Qwen3-Coder 480B A35B Instruct: Benchmarks, Pricing & Context Window
Qwen3-Coder 480B A35B Instruct is a language model from Qwen, released in January 2025, with a 262K-token context window, and pricing from $0.300/M input, $0.100/M cached input, $1.00/M output.
Qwen3-Coder-480B-A35B-Instruct is Qwen's most agentic code model to date, featuring 480 billion total parameters with 35 billion activated parameters using MoE architecture. It achieves significant performance among open models on Agentic
Qwen3-Coder 480B A35B Instruct benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for Qwen3-Coder 480B A35B Instruct across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How Qwen3-Coder 480B A35B Instruct holds up as conversations get longer.
Quality Tracker
Qwen3-Coder 480B A35B Instruct Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Fri Oct 09 2026Qwen3-Coder 480B A35B Instruct pricing
Providers
Qwen3-Coder 480B A35B Instruct starts at $0.300 per million input tokens and $1.00 per million output tokens via DeepInfra. Reused prompt prefixes cost $0.100 per million cached input tokens.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 DeepInfra | $0.300 | $0.100 | $1.00 | 262.1K/262.1K | — | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Qwen3-Coder 480B A35B Instruct model size
Qwen3-Coder 480B A35B Instruct has 480 billion parameters. See how it compares to other models in the same parameter range.
Qwen3-Coder 480B A35B Instruct context window
Input and output token limits for Qwen3-Coder 480B A35B Instruct, plus how it ranks on long-context understanding.
Try now
huggleMake it with
Qwen3-Coder 480B A35B Instruct.
Qwen3-Coder 480B A35B Instruct latency
Qwen3-Coder 480B A35B Instruct time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
Qwen3-Coder 480B A35B Instruct examples
Recent arena outputs from Qwen3-Coder 480B A35B Instruct, picked from the highest-ranked matchups.
Qwen3-Coder 480B A35B Instruct license
Qwen3-Coder 480B A35B Instruct is released under the Apache 2.0 license, which permits commercial use, has 480.0B parameters.
- License
- Apache 2.0
- Commercial use allowed
- Parameters
- 480.0B
Apache License 2.0 - allows commercial use
Qwen3-Coder 480B A35B Instruct resources
Official sources for Qwen3-Coder 480B A35B Instruct: provider documentation, official playground, paper or system card, official launch post, source repository, model weights.
Qwen3-Coder 480B A35B Instruct vs other models
The most-compared alternatives to Qwen3-Coder 480B A35B Instruct are LongCat-Flash-Thinking-2601, Nova 2 Pro, o1. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Qwen3-Coder 480B A35B Instruct
Models ranked just above and below Qwen3-Coder 480B A35B Instruct by LLM Stats score.
FAQ
Common questions about Qwen3-Coder 480B A35B Instruct.