google/gemma-4-31B-it-Ultra vs Qwen3 Omni 30B A3B Thinking
They cost about the same for input tokens: google/gemma-4-31B-it-Ultra $0.27 per M, Qwen3 Omni 30B A3B Thinking $0.25 per M. google/gemma-4-31B-it-Ultra is 1.3× cheaper for output tokens: google/gemma-4-31B-it-Ultra costs $0.76 per M and Qwen3 Omni 30B A3B Thinking costs $0.97 per M. google/gemma-4-31B-it-Ultra reads more: google/gemma-4-31B-it-Ultra takes up to 131,072 tokens of context and Qwen3 Omni 30B A3B Thinking up to 65,536. google/gemma-4-31B-it-Ultra accepts image, text; Qwen3 Omni 30B A3B Thinking accepts audio, image, text.
| google/gemma-4-31B-it-Ultra | Qwen3 Omni 30B A3B Thinking | |
|---|---|---|
| Model id | google/gemma-4-31B-it-Ultra | qwen/qwen3-omni-30b-a3b-thinking |
| Input | $0.27 per M | $0.25 per M |
| Output | $0.76 per M | $0.97 per M |
| Context length | 131,072 tokens | 65,536 tokens |
| Accepts | image, text | audio, image, text |
| Produces | text | text |
| Served by | deepinfra | novita |
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.