New Release|Introducing Our Model Gateway|Read more in the changelog

Preparing your page

AI Stats is fetching the latest data for this page. This usually only takes a moment.

Back to home

Go back home

Return to the main page and start from a clean slate.

Browse models

Explore the catalogue of AI models and their details.

Read the docs

Check the documentation for guides, references, and examples.

Explore the Gateway

Access the largest unified AI Gateway and use over 300+ models easily.

If this screen doesn't disappear after a short while, you can refresh the page or use one of the links above to continue.

bash

# 1) Set your key
export AI_STATS_API_KEY="sk-live-***"

# 2) Send a request
curl -s https://api.ai-stats.phaseo.app/v1/chat/completions \
-H "Authorization: Bearer $AI_STATS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
  "model": "openai/gpt-4-1-nano-2025-04-14",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Give me one fun fact about cURL."
    }
  ]
}'

Streaming (SSE)

Token-by-token output from chat completions. Streaming is enabled by including "stream: true" in the request body — it really is that easy, and it can be used with any model.

Note: Streaming returns token-by-token output from the server. Use the example for your preferred language below.

bash

# 1) Set your key
export AI_STATS_API_KEY="sk-live-***"

# 2) Send a streaming request
curl -s https://api.ai-stats.phaseo.app/v1/chat/completions \
-H "Authorization: Bearer $AI_STATS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "openai/gpt-4-1-nano-2025-04-14",
    "stream": true,
    "messages": [{ "role": "user", "content": "Write a haiku about rainy Tuesdays." }]
}'

Endpoints

Our main gateway endpoints. See more on the documentation.

Method	Path	Notes
GET	/v1/models	Access all available models and their metadata (capabilities, provider, and supported formats).
POST	/v1/chat	Get a chat-style response from a conversational model; supports streaming.
POST	/v1/images	Create images using image-capable models (generations, edits, variations).
POST	/v1/video	Create or process videos using video-capable models (generations, transformations).
POST	/v1/embeddings	Request vector embeddings for text or other supported inputs.
POST	/v1/moderation	Moderate text or image content for policy compliance and safety checks.

List models

bash

curl -s https://api.ai-stats.phaseo.app/v1/models \
  -H "Authorization: Bearer $AI_STATS_API_KEY" | jq '.[0:5]'

Auth

Send on every request. Keys begin with .

Authorization: Bearer <your key>

aistats_

4xx example

HTTP/1.1 402 Payment Required
{
  "error": {
    "type": "payment_error",
    "code": "insufficient_funds",
    "message": "Your wallet balance is too low for this request.",
    "generation_id": "G-abc123"
  }
}

5xx example

HTTP/1.1 502 Bad Gateway
{
  "error": {
    "type": "server_error",
    "code": "upstream_provider_error",
    "message": "The model provider returned an error. Please retry.",
    "generation_id": "G-xyz789"
  }
}

GPT 4.1 Nano Gateway - Providers & Routing Options | AI Stats

Preparing your page

GPT 4.1 Nano

OpenAI

Active providers

Inactive or upcoming providers

1) Get an API key

Discord

Email

Contact Support (Fastest)

Docs

X (Twitter)

GitHub

List models

Auth