Text Series
General Chat API (Default Streaming)
- Unified chat API interface supporting all text generation models
- Select different AI models via the model parameter
- Compatible with OpenAI Chat Completions API format
POST
Documentation Index
Fetch the complete documentation index at: https://gccai.heqingsong.uk/llms.txt
Use this file to discover all available pages before exploring further.
Authorizations
All API endpoints require Bearer Token authenticationGet your API Key:Visit the API Key Management Page to get your API KeyAdd it to the request header:
Body
Model nameSupported models include:
- OpenAI:
gpt-5,gpt-5-chat-latest,gpt-5-mini,gpt-5-nano,gpt-5-pro - Anthropic:
claude-sonnet-4-5-20250929,claude-opus-4-1-20250805,claude-haiku-4-5-20251001,claude-opus-4-1-20250805-thinking,claude-sonnet-4-5-20250929-thinking - Google:
gemini-2.5-pro,gemini-2.5-flash,gemini-2.5-pro-thinking,gemini-2.5-flash-lite - DeepSeek:
deepseek-v3.1-250821,deepseek-v3.1-think-250821,deepseek-v3-0324 - Doubao:
doubao-seed-1-6-251015,doubao-seed-1-6-flash-250828,doubao-seed-1-6-thinking-250715 - More models being added continuously…
List of conversation messagesMessage array. Each message contains Advanced usage:Add system prompt (to define AI behavior):Multi-turn conversation (with context):Role descriptions:
role and content fields.💡 Quick fill (Try it area):- Click ”+ Add an item” to add a message
- Enter
user(user message),assistant(AI response), orsystem(system prompt) forrole - Enter what you want to say in
content
user: User message (use this most of the time)system: System prompt to set AI behavior and roleassistant: AI’s previous responses, used for conversation context
Controls output randomness, range 0-2
- Lower values (e.g., 0.2) make output more deterministic
- Higher values (e.g., 1.8) make output more random
Maximum number of tokens to generateDifferent models have different maximum limits, please refer to specific model documentation
Whether to use streaming output
true: Streaming response (SSE format)false: Complete response at once
Nucleus sampling parameter, range 0-1Controls diversity of generated text, recommend using either this or temperatureDefault: 1.0
Frequency penalty, range -2.0 to 2.0Positive values reduce the likelihood of repeating the same wordsDefault: 0
Presence penalty, range -2.0 to 2.0Positive values increase the likelihood of talking about new topicsDefault: 0
Stop sequencesUp to 4 sequences where generation will stop when encountered
Number of completions to generateDefault: 1⚠️ Note: Must enter a plain number (e.g.,
1), do not use quotes or it will cause an errorResponse
Unique identifier for the response
Object type, fixed as
chat.completionCreation timestamp
The actual model name used
List of generated responses
Token usage statistics
Supported Models
OpenAI Series
gpt-5- GPT-5 base modelgpt-5-chat-latest- GPT-5 latest chat versiongpt-5-mini- GPT-5 lightweight version, cost-effectivegpt-5-nano- GPT-5 ultra-lightweight versiongpt-5-pro- GPT-5 professional enhanced version
Anthropic Series
claude-haiku-4-5-20251001- Claude 4.5 fast response versionclaude-sonnet-4-5-20250929- Claude 4.5 balanced versionclaude-opus-4-1-20250805- Most powerful Claude 4.1 flagship modelclaude-opus-4-1-20250805-thinking- Claude 4.1 Opus deep thinking versionclaude-sonnet-4-5-20250929-thinking- Claude 4.5 Sonnet deep thinking version
Google Series
gemini-2.5-flash- Gemini 2.5 fast versiongemini-2.5-pro- Gemini 2.5 professional versiongemini-2.5-flash-lite- Gemini 2.5 ultra-lightweight versiongemini-2.5-pro-thinking- Gemini 2.5 Pro deep thinking version
DeepSeek Series
deepseek-v3.1-250821- DeepSeek V3.1 base versiondeepseek-v3.1-think-250821- DeepSeek V3.1 thinking versiondeepseek-v3-0324- DeepSeek V3 standard version
Doubao Series
doubao-seed-1-6-flash-250828- Doubao Seed 1.6 fast versiondoubao-seed-1-6-thinking-250715- Doubao Seed 1.6 thinking versiondoubao-seed-1-6-251015- Doubao Seed 1.6 standard version