deepseek-ai/DeepSeek-V3.1 vs google/gemma-4-31B-it-Ultra
They cost about the same for input tokens: deepseek-ai/DeepSeek-V3.1 $0.25 per M, google/gemma-4-31B-it-Ultra $0.27 per M. google/gemma-4-31B-it-Ultra is 1.3× cheaper for output tokens: deepseek-ai/DeepSeek-V3.1 costs $0.95 per M and google/gemma-4-31B-it-Ultra costs $0.76 per M. deepseek-ai/DeepSeek-V3.1 reads more: deepseek-ai/DeepSeek-V3.1 takes up to 163,840 tokens of context and google/gemma-4-31B-it-Ultra up to 131,072. deepseek-ai/DeepSeek-V3.1 accepts text; google/gemma-4-31B-it-Ultra accepts image, text.
| deepseek-ai/DeepSeek-V3.1 | google/gemma-4-31B-it-Ultra | |
|---|---|---|
| Model id | deepseek-ai/DeepSeek-V3.1 | google/gemma-4-31B-it-Ultra |
| Input | $0.25 per M | $0.27 per M |
| Output | $0.95 per M | $0.76 per M |
| Context length | 163,840 tokens | 131,072 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.