Compare models
Choose two or three models, including exact thinking and fast versions. Copy the URL to share your selection.
| Comparison | GPT-5.2 Fastopenai/gpt-5.2-low | Choose model 2 |
|---|---|---|
| Type | Chat | — |
| Best for | Fast, low-cost replies and high-volume everyday tasks | — |
| TokenRex price | $1.75 in / $14.00 out per 1M tokens | — |
| Cached input / 1M tokens | $0.175 per 1M tokens | — |
| Cache write / 1M tokens | No extra fee | — |
| Cached output | Not offered · standard output rate applies | — |
| Market price | $1.75 in / $14.00 out per 1M tokens | — |
| Context window (provider) | 400,000 tokens | — |
| Input token limit (provider) | Within the context window | — |
| Maximum output | 128,000 tokens | — |
| Knowledge cutoff | Aug 31, 2025 | — |
| Vendor input modalities | Not verified | — |
| Vendor output modalities | Not verified | — |
| TokenRex endpoints | POST /v1/chat/completions | — |
| TokenRex input | Text, Image/PDF content through the chat bridge | — |
| TokenRex output | Text | — |
| Benchmark evidence | 1 source-linked results | — |
| lineage-bench (overall, avg of lineage-8/16/32/64/128) | 0.66accuracy (0-1) gpt-5.2, reasoning.effort=low, lineage-bench (graph relationship reasoning), via OpenAI API (author states repeated directly, not only via OpenRouter). Community-reproduced micro-benchmark, not an OpenAI-published table; single independent tester, small forum post, not peer reviewed. Publisher excerpt: gpt-5.2 (low) | 0.660 | 1.000 | 0.975 | 0.800 | 0.400 | 0.125 OpenAI Developer Community forum · independent lineage-bench results by user sszymczy | — |
No overall score, winner or cost-versus-score frontier is calculated without comparable, attributable benchmark evidence. Different test configurations appear separately. Vendor capabilities are distinct from TokenRex API support.
— means no published value or no matching capability. Provider token limits are not tested gateway guarantees; TokenRex media controls and response formats are listed separately.
GPT-5.2 Fast
Sources and verification
Provider specifications describe the upstream model, not a guarantee of every feature through TokenRex. Prices come from the enabled catalog; benchmark results belong to the exact tested model.
- Provider model specifications
Vendor-reported
Last checked - OpenAI - Introducing GPT-5.2
Vendor-reported
Last checked - OpenAI Developer Community forum · independent lineage-bench results by user sszymczy
Third-party report
Last checked
Research notes (1)
- Published provider limits; maximum-capacity requests have not been independently exercised through TokenRex. Thinking-level variants use the same provider model; reasoning and answer tokens share the output budget.