$
Call AntSeed with curl or raw HTTP
Hit the proxy with plain HTTP - useful for scripts and debugging.
Raw HTTPMulti-format~1 min
The buyer proxy is a vanilla HTTP server. Anything that can issue an HTTP POST works. Three endpoints are exposed:
• POST /v1/messages - Anthropic Messages format
• POST /v1/chat/completions - OpenAI Chat Completions
• POST /v1/responses - OpenAI Responses API
Run AntSeed first
Every integration assumes a buyer proxy at http://localhost:8377. One-time setup, ~2 minutes.
Step 1
Point curl / raw HTTP at AntSeed
# Anthropic format
curl http://localhost:8377/v1/messages \
-H 'content-type: application/json' \
-d '{
"model": "kimi-k2.6",
"max_tokens": 1024,
"messages": [{"role": "user", "content": "Hello"}]
}'
# OpenAI Chat format
curl http://localhost:8377/v1/chat/completions \
-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 http://localhost:8377/v1/chat/completions \
-H 'content-type: application/json' \
-d '{
"model": "<peerId>@deepseek-v4-flash",
"messages": [{"role": "user", "content": "Hello"}]
}'
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 Messagesserviceprotocolsincludesanthropic-messages/v1/chat/completionsOpenAI Chat Completionsserviceprotocolsincludesopenai-chat-completions/v1/responsesOpenAI Responsesserviceprotocolsincludesopenai-responses