LMFinder
G

GPT-5.2-Codex

Reviewed 2026-06-27
OpenAIopenai/gpt-5.2-codex
Context
400K
Price
$1.75/$14
Tooling
5/5
Deploy
Cloud API

Best for

  • Agentic workflows and tool calling
  • Writing and editing code
  • Long documents (~400K context)

Skip if

  • You need open weights to self-host

Capability scores

Tool calling5/5
Multi-step reasoning4/5

Specifications

Context window
400K tokens
VRAM
N/A (cloud-hosted)
License
proprietary
Pricing
$1.75/M input · $14/M output
Deployment
Cloud API

Our take

GPT-5.2-Codex from OpenAI offers a 400K-token context window and is well-suited to strong tool calling, multi-step reasoning, coding, long-context work. Pricing is $1.75/M input · $14/M output, billed per token through the provider API.

Watch for the trade-offs: weights are closed, so you cannot self-host.

Compare to

Claude Fable 5
Anthropic
1M context · $10/M input · $50/M output
Claude Opus 4.8
Anthropic
1M context · $5/M input · $25/M output
Claude Sonnet 4.6
Anthropic
1M context · $3/M input · $15/M output
Best LLMs for Agents & Tools →

Not sure this is the one?

Describe your project and let LMFinder rank the field for your exact constraints.

Describe your project →