Qwen3-Coder-480B-A35B-Instruct is a large Mixture-of-Experts code model optimized for agentic coding tasks, tool use, and long-context understanding. The model performs well on benchmarks involving code generation, tool calls, and browser-based tasks, with results comparable to Claude Sonnet.
Qwen3 Coder 480B A35B Instruct is available via Fireworks' serverless API, where you pay per token. There are several ways to call the Fireworks API, including Fireworks' Python client, the REST API, or OpenAI's Python client.
Learn MoreOn-demand deployments allow you to use Qwen3 Coder 480B A35B Instruct on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.
Learn MoreQwen
256k
Available
$0.45 / $1.8
