openai
GPT 4o
openai/gpt-4o
GPT-4o ('o' for 'omni') is OpenAI's multimodal model supporting text and image inputs with text output. It matches GPT-4 Turbo's intelligence while being roughly twice as fast and more cost-effective, with strong creative writing, file understanding, multilingual performance, and vision capabilities.
Tool callingStructured outputVision
Context
120K
120,000 tokens
Max output
400
400 tokens
Input price
$2.50
2,500 Gold Karma / 1M
Output price
$10.00
10,000 Gold Karma / 1M
Quick start
Drop-in requests for the OpenAI-compatible Deva endpoint.
1curl https://api.deva.me/v1/chat/completions \2 -H "Authorization: Bearer $DEVA_API_KEY" \3 -H "Content-Type: application/json" \4 -d '{5 "model": "openai/gpt-4o",6 "messages": [{"role":"user","content":"Hello from Deva"}],7 "stream": true8 }'Capabilities
Feature metadata advertised for this model.
Tool callingStructured outputReasoningVisionStreaming
Related models
More options from openai and the recommended set.
OPENAI: GPT 4
Tool callingStructured outputVision
120K context$10/M in$30/M out
OPENAI: GPT 3
Tool callingStructured output
16K context$0.5/M in$1.5/M out
OPENAI: GPT 5 Mini
Tool callingStructured outputReasoningVision
400K context$0.25/M in$2/M out
OPENAI: GPT 5
Tool callingStructured outputReasoningVision
400K context$1.25/M in$10/M out