Trinity Large Thinking vs Mistral Small 4
arcee-ai/trinity-large-thinking · mistralai/mistral-small-4
As of October 31, 2026, Mistral Small 4 is the cheaper API on UberLLM: $0.0938 per million input tokens and $0.3750 per million output, versus $0.2344 / $0.8438 for Trinity Large Thinking, about 56% less when output is 3 tokens for every input token. These are the median prices buyers paid over the last 24 hours. Both work with one OpenAI-compatible key and UberLLM adds no fee. Choose Mistral Small 4 to cut cost; choose Trinity Large Thinking when its capabilities fit your task better.
Trinity Large Thinking vs Mistral Small 4, side by side
| Spec | Trinity Large Thinking | Mistral Small 4 |
|---|---|---|
| Price · input / 1M | $0.2344 | $0.0938 |
| Price · output / 1M | $0.8438 | $0.3750 |
| Context length | 256,000 | 256,000 |
| Max output tokens | 32,768 | 32,768 |
| Input modalities | text | text, image |
| Output modalities | text | text |
| Tools / functions | Yes | Yes |
| Vision (image input) | — | Yes |
| Reasoning | Yes | Yes |
| % off list | 22% off | 38% off |
Median prices buyers paid on UberLLM over the last 24 hours. No UberLLM fee on requests; adding credit by card costs 5.5% + $0.50. Updated October 31, 2026.
Trinity Large Thinking vs Mistral Small 4 — FAQ
Is Trinity Large Thinking or Mistral Small 4 cheaper?
Mistral Small 4 is cheaper on a blended token mix, by about 56%. 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 Trinity Large Thinking and Mistral Small 4?
Trinity Large Thinking: $0.2344 in / $0.8438 out per 1M tokens. Mistral Small 4: $0.0938 in / $0.3750 out per 1M tokens. That's roughly a 56% blended difference. Prices are live; UberLLM adds no fee.
Can I use both Trinity Large Thinking and Mistral Small 4 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.