Compare Deepinfra Gemma 4 26B A4B It from Google and gemini-2.5-flash-preview-05-20-nothink from Google on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the AIHubMix API.
Deepinfra Gemma 4 26B A4B Itgemini-2.5-flash-preview-05-20-nothinkA Mixture-of-Experts model that activates only 4B parameters per inference,delivering high-performance reasoning with a fraction of the memory cost - idealfor cost-efficient, high-throughput server deployments.
Gemini-2.5-flash-preview-05-20 is enabled by default for thinking; to disable it, request the name gemini-2.5-flash-preview-05-20-nothink.Only OpenAI-compatible format calls are supported; Gemini SDK is not supported. For the native Gemini SDK, please set the parameter budget=0 directly.
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Promotional prices show the discounted rate; see each model page for promotion windows.
Daily traffic served through AIHubMix — how demand for each model is trending.
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
Estimate your monthly bill for the same workload on each model.
Monthly = daily × 30. Discounted rates applied where a promotion is active.
Deepinfra Gemma 4 26B A4B It: $0.385/M output tokens; gemini-2.5-flash-preview-05-20-nothink: $2.499/M. Use the cost calculator above to estimate your own workload.
Deepinfra Gemma 4 26B A4B It: 0.3s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
Deepinfra Gemma 4 26B A4B It accepts 262,100 and gemini-2.5-flash-preview-05-20-nothink accepts 1,048,576 input tokens. Maximum output per request is 131,100 tokens on Deepinfra Gemma 4 26B A4B It and 65,536 tokens on gemini-2.5-flash-preview-05-20-nothink.
gemini-2.5-flash-preview-05-20-nothink at 54.6 tok/s and Deepinfra Gemma 4 26B A4B It at 32.7 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.
Related model match-ups readers also look at.