All models
Alibaba (Qwen)
Qwen3 Coder 480B A35B fastruns locally
alibaba/qwen3-coder
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-context reasoning over...
Input / 1M
$0.30
USD per million tokens
Output / 1M
$1.00
USD per million tokens
Est. cost / token
$0.000000475
$0.47 per 1M, 3:1 mix
Context window
262K
max output 66K
Major features
Open weightsCachingJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding4
- reasoning2
- math2
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision1
- long context3
- agentic3
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 218 GB |
| Q3_K_M | fair | 253 GB |
| Q4_K_Mrecommended | good | 315 GB |
| Q5_K_M | very good | 365 GB |
| Q6_K | excellent | 420 GB |
| Q8_0 | near-lossless | 542 GB |
| F16 | lossless | 1015 GB |
Estimates. Mixture-of-experts: memory covers all parameters; only the active ones are used per token, so it runs faster than its size suggests.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.30 | $1.00 | $0.10 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.30
- Output
- $1.00
- Cached input
- $0.10
- Blended (3:1)
- $0.47
Details
- Company
- Alibaba (Qwen)
- Version
- 3
- Family
- Qwen
- Released
- 2025-07-23
- Parameters
- 480.2B (35B active)
- Max output
- 66K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 25 min ago