o3

OpenAIopenai/o3
Modality

Reasoning

Family

OpenAI o-series

Context window

200K tokens

Max output

100K tokens

Served On

OpenAI API

o3 is a reasoning model made by OpenAI, served on nRouter. It has a 200K-token context window.

Model pricing

Exact provider list price · 0% platform fee · x-nr-request-cost header

Rates are read live

Pricing for openai/o3 is fetched from the live catalogue on load, so it is never served from a cache that could outlive a repricing.

Start building with openai/o3

One API key, three steps. Choose your tool to begin.

  1. Set your API key

    export NROUTER_API_KEY="<YOUR_API_KEY>"
  2. Configure Claude Code

    Choose a tool, then copy its setup from the panel.

npm install -g @anthropic-ai/claude-code
Claude Code · openai/o3
# Point Claude Code to nRouter gateway
export ANTHROPIC_BASE_URL="https://api.nrouter.ai"
export ANTHROPIC_API_KEY="$NROUTER_API_KEY"

# Launch with openai/o3
claude --model openai/o3

Specifications & capabilities

VisionFunction callingStreamingJSON modeSystem prompt
Compare context window against peer models (200.0K)

Context window, ranked against other reasoning models

Proportional scale: 0 to 200K tokens. Not ranked, no published context window: xai/grok-4.1-fast-non-reasoning, xai/grok-4.1-fast-reasoning, moonshot/kimi-k2-thinking, microsoft/phi-4-reasoning, microsoft/phi-4-mini-reasoning.

Benchmarks & performance rankings

Published LLM Arena category placements and Elo ratings for o3.

LLM Arena category ratings
Overall#148

1410Elo

Coding#175

1407Elo

Math#115

1426Elo

Creative Writing#164

1359Elo

Hard Prompts#171

1402Elo

Instruction Following#179

1368Elo

Multi-Turn#154

1405Elo

Longer Query#190

1371Elo

Non-English#137

1401Elo

Vision#86

1214Elo

Source: huggingface.co · CC-BY-4.0

Provider-Reported Capabilities

What the hosting provider reports for this model, shown as it was returned. nRouter adds nothing to this report and infers nothing that is missing from it.

Area area

US

Agents V2 agentsV2

true

Responses responses

true

Chat Completion chatCompletion

true

Supports vision supports_vision
Supports JSON mode supports_json_mode
Supports responses supports_responses
Supports streaming supports_streaming
Supports function calling supports_function_calling

Availability

Collecting probe samples

Not enough health probe samples collected yet to publish an uptime or latency figure.

More from OpenAI

FAQs

What is o3?

o3 is a reasoning model made by OpenAI, served on nRouter. It has a 200K-token context window.

How much does o3 cost?

o3 is billed at the provider's list price on nRouter with no per-token markup — tokens settle at the exact upstream rate. Input and output rates are read live, so see the pricing section above for the current figures.

What is the context length of o3?

o3 supports a 200,000-token context window. It can generate up to 100,000 output tokens per request.

Does o3 support tool calling and structured outputs?

No. o3 does not support tool calling, so it cannot invoke external tools or functions. It does not support a structured JSON output mode.

What inputs and outputs does o3 support?

o3 takes text as input and returns text as output.

How do I use o3 via nRouter?

Use any OpenAI-compatible client: point it at https://api.nrouter.ai/v1 with your nRouter API key and set the model to "openai/o3". The quick-start panel above has a copy-paste curl command for this model.

Where is the o3 documentation?

Start at nrouter.ai/docs. The quick-start guide (nrouter.ai/docs/getting-started/quick-start) covers API keys and your first request, and the API reference (nrouter.ai/docs/api-reference) lists every parameter.

What other text models does OpenAI have?

Other OpenAI text models on nRouter include Text Embedding 3 Large (nrouter.ai/models/openai-text-embedding-3-large), GPT-6 Sol (nrouter.ai/models/openai-gpt-6-sol), GPT-6 Astra (nrouter.ai/models/openai-gpt-6-astra), GPT-5.6 Luna (nrouter.ai/models/openai-gpt-5.6-luna).