Qwen3 235B A22B Instruct is
Alibaba's language model with a 262K context window and up to 33K output tokens, available from 7 providers, starting at $0.090 / 1M input and $0.580 / 1M output. An instruction-tuned FP8 version of the Qwen3 235B A22B MoE model with enhanced tool use, coding, instruction following, and logical reasoning capabilities.
17.0#159 |
14.0#146 |
23.7#139 |
0.8#100 |
0.6#149 |
0.0#198 |
0.3#136 |
0.3#50 |
0.4#159 |
1.30s#267 |
0.3#135 |
0.9#46 |
0.2#139 |
0.0#222 |
0.1#139 |
0.2#163 |
35.9#175 |
Capabilities
Input1/5
✓
·
·
·
·
Output1/5
✓
·
·
·
·
Capabilities3/13
·
·
✓
✓
✓
·
·
·
·
·
·
·
·
Pricing by Provider
| Provider | Standard | Batch | ||
|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | |
DeepInfra | $0.090 | $0.600 | — | — |
Novita | $0.090 | $0.580 | — | — |
Together AI | $0.200 | $6.00 | — | — |
Fireworks AI | $0.220 | $0.880 | — | — |
Google Vertex AI | $0.220 | $0.880 | $0.110 | $0.440 |
Alibaba Qwen | $0.230 | $0.920 | $0.115 | $0.460 |
Replicate | $0.264 | $1.06 | — | — |
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 | Available | |
| 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 | |
| Qwen3 235B A22B Instruct | — | 262K | $0.090 | $0.580 | Current |
| KwaiPilot KAT Coder | — | 262K | $0.900 | $0.900 | Available |
| Qwen3 Coder 480B A35B Instruct | — | 262K | $0.220 | $1.30 | Available |
| Qwen3 Coder 480B Instruct | — | 4K | $0.900 | $0.900 | Available |
HuggingFace
773 likes165,625 downloads/month1,172,897 total downloads