GPT-5

OpenAIMCP Tool CallReasoning
openai/gpt-5Closed API

Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows

Benchmark Pricing$1.25 / 1M in$10.00 / 1M out$0.13 cache read
Context: 400,000 tokens•Max Output: 128,000 tokens•Knowledge: 2024-09-30•Released: 2025-08-07

TECHNICAL SPECIFICATIONS

Context Window400,000400K tokens
Max Output128,000128K tokens
LicenseProprietaryCloud API only
Input Modalities
TextVision
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ GPT-5 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 400,000 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

STANDARDIZED BENCHMARKS & EVALS

Aider Polyglotpercent correct
88
SWE-Bench Proresolve rate
41.78

API CALL INVOCATION EXAMPLE

// Example: Calling GPT-5 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-5",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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

PRICING BY PROVIDER

15 providers
OpenAIgpt-5
$1.25 / $10.00$0.13 cache
Cortecsgpt-5.6-sol
$4.40 / $22.00$0.44 cache
QiHanggpt-5-mini
$0.04 / $0.29
NanoGPTopenai/gpt-5.6-sol
$2.00 / $10.00$0.20 cache
SAP AI Coregpt-5.6-sol
$4.00 / $20.00$0.40 cache
OpenCode Gogpt-5.6-luna
$0.20 / $1.20$0.02 cache
GitHub Copilotgpt-5.6-sol
$4.00 / $20.00$0.40 cache
CrossModelopenai/gpt-5.6-sol
$4.00 / $20.00$0.40 cache
Snowflake Cortexopenai-gpt-5.6-sol
$4.00 / $20.00$0.40 cache
302.AIgpt-5.6-sol
$5.00 / $30.00$0.50 cache
Vivgridgpt-5.6-sol
$5.00 / $30.00$0.50 cache
LLM Gatewayopenai/gpt-5.6-sol
$4.00 / $20.00$0.40 cache
Poeopenai/gpt-5.4-pro
$27.27 / $163.64
HPC-AIopenai/gpt-5.5
$5.00 / $30.00$0.50 cache
AI/ML APIopenai/gpt-5.6-sol
$5.20 / $26.00$0.52 cache

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

Prompt Caching Active

This model supports prompt caching at $0.13 / 1M tokens, saving up to 90% on repetitive MCP tool definitions and system instructions.

MODEL RESOURCES