Qwen/operational

Qwen: 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...

Input / output per 1M

$0.30/$1.00

Get an API key

codefunction-callingreasoningopen weights

262K

Context window

tokens

66K

Max output

tokens per reply

85ms

Time to first token

p50, EU region

$1.00

Output price

per 1M tokens

Fit

Where this model earns its place

code

Code generation and refactoring across large repositories, including multi-file changes.

function calling

Tool use and structured output — dependable JSON for agent loops, RAG pipelines, and workflow automation.

reasoning

Multi-step reasoning — planning, quantitative analysis, and problems that need deliberation rather than recall.

Data handling

Requests are processed in the EU. Prompts are not used for training, and logs follow the retention period in your contract — zero-retention is available on request.

Specifications

Model

Model ID: qwen/qwen3-coder
Provider: Qwen
Context length: 262K
Max output: 66K
Modality: text
Licence: Open Weight

Commercial

Input: $0.30
Output: $1.00
Cached input: $0.10
Deployment: serverless
Availability: operational
Last updated: 2026-10-26

Cost

What a month actually costs

Workload	Input tokens	Output tokens	Monthly cost
Prototype	1.0M	250K	$0.55
Production	50.0M	12.0M	$27.00
At scale	500.0M	120.0M	$270.00

Illustrative volumes at list price, excluding cached-input discounts and any committed-use agreement. Your invoice shows the same rates, itemised per key.

Cheaper by caching

Repeated prompts — system instructions, retrieved context, few-shot examples — are billed at the cached-input rate where the model supports it. On long system prompts this is typically the largest single line-item saving.

API

Same SDK, different base URL

cURL

curl https://api.itciphtech.com/v1/chat/completions \
  -H "Authorization: Bearer $CIPHER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3-coder",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

TypeScript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.itciphtech.com/v1",
  apiKey: process.env.CIPHER_API_KEY,
});

const res = await client.chat.completions.create({
  model: "qwen/qwen3-coder",
  messages: [{ role: "user", content: "Hello!" }],
});

Alternatives

Close substitutes in the catalog

Qwen2.5 72B Instruct

Qwen

Context

33K

In / out

$0.36 / $0.40

TTFB

104ms

View

Qwen2.5 Coder 32B Instruct

Qwen

Context

33K

In / out

$0.66 / $1.00

TTFB

60ms

View

Qwen: Qwen2.5 VL 72B Instruct

Qwen

Context

128K

In / out

$0.80 / $1.00

TTFB

106ms

View

Qwen: Qwen3 235B A22B Instruct 2507

Qwen

Context

262K

In / out

$0.09 / $0.55

TTFB

74ms

View

Need this model on dedicated hardware?

Run it single-tenant, inside your own network boundary, with the operations handled by us.

Private hosting