GPT-4o (2024-08-06)

OpenAIMCP Tool Call
openai/gpt-4o-2024-08-06Closed API

GPT model for general reasoning, writing, coding, and tool-assisted tasks

Benchmark Pricing$2.50 / 1M in$10.00 / 1M out$1.25 cache read
Context: 128,000 tokens•Max Output: 16,384 tokens•Knowledge: 2023-09•Released: 2024-08-06

TECHNICAL SPECIFICATIONS

Context Window128,000128K tokens
Max Output16,38416.4K tokens
LicenseProprietaryCloud API only
Input Modalities
TextVision
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ GPT-4o (2024-08-06) 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 128,000 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

STANDARDIZED BENCHMARKS & EVALS

Aider Polyglotpercent correct
23.1
Artificial Analysis Coding Indexindex
16.6
SciCodepercent correct
33.1
Terminal-Bench Hardsuccess rate
8.3

API CALL INVOCATION EXAMPLE

// Example: Calling GPT-4o (2024-08-06) 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/gpt-4o-2024-08-06",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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

PRICING BY PROVIDER

8 providers
OpenAIgpt-4o-2024-08-06
$2.50 / $10.00$1.25 cache
NanoGPTopenai/gpt-4o-2024-08-06
$2.50 / $10.00$1.25 cache
AI/ML APIopenai/gpt-4o-2024-08-06
$3.25 / $13.00$1.63 cache
Eden AIopenai/gpt-4o-2024-08-06
$2.50 / $10.00$1.25 cache
Merge Gatewayopenai/gpt-4o-2024-08-06
$2.50 / $10.00$1.25 cache
Kilo Gatewayopenai/gpt-4o-2024-08-06
$2.50 / $10.00$1.25 cache
OpenRouteropenai/gpt-4o-2024-08-06
$2.50 / $10.00$1.25 cache
OrcaRouteropenai/gpt-4o-2024-08-06
$2.50 / $10.00$1.25 cache

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

Prompt Caching Active

This model supports prompt caching at $1.25 / 1M tokens, saving up to 50% on repetitive MCP tool definitions and system instructions.

MODEL RESOURCES