TokenCosts AI.iov1.0
Back to Models Directory
Alibaba Qwenqwen3-coder

Qwen: Qwen3 Coder 480B A35B API Pricing

Official PricingCall via OpenRouter

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-...

Base Input Price$0.30/ 1M tokens
Base Output Price$1.00/ 1M tokens
Prompt Cache Read$0.100-66.67% discount
Batch API Rate-40%24h async offload

Inference Hosts & Aggregator Providers

Compare rates and latency across direct APIs, OpenRouter, and hyperscale cloud providers

Live verified rates
Provider NameInput / 1MOutput / 1MPrompt CachingAccess Endpoint
Alibaba Qwen Direct$0.30$1.00SupportedConnect
OpenRouter$0.30$1.00SupportedConnect

Head-to-Head Comparisons for Qwen: Qwen3 Coder 480B A35B

Qwen: Qwen3 Coder 480B A35B vs OpenAI: GPT-6.1 Sol$0.3/M vs $2/M
Qwen: Qwen3 Coder 480B A35B vs GPT-4o (Omni)$0.3/M vs $2.5/M
Qwen: Qwen3 Coder 480B A35B vs Claude 3.5 Sonnet$0.3/M vs $3/M
Qwen: Qwen3 Coder 480B A35B vs DeepSeek-V3 (deepseek-chat)$0.3/M vs $0.27/M