Gemini 2.5 Flash-Lite (Reasoning)
Gemini 2.5 Flash-Lite (Reasoning) is a text-based AI model by Google. It features 329 tok/s output speed, $0.10/1M input tokens pricing. It scores 17.6 on the intelligence index.
Strengths
- +Very fast output (329 tok/s)
- +Very affordable pricing ($0.10/1M tokens)
Benchmarks
Intelligence17.6Coding9.5Math53.3
MMLU-Pro
0.8
GPQA
0.6
LiveCodeBench
0.6
Intelligence
17.6
Coding
9.5
Math
53.3
Output Speed
329 tok/s
Latency (TTFT)
11.34s
Blended Price
$0.17/M
Pricing per 1M Tokens
| Input (Prompt) | $0.10 |
| Output (Completion) | $0.40 |
| Cache Read | Free |
| Cache Write | Free |
Specifications
| Context Length | N/A |
| Max Output Tokens | N/A |
| Input Modalities | Text |
| Output Modalities | Text |
| Tokenizer | N/A |
Compare Gemini 2.5 Flash-Lite (Reasoning) with:
Alternatives to Gemini 2.5 Flash-Lite (Reasoning)
More from Google
Frequently Asked Questions
How much does Gemini 2.5 Flash-Lite (Reasoning) cost?
Gemini 2.5 Flash-Lite (Reasoning) costs $0.10/1M input tokens and $0.40/1M output tokens.
Is Gemini 2.5 Flash-Lite (Reasoning) good for coding?
Gemini 2.5 Flash-Lite (Reasoning) has a lower coding score of 9.5. For demanding coding tasks, consider a model with a higher coding benchmark.
How fast is Gemini 2.5 Flash-Lite (Reasoning)?
Gemini 2.5 Flash-Lite (Reasoning) generates output at 329 tok/s. Time to first token is 11.34s.
Is there a free version of Gemini 2.5 Flash-Lite (Reasoning)?
No, Gemini 2.5 Flash-Lite (Reasoning) is a paid model. Check the free models page for zero-cost alternatives.
What are alternatives to Gemini 2.5 Flash-Lite (Reasoning)?
Last updated: