Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.openserv.ai/llms.txt

Use this file to discover all available pages before exploring further.

POST https://inference-api.openserv.ai/v1/messages
Anthropic Messages format. Accepts Claude and most other models in the catalog — see endpoint compatibility.

​
Request

​
Authorization
string
required
Bearer $SERV_API_KEY.
​
model
string
required
Model ID from the catalog, for example claude-haiku-4.5.
​
max_tokens
integer
required
Maximum number of tokens to generate. Required by the Messages format.
​
system
string
required
The system prompt. SERV requires one.
​
messages
array
required
The conversation so far. Each entry has a role (user or assistant) and content.
​
thinking
object
Extended thinking controls, for example { "type": "enabled", "budget_tokens": 1024 }.
​
tools
array
Tool definitions, in Anthropic format: { name, input_schema }.
​
tool_choice
string | object
"auto", "any", or { "type": "tool", "name": "..." }.
​
stop_sequences
array
Sequences that stop generation.
​
stream
boolean
default:"false"
Stream the response as server-sent events.
All other Anthropic Messages parameters are accepted and forwarded to the model.

​
Response

​
id
string
Unique identifier for the message.
​
type
string
Always "message".
​
role
string
Always "assistant".
​
model
string
The model used.
​
content
array
Output blocks. Find the block with type: "text" for the generated text.
​
stop_reason
string
Why generation ended. Common values: end_turn, max_tokens, stop_sequence, tool_use.
​
usage
object
Token counts: input_tokens, output_tokens.
curl https://inference-api.openserv.ai/v1/messages \
  -H "Authorization: Bearer $SERV_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-haiku-4.5",
    "max_tokens": 1024,
    "system": "You answer in one sentence.",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

{
  "id": "msg_...",
  "type": "message",
  "role": "assistant",
  "model": "claude-haiku-4.5",
  "content": [{ "type": "text", "text": "Hello! How can I help?" }],
  "stop_reason": "end_turn",
  "usage": { "input_tokens": 16, "output_tokens": 7 }
}