OpenAI

GPT-5.2-Codex

$1.75 per 1M input tokens and $14.00 per 1M output tokens · 400K context · vision, tools, reasoning, JSON.

Prices checked Oct 21, 2026 · tracked by LLM Cost Index since Oct 21, 2026

$1.75
input / 1M tokens
$14.00
output / 1M tokens
$0.175
cached input / 1M
400K
context window
128K
max output
28.5
Artificial Analysis intelligence index

What GPT-5.2-Codex costs per month

Estimated monthly bill for typical workloads, using the cached-input price for repeated context. Try your own numbers in the cost calculator.

WorkloadPer month
Customer chatbot
1,000 conversations a day, 8 turns each
$1,466
Document Q&A (RAG)
500 questions a day over retrieved documents
$248
Coding / tool-using agent
200 tasks a day, long tool-heavy contexts
$541
Content generation
30 long articles a day
$36.23
Classification / extraction
100,000 short items a day
$2,205

Price history

We started tracking GPT-5.2-Codex on Oct 21, 2026; the chart appears as soon as there is a second data point. See all recent price changes.

Cheaper alternatives to GPT-5.2-Codex

Models with the same tool calling, image input, structured output for at least 20% less (3:1 input/output mix), most capable first.

Cheaper alternatives to GPT-5.2-Codex
Model Input / 1M Output / 1M Context Capabilities
$1.25 $4.25 1.05M visiontoolsreasoningJSON
Grok 4.7
xAI
$2.00 $6.00 500K visiontoolsreasoningJSON
MiMo-V2.6-Pro
Xiaomi
$0.435 $0.87 1.05M visionaudiotoolsreasoningJSONopen weights
$2.00 $6.00 1M visiontoolsreasoningJSON
Grok 4.6
xAI
$2.00 $6.00 500K visiontoolsreasoningJSON

How to pay less for GPT-5.2-Codex

For a customer chatbot (1,000 conversations a day, 8 turns each) that costs $1,806 a month at list price without caching:

OptionPer monthYou save
Move to Muse Spark 1.3 (similar capabilities)$569$1,237 (68%)
Use prompt caching (60% of input cached)$1,466$340 (19%)

Other workloads: cut-your-bill tool for GPT-5.2-Codex.

Specifications

Model IDopenai/gpt-5.2-codex
Inputtext, image
Outputtext
Tool callingYes
Structured outputYes
Reasoning modeYes
Open weightsNo
ReleasedJan 14, 2026
Web search$0.01 per request

FAQ

How much does GPT-5.2-Codex cost?
$1.75 per million input tokens and $14.00 per million output tokens; cached input costs $0.175 per million. Prices as of Oct 21, 2026.
What is the context window of GPT-5.2-Codex?
400K tokens, with up to 128K output tokens per response.
Does GPT-5.2-Codex support images, tools and structured output?
Images as input: yes. Tool calling: yes. Structured (JSON) output: yes. Reasoning mode: yes.
What are cheaper alternatives to GPT-5.2-Codex?
Models with the same key capabilities for at least 20% less include Muse Spark 1.3 ($1.25 / $4.25), Grok 4.7 ($2.00 / $6.00), MiMo-V2.6-Pro ($0.435 / $0.87).

More from OpenAI: all OpenAI models · how we collect prices