← Model list
GPT-5.6 Terra
openai·openai/gpt-5.6-terra·BETA·Closed·gpt-terra series·NEW
Balanced GPT-5.6 model for capable, cost-efficient everyday work
At a glance
Official price$2.00 / $12.00 per 1M
Cache read $0.20 · OpenAI
Lowest paid$1.50 / $2.00
Xpersona Gateway · 3.1× spread
1 more $0 channels
Context1,050,000
⚠ Providers report 372,000–1,050,000; the table below is authoritative
Output limit128,000
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
Modalities
TextImagePDF
Knowledge cutoff2026-02-16
Released / updated2026-07-09 / 2026-07-09
Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier max
Intelligence56.6
Value35
Coding76.7
Agentic50.2
Output speed119 tok/s
TTFT186.73 s
Cost per task$0.5080
Value formulaIQ 56.6 ÷ min blended $1.625 = 35
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoningIQ 34.6 · 98 tok/s
lowIQ 41.3 · 94 tok/s
mediumIQ 46.8 · 98 tok/s
highIQ 50.1 · 104 tok/s
xhighIQ 52.8 · 102 tok/s
maxIQ 56.6 · 119 tok/s
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 34 providers32 with public prices · 1 free
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Kenari gpt-5-6-terra | Gateway | Free | — | — | 1,050,000 | 128,000 | ||
| Xpersona | Gateway | $1.50 | $2.00 | $0.15 | — | 372,000 ⚠ | 128,000 | |
| NanoGPT | Gateway | $1.00 | $6.00 | $0.10 | $1.25 | 1,050,000 | 128,000 | |
| routing.run | Gateway | $1.50 | $9.00 | — | — | 1,000,000 ⚠ | 128,000 | |
| Requesty | Gateway | $1.80 tiered >272K: $3.60 | $10.80 | $0.18 | — | 1,050,000 | 128,000 | |
| Impossibl | Gateway | $2.00 tiered >272K: $4.00 | $12.00 | $0.20 | $2.50 | 1,050,000 | 128,000 | |
| OpenRouter | Gateway | $2.00 tiered >272K: $4.00 | $12.00 | $0.20 | $2.50 | 1,050,000 | 128,000 | |
| CrossModel | Gateway | $2.00 tiered >272K: $4.00 | $12.00 | $0.20 | $2.50 | 1,050,000 | 128,000 | |
| OpenAIOfficial | First-party | $2.00 tiered >272K: $4.00 | $12.00 | $0.20 | $2.50 | 1,050,000 | 128,000 | |
| Merge Gateway | Gateway | $2.00 | $12.00 | $0.20 | — | 1,050,000 | 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
1Xpersona$238.00
2NanoGPT$392.00
3Requesty$705.60
4routing.run$750.00
5Impossibl$784.00
6OpenRouter$784.00
8OpenAI · Official$784.00
1 more channels offer $0 (Kenari); free tiers usually have rate limits and no SLA, excluded from ranking.
Switch to Xpersona to save $546.00/mo (70%)
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark12 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Pro | — | 63.4 | resolve rate | Source ↗ |
| Terminal-Bench | v2.1 | 87.4 | success rate | Source ↗ |
| DeepSWE | v1.1 | 69.6 | resolve rate | Source ↗ |
| GPQA Diamond | — | 92.9 | accuracy | Source ↗ |
| FrontierMath | dataset: Tier 1-3 · vv2 | 84.9 | accuracy | Source ↗ |
| BrowseComp | — | 87.5 | accuracy | Source ↗ |
| OSWorld | v2.0 | 50.2 | success rate | Source ↗ |
| MMMU Pro | variant: no tools | 80.7 | accuracy | Source ↗ |
| Agents' Last Exam | — | 50.4 | — | Source ↗ |
| Toolathlon | — | 53.1 | success rate | Source ↗ |
| Artificial Analysis Intelligence Index | variant: max · v4.1 | 55 | index score | Source ↗ |
| Artificial Analysis Coding Agent Index | harness: Codex · variant: max · v1.1 | 77.4 | index score | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Reasoning control
effort = noneeffort = loweffort = mediumeffort = higheffort = xhigheffort = maxbudget_tokenseffort = minimal
2 / 34 providers expose no reasoning control (reasoning_options: []).
Experimental modes2 items
| Mode | Provider | Input | Output | Cache read | Cache write |
|---|---|---|---|---|---|
| fast | OpenAI | $4.00 | $24.00 | $0.40 | $5.00 |
| pro | OpenAI | — | — | — | — |
Related models
GPT-5.6 Terra Prosame series$3.13 / $18.75GPT-5.6 Terra (Global)same series$2.20 / $13.20GPT-5.6 Terra (OpenAI)same series$2.00 / $12.00GLM-5.2cheaper alternative$1.40 / $4.40DeepSeek V4 Procheaper alternative$0.435 / $0.87DeepSeek V4 Flashcheaper alternative$0.14 / $0.28DeepSeek V4 Flash 0731cheaper alternative$0.479 / $1.44
Price historyone sample accumulated per data sync
Input listOutput listMin blended