Gemini 3.5 Flash Lite vs Devstral 2 123B
google/gemini-3-5-flash-lite · mistralai/devstral-2-123b
As of November 4, 2026, Devstral 2 123B is the cheaper API on UberLLM: $0.0077 per million input tokens and $0.0384 per million output, versus $0.0900 / $0.7500 for Gemini 3.5 Flash Lite, about 95% less when output is 3 tokens for every input token. These are the best prices on the market right now. Both work with one OpenAI-compatible key and UberLLM adds no fee. Choose Devstral 2 123B to cut cost; choose Gemini 3.5 Flash Lite when context size wins. Gemini 3.5 Flash Lite carries the larger context window (1,000,000 vs 256,000 tokens), which can matter for long-document work.
Gemini 3.5 Flash Lite vs Devstral 2 123B, side by side
| Spec | Gemini 3.5 Flash Lite | Devstral 2 123B |
|---|---|---|
| Price · input / 1M | $0.0900 | $0.0077 |
| Price · output / 1M | $0.7500 | $0.0384 |
| Context length | 1,000,000 | 256,000 |
| Max output tokens | 65,536 | 32,000 |
| Input modalities | text, image, video, audio, file | text |
| Output modalities | text | text |
| Tools / functions | Yes | Yes |
| Vision (image input) | Yes | — |
| Reasoning | Yes | — |
| % off list | 70% off | 98.1% off |
Best prices on UberLLM right now. No UberLLM fee on requests; adding credit by card costs 5.5% + $0.50. Updated November 4, 2026. A price more than 70% below list is what buyers were billed, not an error. Why so cheap?
Gemini 3.5 Flash Lite vs Devstral 2 123B — FAQ
Is Gemini 3.5 Flash Lite or Devstral 2 123B cheaper?
Devstral 2 123B is cheaper on a blended token mix, by about 95%. A request costs what its provider charged, UberLLM adds no fee, and every request is listed with its cost in Activity.
What's the price difference between Gemini 3.5 Flash Lite and Devstral 2 123B?
Gemini 3.5 Flash Lite: $0.0900 in / $0.7500 out per 1M tokens. Devstral 2 123B: $0.0077 in / $0.0384 out per 1M tokens. That's roughly a 95% blended difference. Prices are live; UberLLM adds no fee.
Can I use both Gemini 3.5 Flash Lite and Devstral 2 123B with one API?
Yes. Both are served through a single OpenAI-compatible endpoint — set the base URL to https://api.uberllm.dev/v1 and your UberLLM key, then switch between them by changing the model id. Anthropic SDKs work via https://api.uberllm.dev/v1/messages.