Capabilities
7-day heat trend
−3.4%Pricing breakdown
Typical 3:1 output-to-input mix, per 1M tokens
Estimated monthly cost by workload
Market position
- Cheaper than 26% of tracked models
- Faster than 93% of tracked models
- Efficiency rank: #24 of 1105
Best suited for
Mixed text, image, audio and document workloads that benefit from one model across modalities.
About google/gemini-3.1-flash-lite
Vercel AI Gateway route for Gemini 3.1 Flash Lite, keeping current low-latency multimodal catalog metadata.
google/gemini-3.1-flash-lite is a Multimodal model from Vercel AI Gateway (US). HotON.ai tracks it at $0.25 per 1M input tokens and $1.50 per 1M output tokens, with a 1049K-token context window, ~170 tokens/sec throughput and 99.0% availability. Its composite efficiency score is 96/100 at an estimated $0.001 per successful task.
Compare google/gemini-3.1-flash-lite
Related market news
Frequently asked questions
How much does google/gemini-3.1-flash-lite cost per 1M tokens?+
google/gemini-3.1-flash-lite is tracked at $0.25 per 1M input tokens and $1.50 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $1.19 per 1M tokens. Figures are illustrative demo data.
What is google/gemini-3.1-flash-lite best for?+
Mixed text, image, audio and document workloads that benefit from one model across modalities.
How fast is google/gemini-3.1-flash-lite?+
google/gemini-3.1-flash-lite delivers about 170 tokens/sec with 99.0% tracked availability, suitable for latency-sensitive, real-time applications.
Is google/gemini-3.1-flash-lite cheaper than other AI models?+
Within the HotON.ai tracked set, google/gemini-3.1-flash-lite is cheaper than 26% of models on input price and ranks #24 of 1105 by overall efficiency.
Related models
Pricing is real (via the TestKey catalog, updated daily). Quality (Arena Elo) is real where the model is ranked on LMArena. Speed, availability and efficiency are modeled estimates.