All models
Alibaba (Qwen)
Qwen3 Coder 30B A3B Instruct fastruns locally
alibaba/qwen3-coder-30b-a3b
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...
Input / 1M
$0.15
USD per million tokens
Output / 1M
$0.60
USD per million tokens
Est. cost / token
$0.000000262
$0.26 per 1M, 3:1 mix
Context window
262K
max output 236K
Major features
Open weightsJSON 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 | 15.9 GB |
| Q3_K_M | fair | 18.1 GB |
| Q4_K_Mrecommended | good | 22.1 GB |
| Q5_K_M | very good | 25.3 GB |
| Q6_K | excellent | 28.7 GB |
| Q8_0 | near-lossless | 36.5 GB |
| F16 | lossless | 66.5 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 | $0.15 | $0.60 | — | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.15
- Output
- $0.60
- Blended (3:1)
- $0.26
Details
- Company
- Alibaba (Qwen)
- Version
- 3
- Family
- Qwen
- Released
- 2025-07-31
- Parameters
- 30.5B (3B active)
- Max output
- 236K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 25 min ago