DeepSeek V4 Flash vs Devstral 2 123B
deepseek/deepseek-v4-flash · mistralai/devstral-2-123b
As of November 4, 2026, DeepSeek V4 Flash is the cheaper API on UberLLM: $0.0082 per million input tokens and $0.0164 per million output, versus $0.0077 / $0.0384 for Devstral 2 123B, about 53% 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 DeepSeek V4 Flash to cut cost; choose Devstral 2 123B when its capabilities fit your task better.
DeepSeek V4 Flash vs Devstral 2 123B, side by side
| Spec | DeepSeek V4 Flash | Devstral 2 123B |
|---|---|---|
| Price · input / 1M | $0.0082 | $0.0077 |
| Price · output / 1M | $0.0164 | $0.0384 |
| Context length | 1,000,000 | 256,000 |
| Max output tokens | 128,000 | 32,000 |
| Input modalities | text | text |
| Output modalities | text | text |
| Tools / functions | Yes | Yes |
| Reasoning | Yes | — |
| % off list | 91% off | 98.1% off |
| First token, median (7 days) | 4.5 s (1,786 requests) | — |
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?
DeepSeek V4 Flash vs Devstral 2 123B — FAQ
Is DeepSeek V4 Flash or Devstral 2 123B cheaper?
DeepSeek V4 Flash is cheaper on a blended token mix, by about 53%. 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 DeepSeek V4 Flash and Devstral 2 123B?
DeepSeek V4 Flash: $0.0082 in / $0.0164 out per 1M tokens. Devstral 2 123B: $0.0077 in / $0.0384 out per 1M tokens. That's roughly a 53% blended difference. Prices are live; UberLLM adds no fee.
Can I use both DeepSeek V4 Flash 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.