Powerful AI models accessible through a simple REST API. Build intelligent applications with our comprehensive suite of language models.
The RapidTextAI API provides access to state-of-the-art language models for text generation, completion, and article creation. Our API is designed to be simple, reliable, and powerful.
Get started with your first API call in under 5 minutes:
All API requests require authentication using your API key. Include your key as a query parameter:
Generate human-like text completions using our advanced language models.
https://app.rapidtextai.com/openai/completion
Parameter | Type | Required | Description |
---|---|---|---|
model |
string | Yes | ID of the model to use |
messages |
array | Yes | List of messages comprising the conversation |
max_tokens |
integer | No | Maximum number of tokens to generate (default: 2048) |
temperature |
number | No | Sampling temperature between 0 and 2 (default: 1) |
top_p |
number | No | Nucleus sampling parameter (default: 1) |
frequency_penalty |
number | No | Penalty for new tokens based on frequency (-2.0 to 2.0) |
presence_penalty |
number | No | Penalty for new tokens based on presence (-2.0 to 2.0) |
Generate comprehensive articles with structured content and optional image integration.
https://app.rapidtextai.com/openai/v1/chat/completionsarticle
Parameter | Type | Required | Description |
---|---|---|---|
model |
string | Yes | ID of the model to use |
messages |
array | Yes | Array containing topic, keywords, tone, audience, and style |
tools |
array | No | Tool configurations for features like image generation |
tool_choice |
string | No | Tool selection mode: "auto" or "none" |
dataType |
string | Yes | Must be set to "article" |
Choose from our selection of cutting-edge language models, each optimized for different use cases.
Model ID | Model Name | Context Length | Access Level | Best For |
---|---|---|---|---|
gemini-2.0-flash |
Gemini 2.0 Flash | 1M tokens | Standard | Fast responses, general tasks |
gpt-4o-mini |
GPT-4o Mini | 128K tokens | Standard | Cost-effective, quick tasks |
gpt-4 |
GPT-4 | 128K tokens | Standard | Complex reasoning, analysis |
deepseek-chat |
DeepSeek V3 | 64K tokens | Standard | Coding, technical content |
gpt-4o |
GPT-4o | 128K tokens | Pro Only | Advanced reasoning, multimodal |
grok-2 |
Grok-2 | 128K tokens | Pro Only | Real-time information, humor |
gemini-1.5-pro |
Gemini 1.5 Pro | 2M tokens | Pro Only | Long documents, analysis |
gemini-2.0-pro |
Gemini 2.0 Pro | 2M tokens | Pro Only | Advanced multimodal tasks |
deepseek-reasoner |
DeepSeek R1 | 64K tokens | Pro Only | Mathematical reasoning, logic |
Simple, transparent pricing based on your usage needs.
Operation | Cost | Description |
---|---|---|
API Request | 1 prompt | Single completion request |
Article Generation | 10 prompts | Full article with structure |
Image Generation | 50 prompts | AI-generated image |
To ensure fair usage and optimal performance, we implement the following rate limits:
Account Type | Requests per Minute | Requests per Day | Concurrent Requests |
---|---|---|---|
Free | 3 | 100 | 1 |
Basic | 60 | 10,000 | 5 |
Premium | 180 | 30,000 | 10 |