Devstral 2 123B vs GPT-4o Mini
mistralai/devstral-2-123b · openai/gpt-4o-mini
As of November 4, 2026, GPT-4o Mini is the cheaper API on UberLLM: $0.0089 per million input tokens and $0.0354 per million output, versus $0.0077 / $0.0384 for Devstral 2 123B, about 6% 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 GPT-4o Mini to cut cost; choose Devstral 2 123B when context size wins. Devstral 2 123B carries the larger context window (256,000 vs 128,000 tokens), which can matter for long-document work.
Devstral 2 123B vs GPT-4o Mini, side by side
| Spec | Devstral 2 123B | GPT-4o Mini |
|---|---|---|
| Price · input / 1M | $0.0077 | $0.0089 |
| Price · output / 1M | $0.0384 | $0.0354 |
| Context length | 256,000 | 128,000 |
| Max output tokens | 32,000 | 16,384 |
| Input modalities | text | text, image |
| Output modalities | text | text |
| Tools / functions | Yes | Yes |
| Vision (image input) | — | Yes |
| % off list | 98.1% off | 94.1% 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?
Devstral 2 123B vs GPT-4o Mini — FAQ
Is Devstral 2 123B or GPT-4o Mini cheaper?
GPT-4o Mini is cheaper on a blended token mix, by about 6%. 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 Devstral 2 123B and GPT-4o Mini?
Devstral 2 123B: $0.0077 in / $0.0384 out per 1M tokens. GPT-4o Mini: $0.0089 in / $0.0354 out per 1M tokens. That's roughly a 6% blended difference. Prices are live; UberLLM adds no fee.
Can I use both Devstral 2 123B and GPT-4o Mini 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.