Back to models
deprecated
Qwen3 235B A22B Instruct 2507
qwen/qwen3-235b-a22b-instructPrices
- Input
$0.22 per 1M tokens
low- Output
$0.88 per 1M tokens
low
Also available on
The same model, sold by someone else. The price above is the maker's own.
| Channel | What | Price |
|---|---|---|
| Fireworks AI · fireworks-ai | Input | $0.22 per 1M tokens |
| Output | $0.88 per 1M tokens | |
| Other · 302ai | Input | $0.29 per 1M tokens |
| Output | $1.14 per 1M tokens | |
| Other · abacus | Input | $0.13 per 1M tokens |
| Output | $0.60 per 1M tokens | |
| Other · cortecs | Input | $0.199 per 1M tokens |
| Input (cached read) | $0.018 per 1M tokens | |
| Output | $0.598 per 1M tokens | |
| Other · crusoe | Input | $0.22 per 1M tokens |
| Input (cached read) | $0.11 per 1M tokens | |
| Output | $0.80 per 1M tokens | |
| Other · deepinfra | Input | $0.09 per 1M tokens |
| Output | $0.55 per 1M tokens | |
| Other · edenai | Input | $0.23 per 1M tokens |
| Input (cached read) | $0.20 per 1M tokens | |
| Input (host: deepinfra) | $0.09 per 1M tokens | |
| Input (host: greenpt) | $0.9973 per 1M tokens | |
| Input (host: nebius) | $0.20 per 1M tokens | |
| Input (host: scaleway) | $0.8311 per 1M tokens | |
| Output | $0.92 per 1M tokens | |
| Output (host: deepinfra) | $0.55 per 1M tokens | |
| Output (host: greenpt) | $2.99 per 1M tokens | |
| Output (host: nebius) | $0.60 per 1M tokens | |
| Output (host: scaleway) | $2.49 per 1M tokens | |
| Other · greenpt | Input | $1.03 per 1M tokens |
| Input (cached read) | $0.018 per 1M tokens | |
| Output | $3.08 per 1M tokens | |
| Output (reasoning) | $8.40 per 1M tokens | |
| Other · huggingface | Input | $0.855 per 1M tokens |
| Output | $2.57 per 1M tokens | |
| Other · huggingface-hyperbolic | Input | $2.00 per 1M tokens |
| Output | $2.00 per 1M tokens | |
| Other · huggingface-nebius | Input | $0.20 per 1M tokens |
| Output | $0.60 per 1M tokens | |
| Other · huggingface-novita | Input | $0.09 per 1M tokens |
| Output | $0.58 per 1M tokens | |
| Other · huggingface-together | Input | $0.20 per 1M tokens |
| Output | $0.60 per 1M tokens | |
| Other · iflowcn | Input | $0.00 per 1M tokens |
| Output | $0.00 per 1M tokens | |
| Other · jiekou | Input | $0.15 per 1M tokens |
| Output | $0.80 per 1M tokens | |
| Other · llmgateway | Input | $0.09 per 1M tokens |
| Output | $0.58 per 1M tokens | |
| Other · llmgateway-providers | Input (host: cerebras) | $0.60 per 1M tokens |
| Input (host: novita) | $0.09 per 1M tokens | |
| Output (host: cerebras) | $1.20 per 1M tokens | |
| Output (host: novita) | $0.58 per 1M tokens | |
| Other · meganova | Input | $0.09 per 1M tokens |
| Output | $0.10 per 1M tokens | |
| Other · merge-gateway | Input | $0.10 per 1M tokens |
| Input (cached read) | $0.0574 per 1M tokens | |
| Output | $0.60 per 1M tokens | |
| Other · modelscope | Input | $0.00 per 1M tokens |
| Output | $0.00 per 1M tokens | |
| Other · nano-gpt | Input | $0.095 per 1M tokens |
| Input (cached read) | $0.0475 per 1M tokens | |
| Output | $0.5803 per 1M tokens | |
| Other · nebius | Input | $0.20 per 1M tokens |
| Input (cached read) | $0.20 per 1M tokens | |
| Output | $0.60 per 1M tokens | |
| Other · novita | Input | $0.09 per 1M tokens |
| Output | $0.58 per 1M tokens | |
| Other · novita-ai | Input | $0.09 per 1M tokens |
| Output | $0.58 per 1M tokens | |
| Other · pioneer | Input | $1.20 per 1M tokens |
| Input (cache write) | $1.20 per 1M tokens | |
| Input (cached read) | $1.20 per 1M tokens | |
| Output | $1.20 per 1M tokens | |
| Other · qiniu-ai | Input | $0.2899 per 1M tokens |
| Output | $1.16 per 1M tokens | |
| Other · replicate | Input | $0.264 per 1M tokens |
| Output | $1.06 per 1M tokens | |
| Other · runcrate | Input | $0.0945 per 1M tokens |
| Output | $0.5775 per 1M tokens | |
| Other · scaleway | Input | $0.8411 per 1M tokens |
| Output | $2.52 per 1M tokens | |
| Output (reasoning) | $8.40 per 1M tokens | |
| Other · submodel | Input | $0.20 per 1M tokens |
| Output | $0.30 per 1M tokens | |
| Other · venice | Input | $0.15 per 1M tokens |
| Output | $0.75 per 1M tokens | |
| Other · wandb | Input | $0.10 per 1M tokens |
| Output | $0.10 per 1M tokens |
Specifications
- Provider
- qwen
- Context window
- 131,072
- Max output tokens
- 16,384
- Open weights
- yes
- Released
- 07/21/2025
- Retires
- no date announced
- First seen by this tracker
Price history
No price of this model has changed since we started tracking it.
- Input
- 0.22 per 1M tokens, unchanged since 09/14/2026
- Output
- 0.88 per 1M tokens, unchanged since 09/14/2026