Qwen3 235B A22B Thinking is
Alibaba's language model with a 262K context window and up to 33K output tokens, available from 7 providers, starting at $0.130 / 1M input and $0.600 / 1M output. A high-performance open-weight MoE language model with 235B total and 22B active parameters, optimized for complex reasoning tasks with structured thinking-mode output.
Capabilities
Input3/5
✓
✓
·
·
✓
Output1/5
✓
·
·
·
·
Capabilities4/13
✓
·
✓
✓
✓
·
·
·
·
·
·
·
·
Pricing by Provider
| Provider | Standard | Batch | |||
|---|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | Input $ / 1M | Output $ / 1M | |
OpenRouter | $0.130 | $0.600 | N/A | — | — |
Fireworks AI | $0.220 | $0.880 | N/A | — | — |
Alibaba Qwen | $0.230 | $2.30 | N/A | $0.115 | $1.15 |
Vercel AI Gateway | $0.230 | $2.30 | $0.200 | — | — |
DeepInfra | $0.300 | $2.90 | N/A | — | — |
Novita | $0.300 | $3.00 | N/A | — | — |
Together AI | $0.650 | $3.00 | N/A | — | — |
Cost Calculator
Preset:
Compares every provider & tier in USD
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Qwen3 30B A3B Thinking | 262K | $0.080 | $0.400 | Available | |
| Qwen3 Coder 30B A3B Instruct | 262K | $0.070 | $0.270 | Available | |
| Qwen3 30B A3B Instruct | 262K | $0.090 | $0.300 | Available | |
| Qwen3 235B A22B Thinking | 262K | $0.130 | $0.600 | Current | |
| Qwen3 Coder | 262K | $0.220 | $1.00 | Available | |
| Qwen3 235B A22B | 262K | $0.180 | $0.540 | Available | |
| Qwen3 30B A3B | 131K | $0.080 | $0.280 | Available | |
| KwaiPilot KAT Coder | — | 262K | $0.900 | $0.900 | Available |
| Qwen3 235B A22B Instruct | — | 262K | $0.090 | $0.580 | Available |
| Qwen3 Coder 480B A35B Instruct | — | 262K | $0.220 | $1.30 | Available |
| Qwen3 Coder 480B Instruct | — | 4K | $0.900 | $0.900 | Available |
HuggingFace
404 likes78,232 downloads/month461,592 total downloads