← All models
OpenAI · Language model
GPT-4
openai/gpt-4- Language
OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...
Specifications
- Context window
- 8,191 tokens
- Max output
- 4,096 tokens
- Input
- text
- Output
- text
- Tokenizer
- GPT
- Knowledge cutoff
- 2021-09-30
Supported parameters
Accepted by the model and forwarded as-is by the gateway.
- frequency_penalty
- logit_bias
- logprobs
- max_completion_tokens
- max_tokens
- presence_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_logprobs
- top_p
Use it
POST /api/v1/chat/completions · MCP chat · full reference
curl https://omnirail.org/api/v1/chat/completions \
-H "Authorization: Bearer $OMNIRAIL_KEY" -H "Content-Type: application/json" \
-d '{"model":"openai/gpt-4","messages":[{"role":"user","content":"Hello"}],"max_tokens":300}'