All models
Alibaba (Qwen)
Qwen3 Next 80B A3B Instruct fastruns locally
alibaba/qwen3-next-80b-a3b
Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...
Input / 1M
$0.15
USD per million tokens
Output / 1M
$1.20
USD per million tokens
Est. cost / token
$0.000000413
$0.41 per 1M, 3:1 mix
Context window
262K
max output 66K
Major features
Open weightsCachingJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- 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 | 39.2 GB |
| Q3_K_M | fair | 45.2 GB |
| Q4_K_Mrecommended | good | 55.6 GB |
| Q5_K_M | very good | 64.2 GB |
| Q6_K | excellent | 73.4 GB |
| Q8_0 | near-lossless | 94.1 GB |
| F16 | lossless | 174 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 | $1.20 | $0.070 | litellm+openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.15
- Output
- $1.20
- Cached input
- $0.070
- Blended (3:1)
- $0.41
Details
- Company
- Alibaba (Qwen)
- Version
- 3
- Family
- Qwen
- Released
- 2025-09-11
- Parameters
- 81.3B (3B active)
- Max output
- 66K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 25 min ago