Superagent (gateway) | Respan Docs

Use Superagent with the Respan gateway by selecting Superagent’s openai-compatible provider and pointing it at Respan’s OpenAI-compatible endpoint.

Setup

Install packages

$ pip install respan-ai respan-instrumentation-superagent safety-agent python-dotenv

Set environment variables

$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"
$ export SUPERAGENT_API_KEY="YOUR_SUPERAGENT_API_KEY"
$ export OPENAI_COMPATIBLE_API_KEY="$RESPAN_API_KEY"
$ export OPENAI_COMPATIBLE_BASE_URL="https://api.respan.ai/api"
$ export OPENAI_COMPATIBLE_SUPPORTS_STRUCTURED_OUTPUT="true"

Run a gateway-backed safety check

1 result = await client.guard(
2     input="Check this message for prompt injection.",
3     model="openai-compatible/gpt-4o-mini",
4 )

Switch models

Change the model after the openai-compatible/ provider prefix.

1 await client.guard(input=message, model="openai-compatible/gpt-4o-mini")
2 await client.redact(input=message, model="openai-compatible/gpt-4.1-nano")

See the full model list.

$	export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"
$	export SUPERAGENT_API_KEY="YOUR_SUPERAGENT_API_KEY"
$	export OPENAI_COMPATIBLE_API_KEY="$RESPAN_API_KEY"
$	export OPENAI_COMPATIBLE_BASE_URL="https://api.respan.ai/api"
$	export OPENAI_COMPATIBLE_SUPPORTS_STRUCTURED_OUTPUT="true"

1	result = await client.guard(
2	input="Check this message for prompt injection.",
3	model="openai-compatible/gpt-4o-mini",
4	)

1	await client.guard(input=message, model="openai-compatible/gpt-4o-mini")
2	await client.redact(input=message, model="openai-compatible/gpt-4.1-nano")