Models

Endpoint

GET https://api.bve.me/v1/models

Requires Authorization: Bearer sk-bve-YOUR_KEY.

This endpoint proxies directly to Fuelix /models. The response follows the OpenAI models list format.

Response

{
  "object": "list",
  "data": [
    {
      "id": "gpt-4o",
      "object": "model",
      "created": 1715367049,
      "owned_by": "openai"
    }
  ]
}

As of 2026-05-22, Fuelix provides 103 models. The list below reflects the live API and may change over time.

GPT models

Model	Notes
`gpt-5.4` / `gpt-5.4-mini` / `gpt-5.4-nano`	Latest GPT generation
`gpt-5.2` / `gpt-5.2-chat`	GPT 5.2
`gpt-5` / `gpt-5-chat` / `gpt-5-mini` / `gpt-5-nano`	GPT 5
`gpt-4.1` / `gpt-4.1-mini` / `gpt-4.1-nano`	GPT 4.1
`gpt-4o` / `gpt-4o-mini`	GPT-4o
`gpt-oss-20b`	Open-source 20B
`o3` / `o3-mini` / `o4-mini`	Reasoning models

Claude models

Model	Notes
`claude-sonnet-4-6`	Claude Sonnet 4.6 (latest)
`claude-sonnet-4-5` / `claude-sonnet-4`	Claude Sonnet 4.x
`claude-haiku-4-5` / `claude-haiku-4`	Claude Haiku 4.x
`claude-3-7-sonnet`	Claude 3.7 Sonnet
`claude-3-5-sonnet` / `claude-3-5-haiku`	Claude 3.5

Gemini models

Model	Notes
`gemini-3.5-flash`	Latest Gemini Flash
`gemini-3.1-pro` / `gemini-3.1-flash-*`	Gemini 3.1
`gemini-3-pro` / `gemini-3-flash`	Gemini 3
`gemini-2.5-pro` / `gemini-2.5-flash`	Gemini 2.5
`gemini-2.0-flash`	Gemini 2.0
`gemini-embedding-001`	Gemini embeddings

Other models

Model	Notes
`mistral-large` / `mistral-large-3`	Mistral Large
`llama-4-maverick-17b-128e` / `llama-4-scout-17b-16e`	Llama 4
`llama-3.2-90b`	Llama 3.2
`deepseek-r1`	DeepSeek R1
`gemma-4-31b-it` / `gemma-4-26b-a4b-it`	Gemma 4

Embedding models

Model	Notes
`text-embedding-3-large`	OpenAI embeddings
`text-embedding-3-small`	OpenAI embeddings
`text-embedding-ada-002`	Legacy OpenAI embeddings
`gemini-embedding-001`	Gemini embeddings

Image models

Model	Notes
`imagen-4-ultra`	Highest quality
`imagen-4`	Google Imagen 4
`imagen-3`	Google Imagen 3
`imagen-3-fast`	Fast Imagen 3
`dall-e-3`	In models list; endpoint behavior may vary

Audio models

Model	Notes
`tts-1`	Text-to-speech
`tts-1-hd`	High-quality TTS
`whisper-1`	Transcription
`gpt-4o-transcribe`	GPT-4o transcription
`gpt-4o-transcribe-diarize`	With speaker diarization

cURL example

curl https://api.bve.me/v1/models \
  -H "Authorization: Bearer sk-bve-YOUR_KEY"

OpenAI SDK

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-bve-YOUR_KEY',
  baseURL: 'https://api.bve.me/v1',
});

const models = await client.models.list();
for (const model of models.data) {
  console.log(model.id);
}

Notes

Model availability is determined by Fuelix, not BVE Gateway.
The allowed_models field can be set per key via the Admin API and is stored in D1, but model filtering is not currently enforced by the gateway. All models accessible to the Fuelix upstream remain accessible regardless of this field.