Documentation

FAQ: Which model should I choose first? in the NexoRouter documentation.

FAQ: Which model should I choose first?

Start with a low-cost, fast chat model while you are still validating base URL, API key, model ID, and Usage Logs. Move to a larger or more expensive model only after the integration path works.

Starter choices

NeedStart withWhy
API setup checkdeepseek-v4-flashFast, low-cost first request and agent-loop testing.
General app featuresgpt-4o-miniBalanced text generation, extraction, and support workflows.
Multilingual outputQwen/Qwen-PlusGood first option for English, Spanish, and Chinese prompts.

Always copy the current model ID from Models. Do not rely on old screenshots, vendor docs, or memory.

Selection checklist

  1. Pick the cheapest model that can complete the task.
  2. Confirm the model appears in GET /v1/models.
  3. Confirm the API key's model scope includes that model.
  4. Run one small non-streaming request.
  5. Check Usage Logs for cost, latency, status, and request ID.
  6. Only then test larger prompts, agent tools, or production traffic.

When to switch models

SymptomTry
Text quality is too weakA stronger chat model from Models.
Latency is too highA faster model or shorter prompt.
Cost is too highA lower-cost model and smaller max_tokens.
Agent edits failA model with better tool-use behavior, then retest in a disposable branch.
model_not_foundCopy the exact model ID and check key model scope.
FAQ: Which model should I choose first? — NexoRouter