Skip to content
Alibaba Qwen

Qwen3 Coder

qwen/qwen3-coder
Open weightsCoding

Agent-grade open coding model, repository-scale context and dependable tool loops for autonomous engineering.

Model overview

Context window

256K

tokens

Input price

—

quoted on request

Output price

—

quoted on request

Weekly volume

—

tokens / week

Open weights

Yes

self-hostable

Capabilities

4

of 11 tags

Description

Qwen3 Coder is a coding model from Alibaba Qwen. Webparam does not stock this model yet and can source it on request — tell us what you need it for and we will come back with availability and a price. Alibaba Qwen’s stated focus is the broadest open model family in the world. Its mean it can also be self-hosted under its licence.

Capabilities

Tool calling
Calls functions you define and returns their arguments as structured data, the basis of agents.
JSON mode
Constrains the response to valid JSON matching a schema you supply.
Streaming
Emits tokens as they are generated, so answers appear progressively rather than all at once.
Open weights
The parameters are published, so the model can be inspected, fine-tuned and self-hosted under its licence.

Strengths & weaknesses

Strengths

  • Agentic coding tuned, not adapted
  • 256K context fits large repos
  • Open weights

Weaknesses

  • General prose is serviceable, not strong
  • Higher output price than Coder V2

Pricing

Pricing for Qwen3 Coder, per 1M tokens
RatePriceUnit
Input— quoted on request—
Output— quoted on request—

This model is not provisioned yet; the rate is quoted on request.

Context window

256Ktokens

covers prompt and response together, so a long input leaves less room for the answer.

256K tokens against a peer range of 128K to 1M, median 256K. Compared across 4 coding models.

Supported features

Feature support for Qwen3 Coder
FeatureSupport
Tool callingSupported
JSON modeSupported
StreamingSupported
Vision inputNot supported
Audio inputNot supported
Long contextNot supported
Open weightsSupported
ReasoningNot supported
Fine-tunableNot supported
BatchNot supported
CachingNot supported

Example use cases

  • Coding agents

  • Repo-wide refactors

  • PR review automation

Related models

Comparison

Compare against anything →
Qwen3 Coder compared with DeepSeek Coder V2 and Claude Sonnet 4.5
AttributeQwen3 CoderDeepSeek Coder V2Claude Sonnet 4.5
Context window256K128K1M
Input priceR0.00R0.00R0.00
Output price— not charged— not charged— not charged
Tool callingSupportedSupportedSupported
JSON modeSupportedSupportedSupported
Vision inputNot supportedNot supportedSupported
Open weightsSupportedSupportedNot supported
Prompt cachingNot supportedNot supportedSupported

Best value in each row is highlighted. Blank cells are facts the supplier does not publish, not zeroes.

Provider information

View Alibaba Qwen →
Alibaba Qwen8 models

Alibaba Qwen · 通义千问 · Hangzhou, China · est. 2023 (Model lab; parent Alibaba founded 1999)

Alibaba's Qwen family spans every size class from edge models to frontier MoE systems, most released with open weights. Its breadth (chat, coding, vision, embeddings) and permissive licensing made it the default base model for much of the global open-source ecosystem.

Recent releases

    Documentation

    Frequently asked questions

    Input is billed at R0.00 per 1M tokens, and there is no separate output charge. Every figure on this page is an illustrative placeholder.