OpenAI: GPT-5.1
GPT-5.1 is a paid multimodal model from OpenAI that accepts text, images, and files as input. It supports a 400,000-token context window and can return up to 128,000 tokens per response, making it suited for long-document work. Tool use and reasoning are both enabled, though structured output support is not confirmed in available specifications. At $1.25 per million input tokens and $10.00 per million output tokens, the output cost is notably high relative to competing models at similar capability tiers. Its blended benchmark score of 64.3 comes from a single benchmark, so that figure should be treated as preliminary rather than a settled measure of performance. Teams with heavy file-processing or long-context needs have reason to shortlist it, but cost-sensitive users running high output volumes should model their expected spend carefully before committing.
- Model ID
- openai/gpt-5.1
- Vendor
- openai
- Tokenizer
- GPT
- Input Modalities
- image, text, file
- Output Modalities
- text
- Max Output
- 128,000 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no