All models
Alibaba (Qwen)
Qwen3 Coder Next fastruns locally
alibaba/qwen3-coder-next
Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...
Input / 1M
$0.12
USD per million tokens
Output / 1M
$0.80
USD per million tokens
Est. cost / token
$0.00000029
$0.29 per 1M, 3:1 mix
Context window
262K
max output 236K
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 | 38.5 GB |
| Q3_K_M | fair | 44.3 GB |
| Q4_K_Mrecommended | good | 54.6 GB |
| Q5_K_M | very good | 62.9 GB |
| Q6_K | excellent | 72 GB |
| Q8_0 | near-lossless | 92.3 GB |
| F16 | lossless | 171 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.12 | $0.80 | $0.070 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.12
- Output
- $0.80
- Cached input
- $0.070
- Blended (3:1)
- $0.29
Details
- Company
- Alibaba (Qwen)
- Version
- 3
- Family
- Qwen
- Released
- 2026-02-04
- Parameters
- 79.7B
- Max output
- 236K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 25 min ago