All AI models · LLM benchmarks · Methodology

Alibaba

Qwen3 Coder 480B A35B Instruct

Open Qwen coding heavyweight for repository reasoning and agentic engineering

Model facts

Context window
262K tokens
Maximum output
66K tokens
Cheapest paid input
$0.38 per 1M tokens
Cheapest paid output
$1.55 per 1M tokens
Open weights
yes
Providers
2

Capabilities and modalities

tool calling, temperature control, open weights, text.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
default18.2not measured39.3not measured

Observed price history

  • 2026-08-24: $0.38 input / $1.55 output per 1M tokens

API providers

  • LLM Gateway (NovitaAI) — model id novita/qwen3-coder-480b-a35b-instruct; $0.38 input / $1.55 output per 1M tokens; provider documentation
  • LLM Gateway (Vertex AI (OpenAI-compatible)) — model id vertex-openai/qwen3-coder-480b-a35b-instruct; $0.22 input / $1.8 output per 1M tokens; provider documentation