Models and Model IDs

The Models page is the source of truth for public model IDs. Use it when calling the API, configuring tools, and troubleshooting model_not_found.

Good starter models

Need	Start with	Why
Low-cost testing	`deepseek-v4-flash`	Fast API checks, automation, and agent loops.
General app features	`gpt-4o-mini`	Text generation, extraction, support, and lightweight reasoning.
Multilingual workflows	`Qwen/Qwen-Plus`	Balanced English, Spanish, and Chinese generation.

Copy the exact model ID

Model IDs are case-sensitive. Slashes and suffixes matter.

Correct:

Qwen/Qwen-Plus

Different IDs:

qwen-plus
Qwen Plus
qwen/qwen-plus

Public model status

The website uses these model status labels:

Status	Meaning
`Available`	Publicly available and usable through the API.
`Price pending`	Visible for catalog transparency but not available through the public API until pricing is confirmed.
`Tiered`	Public model with complex or tiered pricing normalized for display.
`Unavailable`	Not currently available upstream.

Only publicly available models appear in GET /v1/models.

Key model scope

An API key can be:

unrestricted, which means it can use all current and future publicly available models;
limited to chat models;
limited to selected model IDs.

If a key is scoped too narrowly, a request can return model_not_found even when the model exists in the public catalog. Check the key's model scope before changing application code.

Troubleshooting `model_not_found`

Open Models.
Search for the model you want.
Copy the full model ID.
Confirm the key's model scope allows that model.
Retry the request.

Do not copy vendor aliases directly from another provider's documentation. NexoRouter public model IDs may differ from upstream aliases.