Skip to main content
GPT-5

GPT-5

OpenAI's previous intelligent reasoning model for coding and agentic tasks.

ReasoningCodingAgentic Tasks

Context Window

400,000

GPT-5

Max Output

128,000

1M tokens

Input

$1.25

Output

$10

Model Codegpt-5

Playground

gpt-5
Reference Images0/5

Click or drag

No output yet

Pricing

PlanContext WindowMax OutputInputOutputCache WriteCache Read
GPT-5
400,000128,000
$1.25
$10
-
$0.125

Official OpenAI pricing for GPT-5.

Cached input pricing applies to reused prompt tokens.

Cache read or cached input pricing applies to reused prompt tokens.

README

GPT-5 is OpenAI's earlier flagship reasoning model for coding, reasoning, and agentic tasks, with configurable reasoning effort and broad tool support across the API.
  • OpenAI describes GPT-5 as a previous intelligent reasoning model for coding and agentic tasks across domains.
  • It supports configurable reasoning effort, long context, tool use, and structured outputs, making it suitable for complex multi-step workflows.
  • For teams maintaining GPT-5 integrations, it remains useful when they want the original GPT-5 behavior rather than migrating to newer GPT-5 family variants.

API

Use the API docs for request format, parameters, and integration details.

OpenAI's previous intelligent reasoning model for coding and agentic tasks.

Model Code

gpt-5

View API Docs

API

Endpoint

POST /v1/chat/completions

Authentication

Authorization: Bearer YOUR_REACH_API_KEY
Content-Type: application/json

Example

curl -X POST "https://direct.reachapi.ai/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_REACH_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "YOUR_MODEL_ID",
    "messages": [
      {
        "role": "user",
        "content": "Introduce ReachAPI in one sentence."
      }
    ],
    "temperature": 0.2
  }'
GPT-5 API — Reasoning, Coding & Agents | ReachAPI