← Model list
GPT-5.2
openai·openai/gpt-5.2-2·GA·Closed·gpt series
Reliable GPT generation for broad coding, writing, and tool-assisted product work
At a glance
Official price$1.75 / $14.00 per 1M
Cache read $0.175 · OpenAI
Lowest paid$0.25 / $2.00
QiHang Gateway · 84× spread
Context400,000
⚠ Providers report 256,000–400,000; the table below is authoritative
Output limit128,000
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF
Knowledge cutoff2025-08-31
Released / updated2025-12-11 / 2025-12-11
Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier xhigh
Intelligence43.3
Value63
Coding—
Agentic—
Output speed78 tok/s
TTFT142.93 s
Value formulaIQ 43.3 ÷ min blended $0.688 = 63
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoningIQ 26.5 · 68 tok/s
mediumIQ 38.9
xhighIQ 43.3 · 78 tok/s
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 33 providers31 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| QiHang gpt-5.2 | Gateway | $0.25 | $2.00 | — | — | 400,000 | 128,000 | |
| UnoRouter gpt-5.2 | Gateway | $1.05 | $8.40 | — | — | 400,000 | 128,000 | |
| SAP AI Core gpt-5.2 | Cloud | $1.25 | $9.44 | $0.12 | — | 400,000 | 128,000 | |
| Jiekou.AI gpt-5.2 | Gateway | $1.57 | $12.60 | — | — | 400,000 | 128,000 | |
| Poe openai/gpt-5.2 | Gateway | $1.60 | $13.00 | $0.16 | — | 400,000 | 128,000 | |
| OrcaRouter openai/gpt-5.2 | Gateway | $1.75 | $14.00 | $0.175 | — | 400,000 | 128,000 | |
| NanoGPT openai/gpt-5.2 | Gateway | $1.75 | $14.00 | $0.175 | — | 400,000 | 128,000 | |
| Impossibl openai/gpt-5.2 | Gateway | $1.75 | $14.00 | $0.175 | — | 400,000 | 128,000 | |
| OpenRouter openai/gpt-5.2 | Gateway | $1.75 | $14.00 | $0.175 | — | 400,000 | 128,000 | |
| Databricks databricks-gpt-5-2 | Cloud | $1.75 | $14.00 | $0.175 | — | 400,000 | 128,000 | |
| OpenAIOfficial gpt-5.2 | First-party | $1.75 | $14.00 | $0.175 | — | 400,000 | 128,000 | |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1QiHang$150.00
2SAP AI Core$586.40
3UnoRouter$630.00
4Poe$797.20
5Azure Cognitive Services$855.00
6Azure$855.00
13OpenAI · Official$861.00
Switch to QiHang to save $711.00/mo (83%)
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark1 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Pro | dataset: public | 29.94 | resolve rate | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Reasoning control
effort = noneeffort = minimaleffort = loweffort = mediumeffort = higheffort = xhigheffort = max
5 / 33 providers expose no reasoning control (reasoning_options: []).
Related models
RouteLLMsame series$3.00 / $15.00GPT-Realtime-2.1same series$4.00 / $24.00NanoGPT Helpsame series$0 / $0GLM-5.2cheaper alternative$1.40 / $4.40Kimi K2.6cheaper alternative$0.95 / $4.00DeepSeek V4 Procheaper alternative$0.435 / $0.87DeepSeek V4 Flashcheaper alternative$0.14 / $0.28
Price historyone sample accumulated per data sync
Input list $1.75Output list $14.00Min blended $0.688
Price history accumulates from each data sync; currently only 1 sample(s) (2026-08-13). Each future sync adds a point, and once accumulated a line is drawn here.