GPT-5.2
GPT-5.2 is a legacy integration reference; keep it only while you identify a current replacement.
Use it for
- Teams maintaining an existing integration
- Workloads that can use a 400k context window
- Buyers comparing 3 tracked provider routes
Do not use it for
- New production launches
- Family
- GPT-5
- Released
- 2025-12-11
- Context
- 400k
- Architecture
- Decoder Only
- Knowledge cutoff
- 2025-08
- Specialization
- general
- Openness
- Proprietary
- License
- ProprietaryCommercial use: conditional
- Weights
- Not released
- Code
- Unknown
- Training
- Pretrained
Cheapest of 3 routes · OpenRouter
About
GPT-5.2 is OpenAI's incremental update in the GPT-5 series offering improvements in agentic coding and long-context performance at 128K context.
GPT-5.2 is a proprietary model in the GPT-5 family. The structured metadata tracks a 400k-token context window, multimodal input, reasoning, function calling, tool use, structured outputs, and code execution. This page tracks provider routes through Replicate API, OpenRouter, and Vercel AI Gateway, with the cheapest tracked route listed at $1.75 input and $14 output per 1M tokens. Headline tracked benchmarks include SWE-bench Verified 80.0, SWE-bench Pro 55.6, and τ-bench 75.1.
Top use-case fit: coding, agents, and build tasks
Coding
2 relevant benchmarks in the decision map.
RAG
Included by capability and metadata signals in the decision map.
Agents
2 relevant benchmarks in the decision map.
Provider price ladder
Compare all 3Compare API pricing across 3 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Cache | Route |
|---|---|---|---|---|
| OpenRouter | $1.75 | $14.00 | - | Serverless |
| Replicate API | $1.75 | $14.00 | - | Serverless |
| Vercel AI Gateway | $1.75 | $14.00 | read $0.175 | Serverless |
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(5)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| SWE-bench Verified | 80.0 | SWE-bench Verified | https://www.swebench.com/verified.html |
| SWE-bench Pro | 55.6 | — | https://openai.com/index/introducing-gpt-5-2/ |
| τ-bench | 75.1 | τ-bench | https://taubench.com/ |
| MMMU Pro | 79.5 | official OpenAI, without tool use | https://openai.com/index/introducing-gpt-5-2/ |
| GeneBench-Pro | 4.9 | xhigh | https://cdn.openai.com/pdf/21938268-21af-442f-af93-3b2249afb241/genebench-pro.pdf |
Migration checks
No linked migration route is available for this model yet.
Compare GPT-5.2 with other models
Comparison and alternatives
Browse all comparisons →Show all 47 popular comparisonssorted by 7-day search impressions
Frequently asked questions
What is the context window of GPT-5.2?
GPT-5.2 has a context window of 400k tokens.
How much does GPT-5.2 cost?
GPT-5.2 is available at $1.75/1M input tokens through Replicate API.
When was GPT-5.2 released?
GPT-5.2 was released on 2025-12-11.
Which providers offer GPT-5.2?
GPT-5.2 is available from 3 providers: Replicate API, OpenRouter, Vercel AI Gateway.
What benchmarks has GPT-5.2 been tested on?
GPT-5.2 has been evaluated on 5 benchmarks, including SWE-bench Verified, SWE-bench Pro, τ-bench, MMMU Pro, GeneBench-Pro.
Cheapest of 3 routes · OpenRouter