hugging Face ↗

Modalities: text → text
In / out per 1M: Free / Free
Context: 1.0M tokens
Added: Jul 23, 2025

Max output: 262K tokens
Tokenizer: Qwen3
Knowledge cutoff: Jun 30, 2025

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokens	Provider	+ 3% fee	You pay
Input	Free	—	Free
Output	Free	—	Free

Providers

No provider breakdown is published for Qwen3 Coder 480B A35B (free) in the current catalog snapshot (Jul 28, 2026). Browse all providers

Benchmarks

Design Arena

Category	Elo	Win rate	Rank
Code models	1192	61.2%	#54
Data viz models	1126	54.9%	#74
Game dev models	1167	59%	#58
UI components models	1170	61.5%	#56
Websites models	1201	61.7%	#55

Head-to-head preference voting. How we filter and rank

Supported parameters

frequency_penalty
max_tokens
presence_penalty
stop
temperature
tool_choice
tools
top_k
top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model qwen/qwen3-coder:free.

curl Python TypeScript

curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer ***" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3-coder:free",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="qwen/qwen3-coder:free",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "qwen/qwen3-coder:free",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

About Qwen3 Coder 480B A35B (free)

Qwen3 Coder 480B A35B is a Mixture-of-Experts model from Alibaba's Qwen team, built for agentic coding: function calling, tool use, and reasoning across very long inputs. Its context window holds 1,048,576 tokens, larger than 90% of catalog models, and it can return up to 262,000 completion tokens in one response. Across Design Arena's code-related categories it lands elo scores between 1126 and 1201 with win rates from 54.9% to 61.7%, putting it in the mid-50s to low-70s rank band depending on category. It's text-in, text-out only.

This is one of 25 free models on OpenKey, priced at $0 per 1M input and output tokens, versus siblings like Qwen2.5 Coder 32B Instruct at $0.66/$1.00 per 1M or Qwen2.5 72B Instruct at $0.36/$0.40 per 1M. Its 1,048,576-token context window dwarfs Qwen3 14B and every other listed sibling, and it beats the 90th percentile of the whole catalog on context length. It also supports tool calling and tool choice, which none of the pricing alone tells you.

Questions

How much does Qwen3 Coder 480B A35B (free) cost via API?: It's free: $0 per 1M input tokens and $0 per 1M output tokens from the provider, and OpenKey's flat 3% fee on $0 still comes out to $0. There's no cost calculation to do here — both prompt and completion pricing are zero.
What is Qwen3 Coder 480B A35B's context window?: It's 1,048,576 tokens, larger than 90% of models in OpenKey's catalog. That's enough to hold entire codebases or long document sets in a single request, and the model can generate up to 262,000 completion tokens back.
Is Qwen3 Coder 480B A35B free to use?: Yes — this is the free variant, with provider pricing of $0 per 1M tokens for both input and output. It's one of 25 free models currently listed on OpenKey.
Does Qwen3 Coder 480B A35B support tool calling?: Yes, it supports both `tools` and `tool_choice` parameters, along with `frequency_penalty`, `presence_penalty`, `temperature`, `top_k`, and `top_p`. It does not take image or audio input — it's text-to-text only.
What is Qwen3 Coder 480B A35B's knowledge cutoff?: Its knowledge cutoff is June 30, 2025, and it was released July 23, 2025. That makes it one of the more recently trained models in the Qwen lineup on OpenKey.

More from Qwen

All Qwen models →

Qwen

Qwen3.7 Plus

Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...

ctx 1M in $0.330 out $1.32

Qwen

Qwen3.7 Max

Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...

ctx 1M in $1.29 out $3.86

Qwen

Qwen3.5 Plus 2026-04-20

Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...

ctx 1M in $0.309 out $1.85

Qwen

Qwen3.6 27B

Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...

ctx 262K in $0.294 out $2.47