All models
Alibaba (Qwen)
Qwen3 235B A22B Thinking 2507 balancedruns locally
alibaba/qwen3-235b-a22b-thinking-2507
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...
Input / 1M
$0.45
USD per million tokens
Output / 1M
$3.50
USD per million tokens
Est. cost / token
$0.000001213
$1.21 per 1M, 3:1 mix
Context window
128K
max output 16K
Major features
Open weightsReasoningTools
Task suitability (heuristic 1–5, not a benchmark)
- coding4
- reasoning4
- math4
- summarization4
- extraction4
- classification4
- chat4
- creative4
- translation4
- vision1
- long context3
- agentic4
Run it locally
Will it run on my machine? →ollama run qwen3:235b| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 108 GB |
| Q3_K_M | fair | 126 GB |
| Q4_K_Mrecommended | good | 156 GB |
| Q5_K_M | very good | 181 GB |
| Q6_K | excellent | 207 GB |
| Q8_0 | near-lossless | 267 GB |
| F16 | lossless | 499 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 | $0.45 | $3.50 | — | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.45
- Output
- $3.50
- Blended (3:1)
- $1.21
Details
- Company
- Alibaba (Qwen)
- Version
- 3
- Family
- Qwen
- Released
- 2025-07-25
- Parameters
- 235.1B (22B active)
- Max output
- 16K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 25 min ago