Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. Optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. Features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts), and supports variable pricing based on context length.
Struck through is the lowest price elsewhere on the market.
$0.15
market price $0.30 market
$0.05
market price $0.10 market
$0.50
market price $1.00 market
How fast the model answers over every route we serve it from: throughput is tokens written per second, time to first token is how soon the answer starts, end-to-end latency is the whole request.
Share of requests served without a server error. Client errors (4xx) do not count.
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Tokens processed per day on NagaAI.
Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. Optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories.
On NagaAI, Qwen3 Coder costs $0.15 per 1M input tokens and $0.50 per 1M output tokens. You pay only for what you use, with no subscription.
Qwen3 Coder reads up to 262.1k tokens in one request, counting the prompt and the answer together.
Yes. Qwen3 Coder can call your functions as tools and can answer in a JSON schema you give it.
It takes text as input and returns text.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI or Anthropic SDK pointed at NagaAI. The API section on this page has a ready example.
Not enough data yet
Not enough data yet
Not enough data yet