DeepSeek V4 Flash 0731 Fast vs Devstral 2 123B
deepseek/deepseek-v4-flash-0731-fast · 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 $0.2377 / $0.4753 for DeepSeek V4 Flash 0731 Fast, about 93% 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 DeepSeek V4 Flash 0731 Fast when context size wins. DeepSeek V4 Flash 0731 Fast carries the larger context window (1,000,000 vs 256,000 tokens), which can matter for long-document work.
DeepSeek V4 Flash 0731 Fast vs Devstral 2 123B, side by side
| Spec | DeepSeek V4 Flash 0731 Fast | Devstral 2 123B |
|---|---|---|
| Price · input / 1M | $0.2377 | $0.0077 |
| Price · output / 1M | $0.4753 | $0.0384 |
| Context length | 1,000,000 | 256,000 |
| Max output tokens | 32,768 | 32,000 |
| Input modalities | text | text |
| Output modalities | text | text |
| Tools / functions | Yes | Yes |
| Reasoning | Yes | — |
| % off list | 32.1% off | 98.1% off |
| First token, median (7 days) | 1.5 s (1,443 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 0731 Fast vs Devstral 2 123B — FAQ
Is DeepSeek V4 Flash 0731 Fast or Devstral 2 123B cheaper?
Devstral 2 123B is cheaper on a blended token mix, by about 93%. 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 0731 Fast and Devstral 2 123B?
DeepSeek V4 Flash 0731 Fast: $0.2377 in / $0.4753 out per 1M tokens. Devstral 2 123B: $0.0077 in / $0.0384 out per 1M tokens. That's roughly a 93% blended difference. Prices are live; UberLLM adds no fee.
Can I use both DeepSeek V4 Flash 0731 Fast 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.