Skip to main content

GPT-5.2 Codex

GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. $1.75 per million input tokens, $14 per million output tokens. 400,000 token context window, maximum output of 128,000 tokens. Higher uptime with 2 providers. Includes independent benchmarks from Artificial Analysis.

Input / output price
$1.75 / $14.00 per 1M
Context
400K tokens
Released
Dec 18, 2025
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "gpt-5.2-codex".

Read docs

Providers

3 providers, cheapest first, retired then OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Azure Foundryazure_foundry/gpt-5.2-codex
$1.75/M$14.00/M
Azure OpenAIazure_openai/gpt-5.2-codex
$1.75/M$14.00/M
OpenRouterRetiredopenrouter/gpt-5.2-codex
$1.75/M$14.00/M

Is a provider down? Azure OpenAI status, OpenRouter status

Pricing

Averaged across 3 providers, in USD per 1M tokens after gateway discounts.

Average input
$1.75 per 1M
Average output
$14.00 per 1M
Average cache read
$0.17 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$1.75/MAzure Foundry, Azure OpenAI, and OpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

13tokens/sacross providers

Faster than 39% of the other 596 models on the gateway

Response latency

Lower is better

1.2sacross providers

Faster than 58% of the other 766 models on the gateway

Benchmarks

The Respan Index plus 13 published scores from 3 sources, each linked to where it was published.

30.1/ 100

Respan Index#91 of 176

176 ranked models. The shaded band is this model's 95% interval, 20.5 to 48.8. MiMo-V2.5-Pro and Muse Glimmer fall inside it, so the gap is within the margin of error.
GPT-5.2 Codex by category: Coding 18.8, Agents 22.4, Reasoning 35.7, Knowledge & language 34.4, Human preference 49.4
  1. 91GPT-5.2-Codex30.1
  2. 90MiMo-V2.5-Pro30.2
  3. 92Muse Glimmer30.0

Published scores

BenchmarkScore
LiveBench CodingLiveBench83.6%
SWE-Lancer IC DiamondOpenAI76%
Cybersecurity Capture The Flag ChallengesOpenAI67.4%
Terminal-Bench 2.0OpenAI64%
SWE-Bench ProOpenAI56.4%

Compare GPT-5.2 Codex: GPT-5.2-Codex vs Claude Opus 5.5, GPT-5.2-Codex vs GPT-6.2 Astra, GPT-5.2-Codex vs GPT-6 Astra, GPT-5.2-Codex vs GPT-6.1 Sol, GPT-5.2-Codex vs GPT-6.1 Terra, GPT-5.2-Codex vs GPT-6.2 Sol

Apps

Use GPT-5.2 Codex in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

GPT-5.2 Codex FAQ

Short answers, built from the data on this page.

GPT-5.2 Codex is a model from OpenAI, released on Dec 18, 2025. GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. $1.75 per million input tokens, $14 per million output tokens. 400,000 token context window, maximum output of 128,000 tokens. Higher uptime with 2 providers. Includes independent benchmarks from Artificial Analysis.

On the Respan gateway, GPT-5.2 Codex costs $1.75 per 1M input tokens and $14.00 per 1M output tokens on every provider, after gateway discounts.

GPT-5.2 Codex is available through 3 providers: Azure Foundry, Azure OpenAI, and OpenRouter.

GPT-5.2 Codex accepts up to 400K tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "gpt-5.2-codex". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

GPT-5.2 Codex scores 30.1 out of 100 on the Respan Index v1.1, ranking #91 of 176 models. By category: Coding 18.8, Agents 22.4, Reasoning 35.7, Knowledge & language 34.4, and Human preference 49.4. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

GPT-5.2 Codex has 13 published benchmark scores, including LiveBench Coding 83.6%, LiveBench Agentic Coding 49.4%, and LiveBench Data Analysis 78.2%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.