Models and prices¶
The catalog is evaluated for the authenticated key. A model shown in another profile or in an example is not a promise that it is enabled for your key.
Use the bot's Models screen for a human-readable list and this request for the machine-readable source:
curl https://api.nexus-hub.ru/v1/models \
-H "Authorization: Bearer $NEXUS_API_KEY"
The response includes model IDs, supported endpoint types and only the models
that are active and allowed for the key. GET /v1/models/{model} checks one ID
with the same visibility rules.
Prices are estimates and can change. The bot displays them in the selected currency; the API balance is maintained in RUB. See Pricing and balance for usage and top-up behaviour.
Families¶
- OpenAI-compatible text and response models
- Anthropic-compatible message models
- Gemini-compatible generation and embedding models
- Additional families shown by the current key-specific catalog
Choose a model only after reading the current response. Do not hard-code a model that is not returned for the key.
Context windows¶
These are the declared Nexus compatibility windows for request planning. They are not a promise that every model is enabled for every key; a stricter model-specific limit takes precedence.
| Model group | Declared context window |
|---|---|
| OpenAI and Codex routes | 258,000 tokens |
| Current long-context Claude (Opus/Sonnet/Fable) | 1,000,000 tokens |
| Legacy Claude and Haiku 4.5 | 200,000 tokens |
| Gemini-compatible models | 1,048,576 tokens |
| DeepSeek models | 128,000 tokens |
| GLM models | 128,000 tokens |
See the parameter matrix for generation capabilities.