o3 - Oxen.ai

Try o3 in the Workbench

Run this model interactively, tune parameters, and compare outputs.

Model ID: o3-2025-04-16 o3 is an LLM that excels in advanced reasoning, coding, mathematics, science, and visual perception tasks. It is OpenAI’s most powerful reasoning model to date and is notable for its ability to integrate web browsing and image understanding directly into its problem-solving process. Some other noteworthy features of o3 include agentic tool use—allowing it to chain together multiple tool calls (such as searching the web, running code, generating graphs or images) within a single task—and support for up-to-date information retrieval beyond its built-in knowledge. o3 can also interact with custom tools via function calling in the API and demonstrates strong performance on complex benchmarks across coding, science questions, software engineering tasks, and abstract reasoning.

Metric	Value
Parameter Count	Unknown
Mixture of Experts	Unknown
Context Length	Unknown
Multilingual	Yes
Quantized*	Unknown

*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.

Example request

Use the Workbench as a request builder: configure parameters for this model in the UI, then open the API tab to copy the exact cURL or Python call.

Minimal
Basic parameters
All parameters

curl -X POST https://hub.oxen.ai/api/ai/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "o3-2025-04-16",
  "messages": [
    {
      "role": "user",
      "content": "Hello, what can you do?"
    }
  ]
}'

curl -X POST https://hub.oxen.ai/api/ai/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "o3-2025-04-16",
  "messages": [
    {
      "role": "user",
      "content": "Hello, what can you do?"
    }
  ],
  "temperature": 0.7,
  "max_tokens": 1024,
  "stream": false
}'

curl -X POST https://hub.oxen.ai/api/ai/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "o3-2025-04-16",
  "messages": [
    {
      "role": "user",
      "content": "Hello, what can you do?"
    }
  ],
  "temperature": 0.7,
  "max_tokens": 1024,
  "stream": false,
  "top_p": 1.0,
  "frequency_penalty": 0,
  "presence_penalty": 0
}'

Fetch model details

The models endpoint returns the full model object, including its json_request_schema.

curl -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/ai/models/o3-2025-04-16

Request parameters

This model follows the standard OpenAI chat completions request body. See the chat completions reference for the full parameter list.

Inference API

Try o3 in the Workbench

​Example request

​Fetch model details

​Request parameters

Example request

Fetch model details

Request parameters