Qwen3 Coder Flash

Fast & Economy

qwen3-coder-flash · Qwen · text

Back to Models Back to Docs

Platform

Qwen

Visit Official Site

API Pricing

Input / 1M

$0.75/M

Output / 1M

$3.73/M

Cache Read / 1M

$0.0075/M

Overview

Alibaba Cloud's ultra-fast Tongyi Qianwen coding model Qwen3 Coder Flash offers a 256K context window with ultra-low latency and ultra-low pricing. It supports FIM completion and Function Calling, making it ideal for high-concurrency code completion and CI/CD code review.

Capabilities

256K context; FIM completion; Function Calling; JSON mode; code generation; high-speed responses; OpenAI-compatible interface.

Use Cases

Code completion; code transpilation; unit test generation; code review; IDE integration; CI/CD automation.

Limitations

Does not generate images; weaker reasoning than Coder Plus; max_tokens capped at 8K.

Examples

Claude Code

Anthropic official CLI coding agent. Multi-file edits, tool use, long-context reasoning.

Terminal

export ANTHROPIC_AUTH_TOKEN="YOUR_API_KEY"
export ANTHROPIC_BASE_URL="https://api.robovai.com"
export ANTHROPIC_MODEL="qwen3-coder-flash"
claude

Context Window

998K ctx

Thinking Mode

Not supported

Overview

Qwen3 Coder Flash, with a 998K context window and 64K output. An ultra-fast coding model well suited for high-concurrency code completion and generation.