Conversation and image input
Combine text and images in requests for question answering and content understanding.
← Back to product updates
GPT-6 · Multimodal model
Bring text and images into the conversation.
Use conversation, image input, and reasoning in one model. Access GPT-6 Astra through the platform API to build AI experiences for your product.
Capabilities
Understand input. Reason. Return results.
Reasoning
Provide context for tasks that require analysis, then let the model work through the question and respond.
Structured output
Organize results in the structure your application needs for further processing.
Start integrating
Use the platform model ID gpt-6-astra. Create an API key, check capabilities and pricing in model details, and follow the text generation docs.