Models/qwen3-coder

qwen3-coderActive · Cloud

OpenRouter · Released Jul 2025 · Apache-2.0

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...

Context
262K
Max output
262K
Input
$0.22
Output
$0.95
Cached in
-
Latency
-

Capabilities

Core
Streaming
Function calling
JSON mode
Structured outputs
Multimodal
Vision
Image input
Audio
Image generation
Video
Advanced
Reasoning
Tool calling
MCP
Prompt caching
Batch API
Embeddings

Details

ProviderOpenRouter
ReleasedJul 2025
LicenseApache-2.0
InputText
OutputText
Throughput-
Availability99.8%

Related models