Back to models
OpenAI logo

OpenAI

GPT-5

OpenAI’s previous flagship reasoning model for coding, agentic tasks, and broad professional work.

Overall score
92
reasoningcodingagentic
Context window
400K tokens
Speed
Balanced
Input pricing
$1.25 / 1M input tokens
Output pricing
$10 / 1M output tokens

Score breakdown

Capability94
Use-case fit93
Cost efficiency82
Speed85
Reliability92
Agent readiness94
Ecosystem96

Scores combine benchmark signals, product experience, and editorial weighting. Use them as a practical guide, not an absolute truth claim.

Best for

CodingAgent automation

Works with

Codex CLIOpenAI Responses APILangGraphE2B

Modalities

textimage

Sources & trust

Officially verified core fields
Official linkSummaryDescriptionModalitiesModality profileContext windowMax outputTool supportPricingPricing page

Editorial fields such as shortlist guidance, strengths, caveats, and scoring remain clearly separated from official provider data.

Last verified: Apr 9, 2026

Strengths

  • Strong coding and tool-use baseline with broad ecosystem support.
  • Large context and mature Responses API integration.

Things to watch

  • No longer OpenAI’s newest flagship tier.
  • Costs rise quickly on long, high-output workflows.

Best for