openai
OpenAI: GPT-5.2-Codex
openai/gpt-5.2-codex
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
GPT-5.2-Codex is an OpenAI coding model listed in the OpenRouter catalog as an upgraded successor to GPT-5.1-Codex, aimed at software engineering workflows. According to the catalog, it targets both interactive development sessions and long autonomous execution of complex engineering tasks. It accepts text and image input, returns text, and lists a 400,000-token context window. Reasoning is mandatory with multiple effort levels, and tool use plus structured outputs are supported. OpenRouter also reports Design Arena results for agentic coding categories. No independent model card was included in this source pack, so these are catalog-reported claims worth validating on real workloads.[1]
Strengths
- The catalog describes it as optimized for software engineering, supporting interactive development and extended autonomous task execution.[1]
- Accepts image as well as text input and lists a large 400,000-token context window.[1]
- Supports tools, structured outputs, and adjustable reasoning effort, per the catalog's parameter listing.[1]
Limitations
- Evidence is limited to the OpenRouter catalog; no independent model card was supplied, so capabilities are catalog-reported only.[1]
- Catalog benchmark data covers only Design Arena agent categories, and fields such as knowledge cutoff are listed as unknown.[1]
- Reasoning is mandatory and cannot be disabled, according to the catalog.[1]
Where to use it
- Agentic coding workflows and multi-step engineering tasks, matching the catalog's stated design focus; validate on your own workload.[1]
- Interactive coding assistance such as pair-programming sessions, consistent with the catalog description.[1]
- Tool-calling pipelines that require structured outputs, given the supported parameters.[1]
Sources
- [1] OpenRouter catalog · OpenAI: GPT-5.2-CodexSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....
Specifications
- Model ID
- openai/gpt-5.2-codex
- Canonical ID
- openai/gpt-5.2-codex-20260114
- Creator
- openai
- Added to OpenRouter
- 14.01.2026
- Context length
- 400,000
- Modality
- text+image->text
- Input modalities
- text, image
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $1.75 / out $14
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: mandatory · default medium · efforts: xhigh, high, medium, low · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: mandatory · default medium · efforts: xhigh, high, medium, low · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Design Arena | agents · androidnativewin rate 47.5% · rank 19 | 1,176Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · fullstackwin rate 37.2% · rank 43 | 971Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · godotgamedevwin rate 47.8% · rank 23 | 1,142Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · mobileappswin rate 46.6% · rank 45 | 1,084Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · webappswin rate 39.6% · rank 44 | 1,032Elo | CC — below the B band | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Azure | 400,000 | $1.75 | $14 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.