Gemini 3.5 Flash
6 benchmark results for this configuration
GeekRadar / The comparison desk
COMPARE.
AI modelsGemini 3.5 Flash
AI model Released
- API mode
- Chat*
- Context window
- 1,048,576 tokens
- Maximum output
- 65,536 tokens
- Open weights
- No
Capability & preference
General capability · ECI
A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.
Human preference · Arena
Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.
Benchmark results
- Reported score · version unreported · intelligence50.20*Platform unreported Compare results
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.
Arena text preference / chinesehuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,526.52 rating
Confidence interval: 1,515.80 – 1,537.23
3416 votes
- Category
- chinese
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
1,525.30 rating
Confidence interval: 1,514.77 – 1,535.83
3583 votes
- Category
- chinese
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,492.97 rating
Confidence interval: 1,486.95 – 1,499.00
13850 votes
- Category
- coding
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
1,487.50 rating
Confidence interval: 1,481.34 – 1,493.66
13619 votes
- Category
- coding
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,471.27 rating
Confidence interval: 1,463.93 – 1,478.60
9411 votes
- Category
- creative_writing
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
1,468.68 rating
Confidence interval: 1,461.48 – 1,475.87
9379 votes
- Category
- creative_writing
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,480.62 rating
Confidence interval: 1,475.47 – 1,485.76
20531 votes
- Category
- english
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
1,476.48 rating
Confidence interval: 1,471.16 – 1,481.79
20033 votes
- Category
- english
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,491.07 rating
Confidence interval: 1,486.00 – 1,496.14
36490 votes
- Category
- exclude_ties
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
1,486.55 rating
Confidence interval: 1,481.17 – 1,491.92
35425 votes
- Category
- exclude_ties
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,494.46 rating
Confidence interval: 1,485.97 – 1,502.95
5567 votes
- Category
- expert
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
1,484.86 rating
Confidence interval: 1,476.34 – 1,493.39
5585 votes
- Category
- expert
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,489.38 rating
Confidence interval: 1,472.91 – 1,505.85
1546 votes
- Category
- french
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
1,475.45 rating
Confidence interval: 1,458.70 – 1,492.19
1502 votes
- Category
- french
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,492.75 rating
Confidence interval: 1,470.57 – 1,514.93
773 votes
- Category
- german
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
1,492.45 rating
Confidence interval: 1,469.95 – 1,514.95
757 votes
- Category
- german
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,488.19 rating
Confidence interval: 1,483.64 – 1,492.74
32328 votes
- Category
- hard_prompts
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
1,485.16 rating
Confidence interval: 1,480.36 – 1,489.96
31463 votes
- Category
- hard_prompts
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,482.35 rating
Confidence interval: 1,476.34 – 1,488.36
13762 votes
- Category
- hard_prompts_english
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
1,479.13 rating
Confidence interval: 1,472.99 – 1,485.27
13314 votes
- Category
- hard_prompts_english
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,467.21 rating
Confidence interval: 1,460.36 – 1,474.06
9384 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
1,459.28 rating
Confidence interval: 1,452.25 – 1,466.31
9092 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,459.68 rating
Confidence interval: 1,453.05 – 1,466.30
12013 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
1,458.73 rating
Confidence interval: 1,452.21 – 1,465.26
11832 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,487.35 rating
Confidence interval: 1,477.13 – 1,497.57
3834 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
1,486.63 rating
Confidence interval: 1,476.76 – 1,496.51
4050 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,494.87 rating
Confidence interval: 1,487.48 – 1,502.25
7784 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
1,493.88 rating
Confidence interval: 1,486.68 – 1,501.07
7983 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,494.14 rating
Confidence interval: 1,482.20 – 1,506.08
2705 votes
- Category
- industry_mathematical
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
1,492.24 rating
Confidence interval: 1,480.66 – 1,503.81
2886 votes
- Category
- industry_mathematical
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,483.56 rating
Confidence interval: 1,472.97 – 1,494.16
3543 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
1,482.58 rating
Confidence interval: 1,471.82 – 1,493.34
3445 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,493.90 rating
Confidence interval: 1,488.60 – 1,499.21
19402 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
1,485.92 rating
Confidence interval: 1,480.43 – 1,491.42
18867 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,478.24 rating
Confidence interval: 1,471.93 – 1,484.56
12578 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
1,473.53 rating
Confidence interval: 1,467.11 – 1,479.94
12746 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,467.19 rating
Confidence interval: 1,461.62 – 1,472.76
17342 votes
- Category
- instruction_following
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
1,464.92 rating
Confidence interval: 1,459.20 – 1,470.63
17044 votes
- Category
- instruction_following
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,489.77 rating
Confidence interval: 1,466.01 – 1,513.54
707 votes
- Category
- japanese
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
1,461.25 rating
Confidence interval: 1,436.73 – 1,485.77
697 votes
- Category
- japanese
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,447.90 rating
Confidence interval: 1,427.10 – 1,468.70
878 votes
- Category
- korean
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
1,444.94 rating
Confidence interval: 1,425.26 – 1,464.63
970 votes
- Category
- korean
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,482.81 rating
Confidence interval: 1,477.51 – 1,488.11
22730 votes
- Category
- longer_query
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
1,477.25 rating
Confidence interval: 1,471.86 – 1,482.65
22607 votes
- Category
- longer_query
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,504.22 rating
Confidence interval: 1,491.82 – 1,516.61
2385 votes
- Category
- math
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
1,486.16 rating
Confidence interval: 1,473.36 – 1,498.97
2209 votes
- Category
- math
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,480.95 rating
Confidence interval: 1,473.59 – 1,488.31
8083 votes
- Category
- multi_turn
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
1,475.97 rating
Confidence interval: 1,468.36 – 1,483.58
7651 votes
- Category
- multi_turn
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,475.72 rating
Confidence interval: 1,471.01 – 1,480.43
27843 votes
- Category
- non_english
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
1,471.92 rating
Confidence interval: 1,467.01 – 1,476.84
27160 votes
- Category
- non_english
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,482.18 rating
Confidence interval: 1,478.31 – 1,486.04
48376 votes
- Category
- overall
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
1,478.16 rating
Confidence interval: 1,474.04 – 1,482.28
47196 votes
- Category
- overall
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,517.14 rating
Confidence interval: 1,495.83 – 1,538.44
802 votes
- Category
- polish
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
1,498.51 rating
Confidence interval: 1,475.84 – 1,521.17
688 votes
- Category
- polish
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,494.46 rating
Confidence interval: 1,485.87 – 1,503.05
5437 votes
- Category
- russian
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
1,493.17 rating
Confidence interval: 1,484.46 – 1,501.88
5376 votes
- Category
- russian
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
Gemini 3.5 Flash
1,481.17 rating
Confidence interval: 1,464.60 – 1,497.73
1425 votes
- Category
- spanish
- Evaluated configuration
- Gemini 3.5 Flash (High)
- Evaluation type
- human preference
1,477.39 rating
Confidence interval: 1,460.29 – 1,494.48
1296 votes
- Category
- spanish
- Evaluated configuration
- Gemini 3.5 Flash (Medium)
- Evaluation type
- human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,526.40 rating
Confidence interval: 1,515.71 – 1,537.09
3441 votes
- Category
- chinese
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
1,525.44 rating
Confidence interval: 1,514.94 – 1,535.94
3611 votes
- Category
- chinese
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,493.22 rating
Confidence interval: 1,487.19 – 1,499.26
13847 votes
- Category
- coding
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
1,487.58 rating
Confidence interval: 1,481.41 – 1,493.75
13614 votes
- Category
- coding
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,469.83 rating
Confidence interval: 1,462.50 – 1,477.15
9481 votes
- Category
- creative_writing
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
1,468.07 rating
Confidence interval: 1,460.89 – 1,475.25
9467 votes
- Category
- creative_writing
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,480.52 rating
Confidence interval: 1,475.37 – 1,485.66
20571 votes
- Category
- english
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
1,476.24 rating
Confidence interval: 1,470.91 – 1,481.56
20074 votes
- Category
- english
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,490.81 rating
Confidence interval: 1,485.74 – 1,495.89
36544 votes
- Category
- exclude_ties
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
1,485.55 rating
Confidence interval: 1,480.17 – 1,490.93
35507 votes
- Category
- exclude_ties
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,494.97 rating
Confidence interval: 1,486.47 – 1,503.46
5582 votes
- Category
- expert
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
1,485.13 rating
Confidence interval: 1,476.59 – 1,493.66
5583 votes
- Category
- expert
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,489.52 rating
Confidence interval: 1,472.99 – 1,506.05
1544 votes
- Category
- french
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
1,475.67 rating
Confidence interval: 1,458.84 – 1,492.49
1500 votes
- Category
- french
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,493.29 rating
Confidence interval: 1,470.78 – 1,515.79
758 votes
- Category
- german
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
1,492.21 rating
Confidence interval: 1,470.12 – 1,514.30
781 votes
- Category
- german
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,488.16 rating
Confidence interval: 1,483.60 – 1,492.71
32403 votes
- Category
- hard_prompts
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
1,484.46 rating
Confidence interval: 1,479.65 – 1,489.26
31530 votes
- Category
- hard_prompts
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,482.49 rating
Confidence interval: 1,476.48 – 1,488.50
13789 votes
- Category
- hard_prompts_english
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
1,479.04 rating
Confidence interval: 1,472.89 – 1,485.18
13343 votes
- Category
- hard_prompts_english
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,466.88 rating
Confidence interval: 1,460.03 – 1,473.73
9395 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
1,458.45 rating
Confidence interval: 1,451.42 – 1,465.48
9103 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,459.13 rating
Confidence interval: 1,452.50 – 1,465.76
12062 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
1,458.81 rating
Confidence interval: 1,452.28 – 1,465.33
11903 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,487.78 rating
Confidence interval: 1,477.57 – 1,498.00
3849 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
1,486.19 rating
Confidence interval: 1,476.35 – 1,496.03
4094 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,494.45 rating
Confidence interval: 1,487.06 – 1,501.84
7792 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
1,494.14 rating
Confidence interval: 1,486.94 – 1,501.34
8004 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,494.31 rating
Confidence interval: 1,482.33 – 1,506.29
2700 votes
- Category
- industry_mathematical
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
1,492.35 rating
Confidence interval: 1,480.71 – 1,503.98
2872 votes
- Category
- industry_mathematical
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,482.90 rating
Confidence interval: 1,472.30 – 1,493.49
3559 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
1,482.29 rating
Confidence interval: 1,471.52 – 1,493.06
3449 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,494.09 rating
Confidence interval: 1,488.77 – 1,499.40
19417 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
1,485.70 rating
Confidence interval: 1,480.20 – 1,491.20
18883 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,477.79 rating
Confidence interval: 1,471.48 – 1,484.10
12654 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
1,472.26 rating
Confidence interval: 1,465.84 – 1,478.67
12817 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,467.14 rating
Confidence interval: 1,461.57 – 1,472.71
17406 votes
- Category
- instruction_following
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
1,464.22 rating
Confidence interval: 1,458.50 – 1,469.94
17076 votes
- Category
- instruction_following
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,486.23 rating
Confidence interval: 1,462.17 – 1,510.30
695 votes
- Category
- japanese
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
1,461.57 rating
Confidence interval: 1,436.57 – 1,486.57
680 votes
- Category
- japanese
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,449.19 rating
Confidence interval: 1,428.25 – 1,470.14
872 votes
- Category
- korean
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
1,445.43 rating
Confidence interval: 1,425.74 – 1,465.13
967 votes
- Category
- korean
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,482.56 rating
Confidence interval: 1,477.26 – 1,487.87
22808 votes
- Category
- longer_query
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
1,476.62 rating
Confidence interval: 1,471.22 – 1,482.02
22668 votes
- Category
- longer_query
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,503.21 rating
Confidence interval: 1,490.81 – 1,515.61
2385 votes
- Category
- math
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
1,486.46 rating
Confidence interval: 1,473.65 – 1,499.27
2210 votes
- Category
- math
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,480.94 rating
Confidence interval: 1,473.57 – 1,488.30
8090 votes
- Category
- multi_turn
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
1,475.87 rating
Confidence interval: 1,468.26 – 1,483.48
7657 votes
- Category
- multi_turn
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,475.45 rating
Confidence interval: 1,470.74 – 1,480.16
27913 votes
- Category
- non_english
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
1,471.03 rating
Confidence interval: 1,466.11 – 1,475.94
27215 votes
- Category
- non_english
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,482.02 rating
Confidence interval: 1,478.15 – 1,485.88
48486 votes
- Category
- overall
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
1,477.42 rating
Confidence interval: 1,473.30 – 1,481.54
47292 votes
- Category
- overall
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,516.54 rating
Confidence interval: 1,495.19 – 1,537.88
799 votes
- Category
- polish
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
1,499.68 rating
Confidence interval: 1,476.88 – 1,522.49
681 votes
- Category
- polish
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,492.43 rating
Confidence interval: 1,483.85 – 1,501.01
5474 votes
- Category
- russian
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
1,491.22 rating
Confidence interval: 1,482.53 – 1,499.91
5416 votes
- Category
- russian
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
Gemini 3.5 Flash
1,479.63 rating
Confidence interval: 1,463.06 – 1,496.20
1430 votes
- Category
- spanish
- Evaluated configuration
- gemini-3.5-flash-high
- Evaluation type
- human preference
1,475.07 rating
Confidence interval: 1,457.97 – 1,492.18
1300 votes
- Category
- spanish
- Evaluated configuration
- gemini-3.5-flash-medium
- Evaluation type
- human preference
Run it locally
Gemini 3.5 Flash
Closed weights. No supported local deployment or GPU requirement is published.
API cost
Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.
Gemini 3.5 Flash
Gemini 3.5 Flash / Pricing tiers
| Provider / scope | Rate | Currency | Amount / unit |
|---|---|---|---|
| Google Vertex AIGemini 3.5 FlashBatch Token tier: 0 – 200,000 | Cached input | USD | 0.075 / 1M tokens |
| Input | USD | 0.75 / 1M tokens | |
| Output | USD | 4.5 / 1M tokens | |
| Google Vertex AIGemini 3.5 FlashBatch Token tier: 200,000 – No stated upper limit | Cached input | USD | 0.075 / 1M tokens |
| Input | USD | 0.75 / 1M tokens | |
| Output | USD | 4.5 / 1M tokens | |
| Google Vertex AIGemini 3.5 FlashStandard Token tier: 0 – 200,000 | Cached input | USD | 0.15 / 1M tokens |
| Input | USD | 1.5 / 1M tokens | |
| Output | USD | 9 / 1M tokens | |
| Google Vertex AIGemini 3.5 FlashStandard Token tier: 200,000 – No stated upper limit | Cached input | USD | 0.15 / 1M tokens |
| Input | USD | 1.5 / 1M tokens | |
| Output | USD | 9 / 1M tokens |
Capabilities
- Context window
- 1,048,576 tokens
- Maximum input
- 1,048,576 tokens*
- Maximum output
- 65,536 tokens
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes*
- Open weights
- No
- Knowledge cutoff
- 2025-01
- API mode
- Chat*
- Declared context window
- 1M*
- Model type
- LLM (multimodal)*
- Declared modalities
- Text, Image, Audio, Video → Text*
- Image input
- Yes*
- PDF input
- Yes*
- Video input
- Yes*
- Audio input
- Yes*
- Audio output
- No*
- Parallel tool calls
- Yes*
- Prompt caching
- Yes*
- System messages
- Yes*
- Tool choice
- Yes*
- Web search
- Yes*
- Model license
- Proprietary
Input modalities
- text
- image
- video
- audio
Output modalities
- text
System configuration
Detailed specifications
Specifications 1 · 13 fields
- api providers
- Google AI Studio, Vertex AI*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- Google*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- context window
- 1M*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- Google*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- developer
- Google*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- Google*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- input price
- 1.5*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- Google*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- intelligence
- 50.2*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- Google*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- license
- Proprietary*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- Google*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- max output
- 65K*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- Google*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- modality
- Text, Image, Audio, Video → Text*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- Google*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- model type
- LLM (multimodal)*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- Google*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- name
- Gemini 3.5 Flash*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- Google*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- open weights
- no*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- Google*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- output price
- 9*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- Google*
- price_unit
- Not reported*
- price_tiers
- Not reported*
- release date
- 2026*
Scope and conditions
- native_context
- metadata
- name
- Convly AI Models Database*
- description
- Hand-verified specifications, licences, API pricing (USD) and local-hardware VRAM requirements for frontier and open-weight AI models.*
- generated
- 2026-09-22T15:41:48+00:00*
- model_count
- 43*
- fields
- slug*
- name*
- developer*
- model_type*
- modality*
- parameters*
- context_window*
- max_output*
- open_weights*
- license*
- release_date*
- input_price*
- output_price*
- price_unit*
- price_tiers*
- vram_q4*
- vram_q4_gb*
- min_gpu*
- intelligence*
- api_providers*
- official_url*
- retired*
- convly_url*
- developer
- Google*
- price_unit
- Not reported*
- price_tiers
- Not reported*
Specifications 2 · 44 fields
- cache read input token cost
- 1.5e-7*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- 7.5e-8*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- 7.5e-8*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- 2.7e-7*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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.*
- deprecation date
- 2027-05-19*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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.*
- google maps grounding cost per query
- 0.014*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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 audio token
- 1.5e-6*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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 audio token priority
- 2.7e-6*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- 1.5e-6*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- 7.5e-7*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- 7.5e-7*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- 2.7e-6*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- vertex_ai-language-models*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- 1,048,576*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- 65,535*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- 65,535*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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 reasoning token
- 9.0e-6*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- 9.0e-6*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- 4.5e-6*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- 4.5e-6*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- 1.62e-5*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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.*
- prompt cache min tokens
- 4,096*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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_low
- 0.014*
- search_context_size_medium
- 0.014*
- search_context_size_high
- 0.014*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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 free requests
- count
- 5,000*
- period
- month*
- shared_group
- gemini-3*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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/completions*
- /v1/batch*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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*
- audio*
- video*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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 audio input
- Yes*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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 audio output
- No*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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 url context
- Yes*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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 video input
- Yes*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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.*
- web search billing unit
- per_query*
Scope and conditions
- native_context
- provider
- vertex_ai-language-models*
- mode
- chat*
- full_native_model_id
- gemini-3.5-flash*
- 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.*
0 selected Compare 0
* Provisional data