The Avaliar Proxy supports the following models across OpenAI, Anthropic, and Google Gemini. Use the exact model ID shown below in your requests.
OpenAI
| Model ID | Description |
|---|
gpt-4o | GPT-4o — flagship multimodal model |
gpt-4o-mini | GPT-4o Mini — fast and cost-efficient |
gpt-4.1 | GPT-4.1 |
gpt-4.1-mini | GPT-4.1 Mini |
gpt-4.1-nano | GPT-4.1 Nano — lightest GPT-4.1 variant |
gpt-5 | GPT-5 |
gpt-5-mini | GPT-5 Mini |
gpt-5-nano | GPT-5 Nano |
gpt-5.1 | GPT-5.1 |
Anthropic (Claude)
| Model ID | Description |
|---|
claude-opus-4-6 | Claude Opus 4.6 — most capable |
claude-sonnet-4-6 | Claude Sonnet 4.6 — balanced performance |
claude-opus-4-5 | Claude Opus 4.5 |
claude-sonnet-4-5 | Claude Sonnet 4.5 |
claude-haiku-4-5 | Claude Haiku 4.5 — fastest, most compact |
claude-opus-4-1 | Claude Opus 4.1 |
Google Gemini
| Model ID | Description |
|---|
gemini-2.5-pro | Gemini 2.5 Pro — most capable Gemini model |
gemini-2.5-flash | Gemini 2.5 Flash — fast and efficient |
gemini-2.5-lite | Gemini 2.5 Lite — lightest 2.5 variant |
gemini-2.0-pro-exp | Gemini 2.0 Pro (Experimental) |
gemini-1.5-pro | Gemini 1.5 Pro |
gemini-1.5-flash | Gemini 1.5 Flash |
Using a Model
Pass the model ID in the model field of your request:
requests.post(
"https://proxy.avaliar.ai/api/openai_service/chat_completion",
json={
"api_key": "your-avaliar-api-key",
"model": "gpt-4o", # Model ID from the table above
"messages": [...]
}
)
If you request a model that is not supported, the proxy will return a 400 error. Make sure to use the exact model ID as listed in the tables above.
