Back to Models

o3

openaiopenai/o3

API guide

Chat completion

Standard OpenAI-compatible chat. o3 is available via /v1/chat/completions on TheRouter β€” same endpoint, same SDK as gpt-4o or gpt-5.

cURL
curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/o3",
    "messages": [
      {"role": "user", "content": "Prove that the sum of two odd numbers is even."}
    ]
  }'

Reasoning effort control

o3 supports reasoning_effort = low | medium | high. Higher effort = deeper chains and more reasoning tokens (which you are billed for as output). Default is medium.

cURL
curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/o3",
    "reasoning_effort": "high",
    "messages": [
      {"role": "user", "content": "Walk through the failure modes of a 2-of-3 Raft cluster losing a leader."}
    ]
  }'

Vision input

o3 accepts text + image inputs. Pass image_url parts in the user message β€” same shape as gpt-4o multimodal calls. Output is text only.

cURL
curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/o3",
    "messages": [
      {"role": "user", "content": [
        {"type": "text", "text": "What is wrong with this architecture diagram?"},
        {"type": "image_url", "image_url": {"url": "https://therouter.ai/assets/vision-sample.png"}}
      ]}
    ]
  }'

Function calling / tools

o3 supports OpenAI-style function calling and structured outputs. Per OpenAI's reasoning best-practices, prefer fewer, well-described tools over long flat tool lists.

cURL
curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/o3",
    "messages": [{"role": "user", "content": "What is the weather in Tokyo right now?"}],
    "tools": [
      {
        "type": "function",
        "function": {
          "name": "get_weather",
          "description": "Get the current weather for a city.",
          "parameters": {
            "type": "object",
            "properties": {"city": {"type": "string"}},
            "required": ["city"]
          }
        }
      }
    ]
  }'
Fact ledger β€” every claim on this page traces here
sourceURLretrieved
Release dateopenai.com β†—2026-05-31verified
Snapshotdevelopers.openai.com β†—2026-05-31verified
Knowledge cutoffdevelopers.openai.com β†—2026-05-31verified
Context windowdevelopers.openai.com β†—2026-05-31verified
Max output tokensdevelopers.openai.com β†—2026-05-31verified
Reasoning tokensdevelopers.openai.com β†—2026-05-31verified
Statusdevelopers.openai.com/deprecations β†—2026-05-31verified
Codeforcesopenai.com β†—2026-05-31verified
SWE-bench Verifiedopenai.com β†—2026-05-31verified
AIME 2024openai.com β†—2026-05-31verified
AIME 2025openai.com β†—2026-05-31verified
GPQA Diamonddatacamp.com β†—2026-05-31to verify
MMMUopenai.com β†—2026-05-31to verify
o3-pro available to API and ChatGPT ProOpenAI Help Center β†—2026-05-31verified
OpenAI o3 and o4-mini launchopenai.com β†—2026-05-31verified
Is o3 deprecated yet?developers.openai.com β†—2026-05-31to verify
What is o3's context window and max output?developers.openai.com β†—2026-05-31to verify
Does o3 accept image input?developers.openai.com β†—2026-05-31to verify
How does o3 compare to GPT-5 on price?developers.openai.com β†—2026-05-31to verify
Help & contact