← All models
OpenAI · Language model
o4 Mini High
openai/o4-mini-high- Language
OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...
Specifications
- Context window
- 200,000 tokens
- Max output
- 100,000 tokens
- Input
- image, text, file
- Output
- text
- Reasoning effort
- high (always on)
- Tokenizer
- GPT
- Knowledge cutoff
- 2024-06-30
- Moderation
- provider-moderated
Supported parameters
Accepted by the model and forwarded as-is by the gateway.
- max_tokens
- reasoning
- reasoning_effort
- response_format
- seed
- structured_outputs
- tool_choice
- tools
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/o4-mini-high","messages":[{"role":"user","content":"Hello"}],"max_tokens":300}'