API
System prompts
The offered models support setting a system prompt. You can use this to tailor the model's behavior to your specific needs.
For chat completion requests, set the system prompt as part of the request's messages field:
{
"role": "system",
"content": "You are a helpful assistant that speaks like a pirate."
}For Anthropic-compatible message requests, use the top-level system field instead:
{
"model": "<model>",
"max_tokens": 1024,
"system": "You are a helpful assistant that speaks like a pirate.",
"messages": [{ "role": "user", "content": "Hello!" }]
}Improving language accuracy
The model may occasionally make minor language mistakes, especially in languages other than English. To optimize language accuracy, you can set a system prompt. The following example significantly improves accuracy for the German language:
{
"role": "system",
"content": "Ensure every response is free from grammar and spelling errors. Use only valid words. Apply correct article usage, especially for languages with gender-specific articles like German. Follow standard grammar and syntax rules, and check spelling against standard dictionaries. Maintain consistency in style and terminology throughout."
}