Skip to content

One API.Every model.

Frontier and open-weight models through a single gateway.

Start free trial

Frontier and open-weight models, through a single gateway.

  • OpenAI
  • Anthropic
  • Qwen

Start in minutes.Then build.

  1. 1. Choose a model

    From the catalogue, with prices

    Pick an enabled model and see its price, limits and features before you send anything.

  2. 2. Create a key

    Scoped to your application

    Start your free trial, then allow specific models, set a budget and expiry, and rotate or revoke the key from the dashboard.

  3. 3. Send a request

    With your existing client

    Point your existing SDK or HTTP client at SingleAPI and send a chat completion.

Change the model.Keep the interface.

Use the same chat-completion endpoint across supported providers. Pick a model below to see the request.

Check availability
Python with the OpenAI SDK 
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["SINGLEAPI_API_KEY"],
    base_url="https://singleapi.ai/api/v1",
)

stream = client.chat.completions.create(
    model="openai/gpt-4o-mini",
    messages=[{"role": "user", "content": "Say hello."}],
    stream=True,
)

for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
Use cURL instead
cURL
curl "https://singleapi.ai/api/v1/chat/completions" \
  -H "Authorization: Bearer $SINGLEAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o-mini",
    "messages": [{"role": "user", "content": "Say hello."}],
    "stream": true
  }' --no-buffer

Example only. Select an enabled model and allow it on your API key before sending a request. Streaming depends on model support.

Choose howyou connect.

Pay with SingleAPI credits, or bring your own provider key and pay your provider directly.

Set up your own key

SingleAPI credits

Buy prepaid credits and call any model in the catalogue.

Usage billed to
Your SingleAPI balance
Sent with each request
Your SingleAPI key

See each model's price in the catalogue.

Bring your own key (BYOK)

Store your provider key, encrypted, and select it on a request. Your provider bills you directly, and no SingleAPI credits are used.

Usage billed to
Your provider account
Sent with each request
Your SingleAPI key and provider key ID

The model must come from your provider key's provider.

Questions beforeyour first request.

Will my existing SDK work?

Yes, for the endpoints and request fields we document. Point any OpenAI-compatible SDK or HTTP client at SingleAPI's base URL. The API reference lists what is supported.

Check the API reference
Which models can I use?

The model catalogue shows enabled models, customer prices, limits and features. Your API key must also allow the model. Model availability can change.

See models and pricing
Is streaming supported?

Yes, for models with streaming enabled in the catalogue. Set stream to true to receive incremental output. Function tools and JSON formats also depend on the selected model's enabled features.

Read about streaming
Do you store my prompts?

Content logging is off by default. When you opt in on a key, future prompts and responses are encrypted and expire after 30 days. Provider processing and backup retention are separate.

Read about prompt logs
How does billing work?

Starter is $5 a month after a 14-day free trial and includes every model. You pay for tokens with prepaid SingleAPI credits, or bring your own key (BYOK) and your provider bills you.

Read about billing

Keys, budgets and usage.In one place.

  1. Any model, one interfaceThe same request everywhere.

    Call every supported model through one endpoint, with the same request shape every time.

  2. Open-weight and closed-source, one planEvery model on Starter.

    Starter includes every provider and model, open-weight and closed-source, with third-party models at their provider's list price.

  3. Credits or your own keyPay the way you prefer.

    Pay through SingleAPI with prepaid credits, or bring your own provider key and let your provider bill you.

  4. Key budgets and model accessLimits you set and change.

    Allow specific models, set a budget and an expiry on each key, then rotate or revoke it anytime.

  5. Usage and cost recordsSeparate from prompt content.

    See tokens, charges and timing by key and model, kept apart from optional prompt content.

  6. Streaming, tools and JSONOn the models that support them.

    Stream responses and use function tools or JSON output on models with those features enabled.

  7. Opt-in prompt loggingEncrypted and time-limited.

    Turn on encrypted content logs per key when you need them. Captured content expires after 30 days.

Start your free trial.Send your first request today.

Choose a model and connect the client you already use.

Start free trial