Output tokens cost $0.39 per million on deepinfra-gemma-4-26b-a4b-it and $0.40 per million on gemini-2.5-flash-lite. Input tokens cost $0.09 per million on deepinfra-gemma-4-26b-a4b-it and $0.10 per million on gemini-2.5-flash-lite. Cached input tokens are billed at $0.01 per million on deepinfra-gemma-4-26b-a4b-it and $0.01 per million on gemini-2.5-flash-lite. Context lengths are 262,100 tokens on deepinfra-gemma-4-26b-a4b-it and 1,048,576 tokens on gemini-2.5-flash-lite. Time to first token (TTFT) measured on AIHubMix is 0.4s on deepinfra-gemma-4-26b-a4b-it and 3.2s on gemini-2.5-flash-lite. Measured output throughput is 42.6 tok/s on deepinfra-gemma-4-26b-a4b-it and 74.7 tok/s on gemini-2.5-flash-lite.
deepinfra-gemma-4-26b-a4b-itgemini-2.5-flash-liteA 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-Lite is a balanced model from Google, optimized for applications that require low-latency performance. It retains the practical capabilities of the Gemini 2.5 family, including configurable reasoning based on budget, integration with tools such as grounding via Google Search and code execution, multimodal input support, and an ultra-long context window of up to 1 million tokens, delivering a strong balance between efficiency, functionality, and cost.
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: $0.39/M output tokens; gemini-2.5-flash-lite: $0.40/M. Use the cost calculator above to estimate your own workload.
deepinfra-gemma-4-26b-a4b-it: 0.4s 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-lite 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-lite.
gemini-2.5-flash-lite at 74.7 tok/s and deepinfra-gemma-4-26b-a4b-it at 42.6 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.
AIHubMix