Migrate from Tavily or Exa

Keep your code. Point your client at Keiro's compatible endpoints.

Open in…
Ask on Discord
What your agent reads
Keiro serves Tavily- and Exa-shaped endpoints. Change the base URL and the key, and your existing requests keep working.

| You use | Base URL |
| --- | --- |
| Tavily | `https://api.keirolabs.cloud/api/compat/tavily/v1` |
| Exa | `https://api.keirolabs.cloud/api/compat/exa/v1` |

Supported routes: Tavily `/search` and `/extract`; Exa `/search`, `/contents` and `/answer`.

**Tavily**

```python
from tavily import TavilyClient

tavily = TavilyClient(
    api_key="keiro_your_api_key",
    base_url="https://api.keirolabs.cloud/api/compat/tavily/v1",
)
r = tavily.search("latest LLM benchmarks", search_depth="advanced", max_results=5)
```

**Exa**

```python
from exa_py import Exa

exa = Exa(
    api_key="keiro_your_api_key",
    base_url="https://api.keirolabs.cloud/api/compat/exa/v1",
)
r = exa.search_and_contents("best vector databases 2026", num_results=5, text=True)
```

If your SDK has no base URL option, send the same JSON with plain HTTP to the URLs above.

Check what is supported right now at `GET https://api.keirolabs.cloud/api/compat/status`.
Every page: append .md to the URL. Whole site: /llms.txt · /llms-full.txt

Keiro serves Tavily- and Exa-shaped endpoints. Change the base URL and the key, and your existing requests keep working.

You useBase URL
Tavilyhttps://api.keirolabs.cloud/api/compat/tavily/v1
Exahttps://api.keirolabs.cloud/api/compat/exa/v1

Supported routes: Tavily /search and /extract; Exa /search, /contents and /answer.

from tavily import TavilyClient

tavily = TavilyClient(
    api_key="keiro_your_api_key",
    base_url="https://api.keirolabs.cloud/api/compat/tavily/v1",
)
r = tavily.search("latest LLM benchmarks", search_depth="advanced", max_results=5)

If your SDK has no base URL option, send the same JSON with plain HTTP to the URLs above.

Check what is supported right now at GET https://api.keirolabs.cloud/api/compat/status.

Let your agent build it

Paste one prompt into Claude Code, Cursor, Codex or Windsurf. It installs Keiro MCP, reads these docs and writes the integration against the real API.

Ask on Discord