impulse

GPT-5.1 Codex Max

Frontier lab

GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks.

API id gpt-5.1-codex-maxReleased 4 Dec 2025 (Dec 2025)
Input / 1M
$1.25
at OpenAI
Output / 1M
$10.00
at OpenAI
Context window
400K
tokens
Max output
128K
tokens per reply
Hosts
2
5 listings
Released
Dec 2025
4 Dec 2025

Pricing

List prices at OpenAI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$1.25$10.00
Cached input
90% off input
$0.125

What it costs a month

At OpenAI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$1,024
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$690
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$1,155
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$5,400
Use your own numbers

Where to run it

2 hosts serve GPT-5.1 Codex Max. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
OpenAILab API
gpt-5.1-codex-max
$1.25 / $10.00
gpt-5.1-codex-max
$1.25 / $10.00
Retires 18 May 2027
ChatGPTSubscription
gpt-5.1-codex-max
In the subscription
Show 2 more listings: regions, snapshots and variants
Azure OpenAI
eu
gpt-5.1-codex-max
$1.38 / $11.00
+10% vs headline
Retires 18 May 2027
us
gpt-5.1-codex-max
$1.38 / $11.00
+10% vs headline
Retires 18 May 2027

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
ImagesTextPDFs
Produces
Text
Features
Parallel tool callsPDF inputPrompt cachingBuilt-in web search

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than OpenAI.

Smaller OpenAI models

  • GPT-6.1 Terra
    OpenAI · on OpenAI
    $1.00 / $5.00
    Has every key capability
    42% less
  • GPT-5.4 Mini
    OpenAI · on OpenAI
    $0.75 / $4.50
    Has every key capability
    51% less
  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    87% less

Other frontier labs

  • Gemini 4 Hydrogen
    Google · on Google AI Studio
    $1.50 / $7.50
    Has every key capability
    13% less
  • Grok 4.7
    xAI · on xAI
    $2.00 / $6.00
    Has every key capability
    13% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    94% less
  • Gemini 3.8 Flash
    Google · on Google AI Studio
    $0.75 / $3.75
    Has every key capability
    56% less

Open-weight picks

  • Qwen4 Max
    Alibaba Qwen · on Alibaba DashScope
    $1.50 / $4.50
    Has every key capability
    35% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    50% less
  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    80% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    85% less

Call it

Using OpenAI's API.

Python
from openai import OpenAI

client = OpenAI()  # reads OPENAI_API_KEY

response = client.responses.create(model="gpt-5.1-codex-max", input="Hello")
print(response.output_text)

Quick answers

How much does GPT-5.1 Codex Max cost?

On OpenAI, GPT-5.1 Codex Max costs $1.25 per million input tokens and $10.00 per million output tokens. Cached input costs $0.125 per million tokens.

Which APIs offer GPT-5.1 Codex Max?

GPT-5.1 Codex Max runs on 2 APIs: OpenAI and Azure OpenAI.

What is GPT-5.1 Codex Max's context window?

400K tokens, with up to 128K tokens in one reply.

Is GPT-5.1 Codex Max being retired?

Azure OpenAI retires it on 18 May 2027. 1 host keeps serving it.

What are cheaper alternatives to GPT-5.1 Codex Max?

Models that cost less and keep most of what it can do: GPT-6.1 Terra on OpenAI (42% less), Gemini 4 Hydrogen on Google AI Studio (13% less), Grok 4.7 on xAI (13% less) and Qwen4 Max on Alibaba DashScope (35% less). Savings are on a mix of 3 input tokens to 1 output token.

When was GPT-5.1 Codex Max released?

OpenAI released it on 4 Dec 2025.

What is GPT-5.1 Codex Max's API model id?

Use gpt-5.1-codex-max with OpenAI.

Sources

Raw catalog entry for gpt-5.1-codex-max on OpenAI
{
  "cache_read_input_token_cost": 1.25e-7,
  "deprecation_date": "2026-07-23",
  "deprecation_source": "https://developers.openai.com/api/docs/deprecations",
  "successor_model": "gpt-5.6-sol",
  "input_cost_per_token": 0.00000125,
  "litellm_provider": "openai",
  "max_input_tokens": 400000,
  "max_output_tokens": 128000,
  "mode": "responses",
  "output_cost_per_token": 0.00001,
  "fedramp_uplift_multiplier": 1.1,
  "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex-max",
  "supported_endpoints": [
    "/v1/responses"
  ],
  "supported_modalities": [
    "text",
    "image"
  ],
  "supported_output_modalities": [
    "text"
  ],
  "supports_function_calling": true,
  "supports_native_streaming": true,
  "supports_parallel_function_calling": true,
  "supports_pdf_input": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_tool_choice": true,
  "supports_vision": true,
  "supports_web_search": true
}