Use the API

The API follows the OpenAI chat completions shape. Most clients only need a new base URL and a key.

Create a key

Sign in to the portal at https://app.staging.katara.com, open API keys, and create one. The key is shown once. Keys are bound to your wallet: whatever you approved for spending also covers requests made with the key.

Keys for the public test network start with kat_test_.

Send a request

curl https://api.staging.katara.com/v1/chat/completions \
  -H "Authorization: Bearer $KATARA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "katara/cortex@1",
    "messages": [{"role": "user", "content": "Explain a Merkle tree in two sentences."}],
    "max_tokens": 200
  }'

katara/cortex@1 picks a model for the request and keeps answering when a provider goes away; name a specific model instead when you need exactly that one. The reply carries a katara object with the settled price and the provider that served it:

"katara": { "cost_usdc": "0.000018", "provider": "0xfFe5…38DC" }

With the OpenAI client

from openai import OpenAI

client = OpenAI(base_url="https://api.staging.katara.com/v1", api_key=os.environ["KATARA_API_KEY"])
reply = client.chat.completions.create(
    model="katara/cortex@1",
    messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)

Streaming works the same way with stream=True. The final chunk before [DONE] has an empty choices array and carries the katara charge.

Tool calling follows the OpenAI shape too; see Tool calling for what each model is certified for.

List models

GET /v1/models needs no key and returns every model with its capabilities, context window, and the lowest live price. See the API reference for the full shapes and the error codes.