GeekRadar / The comparison desk

COMPARE.

AI models

openai

GPT-5.6 Terra

AI model Released Jul 9, 2026

API mode: Chat^*
Context window: 1,050,000 tokens
Maximum output: 128,000 tokens
Open weights: No

Capability & preference

General capability · ECI

A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.

GPT-5.6 Terra 160.9^* GPT-5.6 Terra · 95% interval 158.7–163.4

Human preference · Arena

Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.

GPT-5.6 Terra 1448.3 GPT-5.6 Terra (xHigh) · 95% interval 1444.2–1452.4 · 48,166 votes · 2026-10-28

Model performance

Radar task score: four tests, equal weight. An experimental summary of these tasks, not a universal intelligence rating.

GPT-5.6 Terra

Tested configuration Radar task score

64.4^* / 100

4/4 core tests · experimental v1

8 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

Expert-written science questions; strict multiple-choice scoring. Chance accuracy is 25%.

GPT-5.6 Terra 93.3^*% Approx. 95% interval: 90.3–96.3% · 2026-07-09

Novel problem solving

Mystery Game Puzzles · 25%

Best-next-move puzzles in an undisclosed game variant. A narrow reasoning test, not general intelligence.

GPT-5.6 Terra 35.0^*% Approx. 95% interval: 25.6–44.4% · 2026-07-28

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

Private v2 mathematics problems with Python tools. Earlier versions and Tier 4 are excluded.

GPT-5.6 Terra 86.0^*% Approx. 95% interval: 81.9–90.0% · 2026-07-09

Factual answers

SimpleQA Verified · 25%

Correct factual answers under a guessing prompt, graded by a model. Not a hallucination or abstention score.

GPT-5.6 Terra 43.2^*% Approx. 95% interval: 40.1–46.3% · 2026-08-10

End-to-end software

MirrorCode · Separate result

Whole-program reimplementation with hidden tests; ML + Private, two languages. Budget: seven days and ten billion tokens per attempt.

GPT-5.6 Terra 41.1^*% Approx. 95% interval: 16.9–65.4% · 2026-10-20

Competition mathematics

OTIS Mock AIME 2024-2025 · Separate result

Competition problems with model-extracted answers checked against an exact key. Earlier grading procedures are excluded.

GPT-5.6 Terra 99.7^*% Approx. 95% interval: 99.2–100.0% · 2026-07-09

Research mathematics

FrontierMath Tier 4 v2 · Separate result

The hardest private FrontierMath problems, corrected v2 set, with Python tools. Separate from Tiers 1-3 in the core score.

GPT-5.6 Terra 70.7^*% Approx. 95% interval: 56.6–84.8% · 2026-07-09

Visual spatial reasoning

Furniture Assembly · Separate result

Assembly-error detection from photos and manuals, with zoom and Python tools. Uses model-assisted grading; not a general vision score.

GPT-5.6 Terra 54.2^*% Approx. 95% interval: 41.6–66.8% · 2026-09-10

Bars show reported task scores. Whiskers are approximate 95% intervals where standard errors are available. Different reasoning budgets are not equal-cost tests. Missing results are never zero.

Recorded results

Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.

Test version

Arena text preference / chinesehuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,513.68 rating

Confidence interval: 1,503.47 – 1,523.88

3821 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,485.47 rating

Confidence interval: 1,479.16 – 1,491.77

12713 votes

Oct 28, 2026

Category: coding
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,412.68 rating

Confidence interval: 1,405.59 – 1,419.78

10250 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,448.77 rating

Confidence interval: 1,443.35 – 1,454.18

19456 votes

Oct 28, 2026

Category: english
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,446.22 rating

Confidence interval: 1,440.89 – 1,451.55

35674 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,495.15 rating

Confidence interval: 1,486.54 – 1,503.75

5537 votes

Oct 28, 2026

Category: expert
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,467.98 rating

Confidence interval: 1,451.55 – 1,484.41

1576 votes

Oct 28, 2026

Category: french
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,460.35 rating

Confidence interval: 1,438.68 – 1,482.02

777 votes

Oct 28, 2026

Category: german
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,468.98 rating

Confidence interval: 1,464.20 – 1,473.77

31313 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,464.98 rating

Confidence interval: 1,458.67 – 1,471.29

12536 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,446.91 rating

Confidence interval: 1,439.79 – 1,454.04

8881 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,418.94 rating

Confidence interval: 1,412.36 – 1,425.52

12344 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,461.04 rating

Confidence interval: 1,451.05 – 1,471.03

4041 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,453.05 rating

Confidence interval: 1,445.59 – 1,460.52

7835 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,477.43 rating

Confidence interval: 1,465.65 – 1,489.22

2772 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,431.90 rating

Confidence interval: 1,421.07 – 1,442.73

3432 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,481.84 rating

Confidence interval: 1,476.29 – 1,487.38

18481 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,431.64 rating

Confidence interval: 1,425.29 – 1,437.98

13409 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,454.51 rating

Confidence interval: 1,448.77 – 1,460.26

17170 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,444.59 rating

Confidence interval: 1,421.59 – 1,467.59

810 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,426.07 rating

Confidence interval: 1,405.48 – 1,446.67

903 votes

Oct 28, 2026

Category: korean
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,452.93 rating

Confidence interval: 1,447.47 – 1,458.39

22238 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,463.72 rating

Confidence interval: 1,450.97 – 1,476.46

2205 votes

Oct 28, 2026

Category: math
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,454.76 rating

Confidence interval: 1,447.18 – 1,462.35

7713 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,441.01 rating

Confidence interval: 1,436.16 – 1,445.87

28700 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,448.30 rating

Confidence interval: 1,444.18 – 1,452.43

48166 votes

Oct 28, 2026

Category: overall
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,448.59 rating

Confidence interval: 1,426.51 – 1,470.67

693 votes

Oct 28, 2026

Category: polish
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,453.17 rating

Confidence interval: 1,444.67 – 1,461.67

5582 votes

Oct 28, 2026

Category: russian
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-10-28 · rating

GPT-5.6 Terra

1,448.37 rating

Confidence interval: 1,432.53 – 1,464.20

1488 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: GPT-5.6 Terra (xHigh)
Evaluation type: human preference

Arena text preference / chinesehuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,514.57 rating

Confidence interval: 1,503.89 – 1,525.24

3415 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,484.87 rating

Confidence interval: 1,478.39 – 1,491.36

11499 votes

Oct 15, 2026

Category: coding
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,412.07 rating

Confidence interval: 1,404.74 – 1,419.40

9176 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,448.23 rating

Confidence interval: 1,442.66 – 1,453.80

17561 votes

Oct 15, 2026

Category: english
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,444.87 rating

Confidence interval: 1,439.38 – 1,450.36

32072 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,494.62 rating

Confidence interval: 1,485.69 – 1,503.54

5032 votes

Oct 15, 2026

Category: expert
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,469.09 rating

Confidence interval: 1,451.64 – 1,486.55

1372 votes

Oct 15, 2026

Category: french
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,458.44 rating

Confidence interval: 1,435.64 – 1,481.24

690 votes

Oct 15, 2026

Category: german
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,468.38 rating

Confidence interval: 1,463.46 – 1,473.30

28222 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,464.34 rating

Confidence interval: 1,457.83 – 1,470.85

11309 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,446.71 rating

Confidence interval: 1,439.35 – 1,454.07

8036 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,418.07 rating

Confidence interval: 1,411.28 – 1,424.86

11055 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,461.46 rating

Confidence interval: 1,451.12 – 1,471.81

3695 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,453.45 rating

Confidence interval: 1,445.73 – 1,461.18

7099 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,477.95 rating

Confidence interval: 1,465.58 – 1,490.32

2463 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,430.30 rating

Confidence interval: 1,419.01 – 1,441.60

3105 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,480.76 rating

Confidence interval: 1,475.07 – 1,486.46

16699 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,431.23 rating

Confidence interval: 1,424.68 – 1,437.78

11998 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,455.53 rating

Confidence interval: 1,449.60 – 1,461.46

15379 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,456.02 rating

Confidence interval: 1,430.82 – 1,481.21

676 votes

Oct 15, 2026

Category: japanese
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,427.29 rating

Confidence interval: 1,406.12 – 1,448.46

840 votes

Oct 15, 2026

Category: korean
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,452.83 rating

Confidence interval: 1,447.21 – 1,458.45

20120 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,464.51 rating

Confidence interval: 1,451.07 – 1,477.96

1946 votes

Oct 15, 2026

Category: math
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,451.75 rating

Confidence interval: 1,443.88 – 1,459.62

6941 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,439.90 rating

Confidence interval: 1,434.90 – 1,444.89

25702 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,447.39 rating

Confidence interval: 1,443.16 – 1,451.62

43271 votes

Oct 15, 2026

Category: overall
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,447.40 rating

Confidence interval: 1,424.44 – 1,470.35

629 votes

Oct 15, 2026

Category: polish
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,452.22 rating

Confidence interval: 1,443.34 – 1,461.10

4920 votes

Oct 15, 2026

Category: russian
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-10-15 · rating

GPT-5.6 Terra

1,449.93 rating

Confidence interval: 1,433.21 – 1,466.66

1320 votes

Oct 15, 2026

Category: spanish
Evaluated configuration: gpt-5.6-terra-xhigh
Evaluation type: human preference

Run it locally

Inference · memory estimate

GPT-5.6 Terra

Closed weights. No supported local deployment or GPU requirement is published.

API cost

USD / month

Input tokens / monthOutput tokens / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

GPT-5.6 Terra

Provider offer

GPT-5.6 Terra / Pricing tiers 8

Provider / scope	Rate	Currency	Amount / unit
OpenAIgpt-5.6-terraBatch	Cached input	USD	0.1 / 1M tokens
	Input	USD	1 / 1M tokens
	Output	USD	6 / 1M tokens
OpenAIgpt-5.6-terraBatch long_context	Cached input	USD	0.2 / 1M tokens
	Input	USD	2 / 1M tokens
	Output	USD	9 / 1M tokens
OpenAIgpt-5.6-terraFlex	Cached input	USD	0.1 / 1M tokens
	Input	USD	1 / 1M tokens
	Output	USD	6 / 1M tokens
OpenAIgpt-5.6-terraFlex long_context	Cached input	USD	0.2 / 1M tokens
	Input	USD	2 / 1M tokens
	Output	USD	9 / 1M tokens
OpenAIgpt-5.6-terraPriority	Cached input	USD	0.4 / 1M tokens
	Input	USD	4 / 1M tokens
	Output	USD	24 / 1M tokens
OpenAIgpt-5.6-terraPriority long_context	Cached input	USD	0.8 / 1M tokens
	Input	USD	8 / 1M tokens
	Output	USD	36 / 1M tokens
OpenAIgpt-5.6-terraStandard long_context	Cached input	USD	0.4 / 1M tokens
	Input	USD	4 / 1M tokens
	Output	USD	18 / 1M tokens
OpenAIgpt-5.6-terraStandard	Cached input	USD	0.2 / 1M tokens
	Input	USD	2 / 1M tokens
	Output	USD	12 / 1M tokens

Capabilities

Context window: 1,050,000 tokens
Maximum input: 922,000 tokens^*
Maximum output: 128,000 tokens
Reasoning: Yes
Tool calling: Yes
Structured output: Yes^*
Open weights: No
Knowledge cutoff: 2026-02-16
API mode: Chat^*
Image input: Yes^*
PDF input: Yes^*
Parallel tool calls: Yes^*
Prompt caching: Yes^*
System messages: Yes^*
Tool choice: Yes^*
Web search: Yes^*
Model license: Proprietary

Input modalities

text
image
pdf

Output modalities

text

System configuration

Detailed specifications

Specifications · 59 fields

cache creation input token cost

2.5e-6^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache creation input token cost above 272k tokens

5.0e-6^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache creation input token cost above 272k tokens batches

2.5e-6^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache creation input token cost above 272k tokens flex

2.5e-6^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache creation input token cost above 272k tokens priority

1.0e-5^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache creation input token cost batches

1.25e-6^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache creation input token cost flex

1.25e-6^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache creation input token cost priority

5.0e-6^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache read input token cost

2.0e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache read input token cost above 272k tokens

4.0e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache read input token cost above 272k tokens batches

2.0e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache read input token cost above 272k tokens flex

2.0e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache read input token cost above 272k tokens priority

8.0e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache read input token cost batches

1.0e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache read input token cost flex

1.0e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

cache read input token cost priority

4.0e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per token

2.0e-6^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per token above 272k tokens

4.0e-6^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per token above 272k tokens batches

2.0e-6^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per token above 272k tokens flex

2.0e-6^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per token above 272k tokens priority

8.0e-6^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per token batches

1.0e-6^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per token flex

1.0e-6^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per token priority

4.0e-6^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

litellm provider

openai^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

max input tokens

922,000^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

max output tokens

128,000^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

max tokens

128,000^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

mode

chat^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

output cost per token

1.2e-5^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

output cost per token above 272k tokens

1.8e-5^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

output cost per token above 272k tokens batches

9.0e-6^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

output cost per token above 272k tokens flex

9.0e-6^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

output cost per token above 272k tokens priority

3.6e-5^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

output cost per token batches

6.0e-6^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

output cost per token flex

6.0e-6^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

output cost per token priority

2.4e-5^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

regional processing uplift multiplier eu

1.1^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

regional processing uplift multiplier us

1.1^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

search context cost per query

search_context_size_high: 0.01^*
search_context_size_low: 0.01^*
search_context_size_medium: 0.01^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supported endpoints

/v1/chat/completions^*
/v1/batch^*
/v1/responses^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supported modalities

text^*
image^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supported output modalities

text^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports function calling

Yes^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports minimal reasoning effort

No^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports native streaming

Yes^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports none reasoning effort

Yes^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports parallel function calling

Yes^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports pdf input

Yes^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports prompt cache breakpoint

Yes^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports prompt caching

Yes^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports reasoning

Yes^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports response schema

Yes^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports system messages

Yes^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports tool choice

Yes^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports tool search

Yes^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports vision

Yes^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports web search

Yes^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports xhigh reasoning effort

Yes^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-5.6-terra^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

* Provisional data