Model
Surogate 3.7 Flash is on llm.buzz
Open weights, text and images in, a 1M-token context, served from the EU.
- tokens of context
- 1M
- tokens of context
- tokens of output
- 32K
- tokens of output
- per million input tokens, Surogate Spark EU
- $0.15
- per million input tokens, Surogate Spark EU
Surogate 3.7 Flash is listed on llm.buzz as surogate/surogate3.7-flash. It reads text and images and writes text, with up to 1M tokens of context and 32K tokens of output. It supports tools, prompt caching and structured outputs.
Who serves it
Two providers in the EU serve it. Neither trains on prompts, and both keep them for zero days. Prices are per million tokens, as llm.buzz showed them on 27 October 2026:
- Surogate Spark EU: $0.15 input, $1.00 output. 0.04 s to the first token, the median of the last 24 hours.
- Simpleminds EU: $0.10 input, $0.75 output, FP4. 0.07 s to the first token.
The router sends requests to Surogate Spark EU for its faster first token. Prices and speeds move; the live numbers are on the model's llm.buzz page.
Call it
One key works for every model on llm.buzz, through an OpenAI-compatible API:
curl https://api.llm.buzz/api/v1/chat/completions \
-H "Authorization: Bearer $LLM_BUZZ_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "surogate/surogate3.7-flash",
"messages": [{"role": "user", "content": "Hello"}]}'The model page does not yet publish a parameter count or a licence text. We will add both here when it does.
