Qwen/Qwen3-235B-A22B-Instruct-2507 vs google/gemma-4-31B-it-turbo
They cost about the same for input tokens: Qwen/Qwen3-235B-A22B-Instruct-2507 $0.09 per M, google/gemma-4-31B-it-turbo $0.09 per M. google/gemma-4-31B-it-turbo is 1.6× cheaper for output tokens: Qwen/Qwen3-235B-A22B-Instruct-2507 costs $0.55 per M and google/gemma-4-31B-it-turbo costs $0.34 per M. Both read up to 262,144 tokens of context. Qwen/Qwen3-235B-A22B-Instruct-2507 accepts text; google/gemma-4-31B-it-turbo accepts image, text.
| Qwen/Qwen3-235B-A22B-Instruct-2507 | google/gemma-4-31B-it-turbo | |
|---|---|---|
| Model id | Qwen/Qwen3-235B-A22B-Instruct-2507 | google/gemma-4-31B-it-turbo |
| Input | $0.09 per M | $0.09 per M |
| Output | $0.55 per M | $0.34 per M |
| Context length | 262,144 tokens | 262,144 tokens |
| Accepts | text | image, text |
| Produces | text | text |
| Served by | deepinfra | deepinfra |
Prices are the providers' list prices per million tokens, as of . Both run on your own provider key through one OpenAI-compatible endpoint, with no fee on the tokens.