OpenAI Documentation for gpt-5.2-chat-latest: Specs and Deprecation

ArticleResource

API documentation for the ChatGPT snapshot gpt-5.2-chat-latest marks the model as deprecated and suggests upgrading to GPT-6 Astra. The page details pricing, token limits, and supported tools.

Key points

  1. Deprecation: gpt-5.2-chat-latest is deprecated; OpenAI recommends GPT-6 Astra for most API workloads.
  2. Model specs: 128,000 context window, 272,000 max input tokens, 16,384 max output tokens, and an August 31, 2025 knowledge cutoff.
  3. Pricing: $1.75 per 1M input tokens, $0.175 per 1M cached input tokens, and $14 per 1M output tokens.
  4. Supported endpoints: Only Chat Completions (v1/chat/completions) and Responses (v1/responses) are active; Batch, Fine-tuning, and Realtime are unsupported.
  5. Responses API tools: Native support includes function_calling, web_search, file_search, image_generation, code_interpreter, and mcp.

Why it matters

Developers relying on direct ChatGPT-equivalent snapshots need to plan migrations to GPT-6 Astra. The specifications also confirm standard Responses API features like MCP integration.

Analysis

The model specification reflects a sunsetting generation. While restricted from newer multimodal audio endpoints, batching, and fine-tuning, it retains full compatibility with structured outputs, multimodal vision inputs, and MCP tooling via the Responses API.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Article:OpenAI

    OpenAI documents GPT-5.4 flagship model with 1.05M context window

    Official documentation outlines GPT-5.4, a flagship model tailored for coding and complex professional tasks. It features a 1,050,000-token context window, up to 128,000 output tokens, and configurable reasoning effort levels.

    AI & LLMs· Resource

  • Article:developers.openai.com

    Overview of Core OpenAI API Concepts

    OpenAI's documentation details the fundamental concepts of its API, including text generation models such as gpt-6-astra and gpt-5.6-terra, embeddings, and token-based processing.

    AI & LLMs· Resource

  • X post:darkzodchi

    Running GPT-6 Astra in Production: Cost Cliffs and Optimisation

    A guide by darkzodchi analyses technical limits and pricing mechanics in OpenAI's GPT-6 Astra. Despite a 1.05-million-token context window, hidden pricing cliffs and TPM constraints can quickly trigger unexpected costs.

    2.4kbookmarks224.2kviews

    AI & LLMs· Tutorial

  • Link:OpenAI

    OpenAI Publishes GPT-6 Astra System Card

    OpenAI has released the system card for GPT-6 Astra, its first model to achieve a 'Critical' cybersecurity capability rating, featuring stronger alignment and jailbreak resistance compared to GPT-5.6 Sol alongside reduced Chain of Thought monitorability.

    AI & LLMs· Resource

  • Article:DeepSeek

    DeepSeek API Changelog: Launch of V4-Flash-Vision-Exp and V4-Pro GA

    DeepSeek's API changelog details the introduction of the multimodal DeepSeek-V4-Flash-Vision-Exp model alongside the GA release of DeepSeek-V4-Pro. The V4 family introduces native support for the Responses API format, granular thinking effort levels, and off-peak pricing.

    AI & LLMs· Announcement

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.