o3

OpenAIMCP Tool CallReasoning
openai/o3Closed API

Deliberate o-series reasoner for hard math, coding, and multi-step analysis

Benchmark Pricing$2.00 / 1M in$8.00 / 1M out$0.50 cache read
Context: 200,000 tokens•Max Output: 100,000 tokens•Knowledge: 2024-05•Released: 2025-04-16

TECHNICAL SPECIFICATIONS

Context Window200,000200K tokens
Max Output100,000100K tokens
LicenseProprietaryCloud API only
Input Modalities
TextVisionPDF
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ o3 natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 200,000 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

STANDARDIZED BENCHMARKS & EVALS

Aider Polyglotpercent correct
81.3

API CALL INVOCATION EXAMPLE

// Example: Calling o3 via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY,
});

const response = await client.chat.completions.create({
  model: "openai/o3",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);

PRICING BY PROVIDER

15 providers
OpenAIo3
$2.00 / $8.00$0.50 cache
NanoGPTholo3-35b-a3b
$0.25 / $1.80$0.13 cache
Upstagesolar-pro3
$0.25 / $0.25
302.AIo3
$2.00 / $8.00
LLM Gatewayopenai/o3-mini
$1.10 / $4.40$0.55 cache
Poeopenai/o3-mini-high
$0.99 / $4.00
AI/ML APIopenai/o3-mini
$1.43 / $5.72$0.71 cache
LLMTRupstage/solar-pro3
$0.15 / $0.60$0.01 cache
Cloudflare AI Gatewayopenai/o3-mini
$1.10 / $4.40$0.55 cache
AIHubMixo3
$2.00 / $8.00$0.50 cache
Abacuso3-mini
$1.10 / $4.40$0.55 cache
Vercel AI Gatewayopenai/o3-pro
$20.00 / $80.00
Eden AIopenai/o3-mini
$1.10 / $4.40$0.55 cache
NEAR AI Cloudopenai/o3-mini
$1.10 / $4.40$0.55 cache
Merge Gatewayopenai/o3-mini
$1.10 / $4.40$0.55 cache

Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.

Prompt Caching Active

This model supports prompt caching at $0.50 / 1M tokens, saving up to 75% on repetitive MCP tool definitions and system instructions.

MODEL RESOURCES