Qwen3 235B A22B Thinking
DeprecatedQwen3 235B A22B Thinking is Alibaba's language model with a 262K context window and up to 33K output tokens, available from 9 providers, starting at $0.149 / 1M input and $0.880 / 1M output. A thinking-mode variant of the Qwen3 235B A22B MoE model that scales chain-of-thought reasoning depth for improved quality on complex tasks.
Capabilities
Input3/5
Text✓
Image✓
Audio·
Video·
PDF✓
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities5/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
| Provider | Standard | Batch | ||
|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | |
 OpenRouter | $0.149 | $1.50 | — | — |
 Fireworks AI | $0.220 | $0.880 | — | — |
Alibaba Qwen | $0.230 | $2.30 | $0.115 | $1.15 |
 DeepInfra | $0.300 | $2.90 | — | — |
 Hugging Face | $0.300 | $3.00 | — | — |
 Novita | $0.300 | $3.00 | — | — |
 Vercel AI Gateway | $0.400 | $4.00 | — | — |
 Together AI | $0.650 | $3.00 | — | — |
Other/Wandb | $10.00 | $10.00 | — | — |
Cost Calculator
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| MiroThinker 1.7 | — | — | — | — | Available |
| Qwen3 30B A3B Thinking | 262K | $0.080 | $0.400 | Available | |
| Qwen3 Coder 30B A3B Instruct | 262K | $0.070 | $0.260 | Available | |
| Qwen3 30B A3B Instruct | 262K | $0.090 | $0.300 | Available | |
| Qwen3 235B A22B Thinking | 262K | $0.149 | $0.880 | Current | |
| Qwen3 Coder | 1.0M | $0.220 | $1.80 | Available | |
| Qwen3 30B A3B | 131K | $0.080 | $0.290 | Available | |
| Qwen3 235B A22B | 262K | $0.071 | $0.100 | Available | |
| Qwen3 Coder 480B A35B Instruct | — | 262K | $0.220 | $1.30 | Available |
| Qwen3 235B A22B Instruct | — | 262K | $0.090 | $0.580 | Available |
| KwaiPilot KAT Coder | — | 262K | $0.900 | $0.900 | Available |