Skip to main content

Documentation Index

Fetch the complete documentation index at: https://doc.hitopen.com/llms.txt

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

Send a conversation history and receive a model-generated reply. The endpoint is compatible with the OpenAI Chat Completions API, so any existing OpenAI SDK or client works without modification.

​
Endpoint

POST https://YOUR_NEWAPI_BASE_URL/v1/chat/completions

​
Request parameters

​
model
string
required
The model ID to use, for example gpt-4o or claude-3-5-sonnet-20241022. The available values depend on the channels your admin has configured.
​
messages
object[]
required
The conversation history as an ordered list of messages. Each message must have a role (system, user, assistant, or tool) and a content field.
​
temperature
number
default:"1"
Sampling temperature between 0 and 2. Lower values make responses more deterministic; higher values make them more varied.
​
top_p
number
default:"1"
Nucleus sampling parameter between 0 and 1. An alternative to temperature — only the tokens comprising the top probability mass are considered.
​
n
integer
default:"1"
Number of completion choices to generate. Must be 1 or greater.
​
stream
boolean
default:"false"
When true, the response is streamed as Server-Sent Events (SSE). Each chunk is a data: line containing a partial JSON delta, ending with data: [DONE].
​
stream_options
object
Options for streaming responses. Set include_usage: true to include a final chunk with token usage statistics.
​
max_tokens
integer
Maximum number of tokens to generate in the response.
​
max_completion_tokens
integer
Alternative to max_tokens. Sets the maximum number of tokens allowed in the completion, including reasoning tokens for models that support them.
​
stop
string | string[]
One or more sequences where generation stops. The model will stop before producing any of the specified sequences.
​
presence_penalty
number
default:"0"
Penalizes new tokens based on whether they have appeared in the text so far. Valid range: -2.0 to 2.0.
​
frequency_penalty
number
default:"0"
Penalizes new tokens based on their frequency in the text so far. Valid range: -2.0 to 2.0.
​
tools
object[]
A list of tools (functions) the model may call. Each tool must include a type of function and a function object with name, description, and parameters.
​
tool_choice
string | object
Controls how the model selects tools. Pass "none" to disable tool calls, "auto" to let the model decide, or an object specifying a particular function to call.
​
response_format
object
Constrains the output format. Set { "type": "json_object" } to enforce JSON output, or { "type": "text" } for plain text.
​
seed
integer
If specified, the system will attempt to sample deterministically so that repeated requests with the same seed and parameters return the same result.
​
reasoning_effort
string
Controls the depth of reasoning for models that support extended thinking. Accepted values: "low", "medium", "high".
​
logit_bias
object
Modify the likelihood of specific tokens appearing in the output. Maps token IDs (as strings) to bias values from -100 to 100.
​
user
string
An optional identifier for the end user. Useful for abuse detection and monitoring.
​
modalities
string[]
Output modalities to request. Supported values include "text" and "audio".
​
audio
object
Audio output configuration when modalities includes "audio". Specify voice and format.

​
Response fields

​
id
string
Unique identifier for the completion.
​
object
string
Always "chat.completion" for non-streaming responses.
​
created
integer
Unix timestamp (seconds) when the completion was created.
​
model
string
The model that generated the response.
​
choices
object[]
​
usage
object
​
system_fingerprint
string
An opaque string representing the system configuration that served the request.

​
Examples

curl -X POST "https://YOUR_NEWAPI_BASE_URL/v1/chat/completions" \
  -H "Authorization: Bearer sk-your-token" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      { "role": "system", "content": "You are a helpful assistant." },
      { "role": "user", "content": "What is the capital of France?" }
    ]
  }'

​
Streaming example

Set stream: true to receive incremental tokens as SSE events. The stream ends with a data: [DONE] sentinel.
cURL (streaming)
curl -X POST "https://YOUR_NEWAPI_BASE_URL/v1/chat/completions" \
  -H "Authorization: Bearer sk-your-token" \
  -H "Content-Type: application/json" \
  --no-buffer \
  -d '{
    "model": "gpt-4o",
    "stream": true,
    "messages": [
      { "role": "user", "content": "Tell me a short story." }
    ]
  }'
Each streamed chunk looks like: 
data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1715000000,"model":"gpt-4o","choices":[{"index":0,"delta":{"content":"Once"},"finish_reason":null}]}
The final chunk contains "finish_reason": "stop" and delta: {}, followed by data: [DONE].

​
Additional chat formats

Newapi also supports Gemini’s native API format at /v1beta/models/{model}:generateContent. Pass your Newapi token as a Bearer token in the Authorization header. This is useful if you are migrating from the Gemini SDK without changing request shapes.
The Anthropic Claude Messages format is available at POST /v1/messages. Include the anthropic-version: 2023-06-01 header alongside your Bearer token. See your admin for model name mappings. The OpenAI Responses API format is also supported at POST /v1/responses, which provides multi-turn conversation state management through previous_response_id.