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
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
3 providers, cheapest first, retired then OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Azure Foundry azure_foundry/gpt-5.2-codex | $1.75/M | $14.00/M |
Azure OpenAI azure_openai/gpt-5.2-codex | $1.75/M | $14.00/M |
OpenRouterRetired openrouter/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.
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 better13tokens/sacross providers
Response latency
Lower is better1.2sacross providers
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
- 91GPT-5.2-Codex30.1
- 90MiMo-V2.5-Pro30.2
- 92Muse Glimmer30.0
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveBench CodingLiveBench | 83.6% | LiveBench | Oct 5, 2026 |
| SWE-Lancer IC DiamondOpenAI | 76% | OpenAI | Feb 5, 2026 |
| Cybersecurity Capture The Flag ChallengesOpenAI | 67.4% | OpenAI | Feb 5, 2026 |
| Terminal-Bench 2.0OpenAI | 64% | OpenAI | Dec 18, 2025 |
| SWE-Bench ProOpenAI | 56.4% | OpenAI | Dec 18, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveBench Agentic CodingLiveBench | 49.4% | LiveBench | Oct 5, 2026 |
| OSWorld-VerifiedOpenAI | 38.2% | OpenAI | Feb 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveBench Data AnalysisLiveBench | 78.2% | LiveBench | Oct 5, 2026 |
| LiveBench ReasoningLiveBench | 77.7% | LiveBench | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveBench MathematicsLiveBench | 88.8% | LiveBench | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveBench LanguageLiveBench | 73.7% | LiveBench | Oct 5, 2026 |
| LiveBench Instruction FollowingLiveBench | 66.4% | LiveBench | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena WebDevLMArena | 1339 Elo · #106 of 124 | LMArena | Nov 19, 2026 |
How GPT compares: Claude vs GPT, Gemini vs GPT, DeepSeek vs GPT
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.