Call Antseed with curl or raw HTTP

Call your gateway with plain HTTP - useful for scripts and debugging.

Raw HTTPMulti-format~1 min

Your gateway and the local buyer proxy are plain HTTP servers. Anything that can issue an HTTP POST works. The model endpoints are:

• POST /v1/messages - Anthropic Messages format • POST /v1/chat/completions - OpenAI Chat Completions • POST /v1/responses - OpenAI Responses API

A gateway needs its key as Authorization: Bearer. The local buyer proxy needs no key, but only answers on the same computer.

Run Antseed first

Every integration needs an Antseed endpoint: a gateway, best on a small server so every tool on every machine can reach it, or the local buyer proxy (same computer only). One-time setup, a few minutes.

Step 1

Point curl / raw HTTP at Antseed

Recommended: a gateway

ANTSEED_BASE_URL	https://gateway.example.com/v1
ANTSEED_API_KEY	antseed_…

Show as shell exports

export ANTSEED_BASE_URL="https://gateway.example.com/v1" export ANTSEED_API_KEY="antseed_…"

Your gateway's base URL, ending in /v1, and an API key from the Keys page of its console. Recommended: a gateway on a server, which every machine can reach. A gateway on this computer is http://localhost:8379/v1; publish it with a tunnel (antseed tunnel start) for other machines. No gateway yet: see Run Antseed first above.

# Anthropic format curl "$ANTSEED_BASE_URL/messages" \ -H "Authorization: Bearer $ANTSEED_API_KEY" \ -H 'content-type: application/json' \ -d '{ "model": "deepseek-v4-flash", "max_tokens": 1024, "messages": [{"role": "user", "content": "Hello"}] }' # OpenAI Chat format curl "$ANTSEED_BASE_URL/chat/completions" \ -H "Authorization: Bearer $ANTSEED_API_KEY" \ -H 'content-type: application/json' \ -d '{ "model": "deepseek-v4-flash", "messages": [{"role": "user", "content": "Hello"}] }' # Route to a specific peer: prefix the model with "<peerId>@" curl "$ANTSEED_BASE_URL/chat/completions" \ -H "Authorization: Bearer $ANTSEED_API_KEY" \ -H 'content-type: application/json' \ -d '{ "model": "<peerId>@deepseek-v4-flash", "messages": [{"role": "user", "content": "Hello"}] }'

Same computer, no gateway: the local buyer proxy

curl http://localhost:8377/v1/chat/completions \ -H 'content-type: application/json' \ -d '{ "model": "deepseek-v4-flash", "messages": [{"role": "user", "content": "Hello"}] }' # Follow the model currently selected in the desktop app: curl http://localhost:8377/v1/chat/completions \ -H 'content-type: application/json' \ -d '{ "model": "antseed", "messages": [{"role": "user", "content": "Hello"}] }'

No key needed. The model antseed follows the desktop app's picker and only works here, not through a gateway.

Wire format • multi-protocol

curl / raw HTTP can send any of Antseed's supported protocols - configure per call. Antseed will match each request to the peer's advertised service protocols (see providerServiceApiProtocols on a peer) and translate when they don't match.

/v1/messagesAnthropic Messagesservice protocols includes anthropic-messages
/v1/chat/completionsOpenAI Chat Completionsservice protocols includes openai-chat-completions
/v1/responsesOpenAI Responsesservice protocols includes openai-responses

Point curl / raw HTTP at Antseed

Run curl / raw HTTP on the open market