GeekRadar / The comparison desk

COMPARE.

AI models

openai

GPT-6 Luna

AI model Released Sep 22, 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-6 Luna 156.8^* GPT-6 Luna · 95% interval 154.0–159.5

Human preference · Arena

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

GPT-6 Luna 1389.2 GPT-6 Luna (Max) · 95% interval 1384.9–1393.4 · 86,478 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-6 Luna

Tested configuration Radar task score

54.5^* / 100

4/4 core tests · experimental v1

9 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

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

GPT-6 Luna 90.5^*% Approx. 95% interval: 86.8–94.1% · 2026-09-22

Novel problem solving

Mystery Game Puzzles · 25%

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

GPT-6 Luna 7.0^*% Approx. 95% interval: 2.0–12.0% · 2026-09-22

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

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

GPT-6 Luna 78.9^*% Approx. 95% interval: 74.2–83.7% · 2026-09-22

Factual answers

SimpleQA Verified · 25%

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

GPT-6 Luna 41.4^*% Approx. 95% interval: 38.3–44.5% · 2026-09-22

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-6 Luna 26.7^*% Approx. 95% interval: 9.0–44.4% · 2026-10-21

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-6 Luna 98.9^*% Approx. 95% interval: 97.6–100.0% · 2026-09-22

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-6 Luna 56.1^*% Approx. 95% interval: 40.7–71.5% · 2026-09-22

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-6 Luna 44.2^*% Approx. 95% interval: 31.6–56.7% · 2026-09-28

Long-horizon computer use

SpireClimb · Separate result

Equally weighted win rates in two Slay the Spire games via screenshots and controls. Fixed game versions; not a general desktop success rate.

GPT-6 Luna 0.0^*% Uncertainty not available · 2026-09-28

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-6 Luna

1,429.67 rating

Confidence interval: 1,421.37 – 1,437.96

7417 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,436.55 rating

Confidence interval: 1,430.74 – 1,442.36

19790 votes

Oct 28, 2026

Category: coding
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,361.95 rating

Confidence interval: 1,355.74 – 1,368.16

19197 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,394.10 rating

Confidence interval: 1,388.69 – 1,399.51

33153 votes

Oct 28, 2026

Category: english
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,365.61 rating

Confidence interval: 1,360.02 – 1,371.20

64162 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,441.01 rating

Confidence interval: 1,433.55 – 1,448.46

8948 votes

Oct 28, 2026

Category: expert
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,405.53 rating

Confidence interval: 1,392.95 – 1,418.11

3684 votes

Oct 28, 2026

Category: french
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,378.18 rating

Confidence interval: 1,359.52 – 1,396.85

1283 votes

Oct 28, 2026

Category: german
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,408.20 rating

Confidence interval: 1,403.33 – 1,413.07

53299 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,410.40 rating

Confidence interval: 1,404.57 – 1,416.22

20743 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,384.48 rating

Confidence interval: 1,378.19 – 1,390.77

14761 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,362.16 rating

Confidence interval: 1,356.21 – 1,368.12

22445 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,395.53 rating

Confidence interval: 1,387.03 – 1,404.02

6888 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,387.11 rating

Confidence interval: 1,380.67 – 1,393.55

14249 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,429.36 rating

Confidence interval: 1,419.93 – 1,438.80

5298 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,355.02 rating

Confidence interval: 1,345.89 – 1,364.15

6079 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,425.44 rating

Confidence interval: 1,419.98 – 1,430.89

30405 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,383.25 rating

Confidence interval: 1,377.45 – 1,389.05

24745 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,405.78 rating

Confidence interval: 1,400.30 – 1,411.25

29447 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,367.90 rating

Confidence interval: 1,350.15 – 1,385.65

1743 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,356.18 rating

Confidence interval: 1,337.49 – 1,374.88

1327 votes

Oct 28, 2026

Category: korean
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,406.61 rating

Confidence interval: 1,401.19 – 1,412.02

36874 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,409.57 rating

Confidence interval: 1,399.81 – 1,419.33

4768 votes

Oct 28, 2026

Category: math
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,393.05 rating

Confidence interval: 1,386.35 – 1,399.75

12512 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,379.99 rating

Confidence interval: 1,375.12 – 1,384.86

53254 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,389.15 rating

Confidence interval: 1,384.90 – 1,393.41

86478 votes

Oct 28, 2026

Category: overall
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,379.53 rating

Confidence interval: 1,361.29 – 1,397.77

1220 votes

Oct 28, 2026

Category: polish
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,389.97 rating

Confidence interval: 1,383.10 – 1,396.84

11809 votes

Oct 28, 2026

Category: russian
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,391.08 rating

Confidence interval: 1,378.79 – 1,403.36

3311 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: GPT-6 Luna (Max)
Evaluation type: human preference

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

GPT-6 Luna

1,428.30 rating

Confidence interval: 1,418.16 – 1,438.44

4234 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,438.18 rating

Confidence interval: 1,431.57 – 1,444.78

11293 votes

Oct 15, 2026

Category: coding
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,363.02 rating

Confidence interval: 1,355.96 – 1,370.09

11078 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,392.99 rating

Confidence interval: 1,387.19 – 1,398.79

19325 votes

Oct 15, 2026

Category: english
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,368.53 rating

Confidence interval: 1,362.52 – 1,374.53

36582 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,441.33 rating

Confidence interval: 1,432.44 – 1,450.22

5345 votes

Oct 15, 2026

Category: expert
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,407.30 rating

Confidence interval: 1,391.72 – 1,422.87

2012 votes

Oct 15, 2026

Category: french
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,387.22 rating

Confidence interval: 1,364.07 – 1,410.37

716 votes

Oct 15, 2026

Category: german
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,411.28 rating

Confidence interval: 1,406.01 – 1,416.55

30535 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,409.79 rating

Confidence interval: 1,403.23 – 1,416.34

12042 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,385.31 rating

Confidence interval: 1,377.97 – 1,392.65

8578 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,365.07 rating

Confidence interval: 1,358.38 – 1,371.77

12825 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,396.67 rating

Confidence interval: 1,386.42 – 1,406.92

4097 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,385.77 rating

Confidence interval: 1,378.35 – 1,393.19

8527 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,426.17 rating

Confidence interval: 1,414.57 – 1,437.78

3023 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,352.22 rating

Confidence interval: 1,341.09 – 1,363.35

3591 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,423.65 rating

Confidence interval: 1,417.72 – 1,429.58

17538 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,385.48 rating

Confidence interval: 1,379.07 – 1,391.89

14256 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,409.99 rating

Confidence interval: 1,403.96 – 1,416.02

16843 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,365.12 rating

Confidence interval: 1,342.17 – 1,388.07

902 votes

Oct 15, 2026

Category: japanese
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,367.67 rating

Confidence interval: 1,344.98 – 1,390.35

814 votes

Oct 15, 2026

Category: korean
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,409.18 rating

Confidence interval: 1,403.33 – 1,415.03

21377 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,405.63 rating

Confidence interval: 1,393.54 – 1,417.71

2715 votes

Oct 15, 2026

Category: math
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,391.93 rating

Confidence interval: 1,383.91 – 1,399.95

7083 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,383.30 rating

Confidence interval: 1,378.03 – 1,388.58

30268 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,391.63 rating

Confidence interval: 1,387.01 – 1,396.25

49617 votes

Oct 15, 2026

Category: overall
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,382.47 rating

Confidence interval: 1,359.39 – 1,405.54

689 votes

Oct 15, 2026

Category: polish
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,393.45 rating

Confidence interval: 1,385.25 – 1,401.64

6576 votes

Oct 15, 2026

Category: russian
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

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

GPT-6 Luna

1,393.15 rating

Confidence interval: 1,378.07 – 1,408.22

1876 votes

Oct 15, 2026

Category: spanish
Evaluated configuration: gpt-6-luna-max
Evaluation type: human preference

Run it locally

Inference · memory estimate

GPT-6 Luna

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-6 Luna

Provider offer

GPT-6 Luna / Pricing tiers 8

Provider / scope	Rate	Currency	Amount / unit
OpenAIgpt-6-lunaBatch long_context	Cached input	USD	0.01 / 1M tokens
	Input	USD	0.1 / 1M tokens
	Output	USD	0.375 / 1M tokens
OpenAIgpt-6-lunaBatch	Cached input	USD	0.005 / 1M tokens
	Input	USD	0.05 / 1M tokens
	Output	USD	0.25 / 1M tokens
OpenAIgpt-6-lunaFlex	Cached input	USD	0.005 / 1M tokens
	Input	USD	0.05 / 1M tokens
	Output	USD	0.25 / 1M tokens
OpenAIgpt-6-lunaFlex long_context	Cached input	USD	0.01 / 1M tokens
	Input	USD	0.1 / 1M tokens
	Output	USD	0.375 / 1M tokens
OpenAIgpt-6-lunaPriority long_context	Cached input	USD	0.04 / 1M tokens
	Input	USD	0.4 / 1M tokens
	Output	USD	1.5 / 1M tokens
OpenAIgpt-6-lunaPriority	Cached input	USD	0.02 / 1M tokens
	Input	USD	0.2 / 1M tokens
	Output	USD	1 / 1M tokens
OpenAIgpt-6-lunaStandard	Cached input	USD	0.01 / 1M tokens
	Input	USD	0.1 / 1M tokens
	Output	USD	0.5 / 1M tokens
OpenAIgpt-6-lunaStandard long_context	Cached input	USD	0.02 / 1M tokens
	Input	USD	0.2 / 1M tokens
	Output	USD	0.75 / 1M tokens

Capabilities

Context window: 1,050,000 tokens
Maximum input: Reported value 1: 922,000 tokens^*
Reported value 2: 1,050,000 tokens^*
Maximum output: 128,000 tokens
Reasoning: Yes
Tool calling: Yes
Structured output: Yes^*
Open weights: No
Knowledge cutoff: 2026-05-18
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 · 95 fields

cache creation input token cost

1.25e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

1.25e-7^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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

2.5e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

2.5e-7^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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

1.25e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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 decisions

2.5e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

1.25e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

5.0e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

6.25e-8^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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 decisions

1.25e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

6.25e-8^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

2.5e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

1.0e-8^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

1.0e-8^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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

2.0e-8^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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

2.0e-8^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

1.0e-8^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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 decisions

2.0e-8^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

1.0e-8^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

4.0e-8^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

5.0e-9^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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 decisions

1.0e-8^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

5.0e-9^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

2.0e-8^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

1.0e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

1.0e-7^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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

2.0e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

2.0e-7^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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

1.0e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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 decisions

2.0e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

1.0e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

4.0e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

5.0e-8^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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 decisions

1.0e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

5.0e-8^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

2.0e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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-6-luna^*
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

bedrock_converse^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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-6-luna^*
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

1,050,000^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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-6-luna^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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-6-luna^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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-6-luna^*
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

5.0e-7^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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

5.0e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

7.5e-7^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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

7.5e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

3.75e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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 decisions

0.0^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

3.75e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

1.5e-6^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

2.5e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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 decisions

0.0^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

2.5e-7^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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

1.0e-6^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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-6-luna^*
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-6-luna^*
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-6-luna^*
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^*
/v1/decisions^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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-6-luna^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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-6-luna^*
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 bedrock converse tool result images

No^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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 computer use

Yes^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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-6-luna^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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 max reasoning effort

Yes^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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 max reasoning effort

Yes^*

Scope and conditions

native_context

provider: openai^*
mode: chat^*
full_native_model_id: gpt-6-luna^*
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-6-luna^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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-6-luna^*
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-6-luna^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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-6-luna^*
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-6-luna^*
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-6-luna^*
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-6-luna^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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-6-luna^*
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-6-luna^*
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 sampling params

No^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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-6-luna^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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-6-luna^*
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-6-luna^*
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-6-luna^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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-6-luna^*
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-6-luna^*
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: bedrock_converse^*
mode: chat^*
full_native_model_id: openai.gpt-6-luna^*
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