Skip to main content

​
Overview

CheckThat supports OpenAI’s latest language models including GPT-5, o3, and o4-mini. These models provide state-of-the-art natural language understanding and generation capabilities with support for structured outputs, streaming responses, and conversation history.

​
Available Models

The following OpenAI models are available through CheckThat:
​
gpt-5-2025-08-07
string
GPT-5 - OpenAI’s flagship model with advanced reasoning capabilities
​
gpt-5-nano-2025-08-07
string
GPT-5 nano - Lightweight version optimized for speed and efficiency
​
o3-2025-04-16
string
o3 - Advanced reasoning model optimized for complex problem-solving
​
o4-mini-2025-04-16
string
o4-mini - Compact reasoning model balancing performance and cost

​
Configuration

​
API Key Setup

​
api_key
string
required
Your OpenAI API key. Get your key from OpenAI Platform.
​
model
string
required
The model identifier from the available models list above.

​
Request Parameters

OpenAI models support all standard OpenAI API parameters:
​
messages
array
required
Array of message objects with role and content fields.
[
  {"role": "system", "content": "You are a helpful assistant."},
  {"role": "user", "content": "Hello!"}
]
​
temperature
number
default:"1.0"
Controls randomness in responses. Range: 0.0 to 2.0.
​
max_tokens
integer
Maximum number of tokens to generate in the response.
​
stream
boolean
default:"false"
Enable streaming responses for real-time output.
​
response_format
object
Structured output format specification (JSON schema).

​
Usage Examples

​
Basic Chat Completion

import requests

url = "https://api.checkthat.ai/v1/chat/completions"
headers = {
    "Authorization": "Bearer YOUR_CHECKTHAT_API_KEY",
    "Content-Type": "application/json"
}

payload = {
    "model": "gpt-5-2025-08-07",
    "provider": "openai",
    "openai_api_key": "YOUR_OPENAI_API_KEY",
    "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain quantum computing in simple terms."}
    ]
}

response = requests.post(url, json=payload, headers=headers)
print(response.json())

​
Streaming Response

import requests

url = "https://api.checkthat.ai/v1/chat/completions"
headers = {
    "Authorization": "Bearer YOUR_CHECKTHAT_API_KEY",
    "Content-Type": "application/json"
}

payload = {
    "model": "gpt-5-2025-08-07",
    "provider": "openai",
    "openai_api_key": "YOUR_OPENAI_API_KEY",
    "messages": [
        {"role": "user", "content": "Write a short story about AI."}
    ],
    "stream": True
}

with requests.post(url, json=payload, headers=headers, stream=True) as response:
    for line in response.iter_lines():
        if line:
            print(line.decode('utf-8'))

​
Structured Output

import requests

url = "https://api.checkthat.ai/v1/chat/completions"
headers = {
    "Authorization": "Bearer YOUR_CHECKTHAT_API_KEY",
    "Content-Type": "application/json"
}

schema = {
    "type": "object",
    "properties": {
        "claim": {"type": "string"},
        "confidence": {"type": "number"},
        "evidence": {"type": "array", "items": {"type": "string"}}
    },
    "required": ["claim", "confidence"]
}

payload = {
    "model": "gpt-5-2025-08-07",
    "provider": "openai",
    "openai_api_key": "YOUR_OPENAI_API_KEY",
    "messages": [
        {"role": "user", "content": "Analyze this claim: 'Solar energy is renewable.'"}
    ],
    "response_format": {
        "type": "json_schema",
        "json_schema": {
            "name": "claim_analysis",
            "schema": schema
        }
    }
}

response = requests.post(url, json=payload, headers=headers)
print(response.json())

​
With Conversation History

import requests

url = "https://api.checkthat.ai/v1/chat/completions"
headers = {
    "Authorization": "Bearer YOUR_CHECKTHAT_API_KEY",
    "Content-Type": "application/json"
}

payload = {
    "model": "gpt-5-2025-08-07",
    "provider": "openai",
    "openai_api_key": "YOUR_OPENAI_API_KEY",
    "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the capital of France?"},
        {"role": "assistant", "content": "The capital of France is Paris."},
        {"role": "user", "content": "What is its population?"}
    ]
}

response = requests.post(url, json=payload, headers=headers)
print(response.json())

​
Features and Capabilities

​
Structured Outputs

All OpenAI models in CheckThat support structured outputs using JSON schema. This ensures responses match your specified format exactly. Supported Models:
  • gpt-5-2025-08-07
  • gpt-5-nano-2025-08-07
  • o3-2025-04-16
  • o4-mini-2025-04-16

​
Conversation History

Maintain context across multiple turns by including previous messages in your request. The API automatically formats conversation history for optimal model performance.

​
Streaming

Get real-time responses as they’re generated using streaming mode. Perfect for chat applications and long-form content generation.

​
Implementation Details

CheckThat’s OpenAI integration (openai.py:18-110) provides:
  • Direct parameter pass-through: Send any OpenAI-compatible parameters
  • Response format support: Full JSON schema and structured output support
  • Streaming: Real-time response generation with Stream[ChatCompletionChunk]
  • Legacy methods: Backward-compatible prompt-based methods

​
Rate Limits and Pricing

Rate limits and pricing are determined by your OpenAI API key tier. CheckThat does not impose additional rate limits on OpenAI models. Refer to OpenAI’s pricing page for current rates:
  • GPT-5: Premium tier pricing
  • GPT-5 nano: Optimized pricing for high-volume use
  • o3/o4-mini: Reasoning model pricing

​
Error Handling

The OpenAI integration includes comprehensive error handling: 
try:
    response = requests.post(url, json=payload, headers=headers)
    response.raise_for_status()
    result = response.json()
except requests.exceptions.HTTPError as e:
    print(f"API Error: {e}")
    print(f"Response: {e.response.text}")
except requests.exceptions.RequestException as e:
    print(f"Request failed: {e}")
Common error codes:
  • 401: Invalid API key
  • 429: Rate limit exceeded
  • 500: OpenAI service error

​
Best Practices

  1. Use appropriate models: Choose GPT-5 nano for speed, GPT-5 for quality, o-series for reasoning
  2. Set max_tokens: Prevent runaway costs by limiting response length
  3. Implement retries: Handle transient failures with exponential backoff
  4. Stream for UX: Use streaming for better user experience in chat applications
  5. Cache responses: Reduce API calls by caching common queries

Build docs developers (and LLMs) love

Get started for freeTalk to us