GPT-4

OpenAIMCP Tool Call
openai/gpt-4Closed API

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

Benchmark Pricing$30.00 / 1M in$60.00 / 1M out
Context: 8,192 tokens•Max Output: 8,192 tokens•Knowledge: 2023-11•Released: 2023-11-06

TECHNICAL SPECIFICATIONS

Context Window8,1928.2K tokens
Max Output8,1928.2K tokens
LicenseProprietaryCloud API only
Input Modalities
Text
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ GPT-4 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 8,192 tokens, this model can handle compact tool sets. Consider keeping MCP server tool manifests minimal to preserve headroom.

STANDARDIZED BENCHMARKS & EVALS

Artificial Analysis Coding Indexindex
13.1

API CALL INVOCATION EXAMPLE

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

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

PRICING BY PROVIDER

15 providers
OpenAIgpt-4
$30.00 / $60.00
Cortecsgpt-4o
$2.66 / $10.63$1.33 cache
NanoGPTopenai/gpt-4o
$2.50 / $10.00$1.25 cache
SAP AI Coregpt-4.1
$2.00 / $8.00$0.50 cache
CrossModelopenai/gpt-4o-mini
$0.15 / $0.60$0.07 cache
Snowflake Cortexopenai-gpt-4.1
$2.00 / $8.00$0.50 cache
302.AIgpt-4o
$2.50 / $10.00
LLM Gatewayopenai/gpt-4o
$2.50 / $10.00$1.25 cache
Poeopenai/gpt-4-classic
$27.00 / $54.00
AI/ML APIopenai/gpt-4o
$3.25 / $13.00$1.63 cache
Cloudflare AI Gatewayopenai/gpt-4o
$1.25 / $5.00$0.63 cache
Venice AIopenai-gpt-4o-mini-2024-07-18
$0.15 / $0.60$0.07 cache
Abacusgpt-4o
$2.50 / $10.00$1.25 cache
Vercel AI Gatewayopenai/gpt-4o-mini-transcribe
$1.25 / $5.00
Eden AIopenai/gpt-4o
$2.50 / $10.00$1.25 cache

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

MODEL RESOURCES