geekradar
Int
Explore GeekRadar

More to explore

Good gear All topics About us Say hello
GeekRadar / The comparison desk
COMPARE.
AI models
google

Gemini 3.5 Flash Lite

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.

Gemini 3.5 Flash Lite 145.0* Gemini 3.5 Flash-Lite · 95% interval 142.6–146.3

Human preference · Arena

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

Gemini 3.5 Flash Lite 1435.5 Gemini 3.5 Flash-Lite · 95% interval 1431.0–1439.9 · 35,740 votes · 2026-10-28

Model performance

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

Gemini 3.5 Flash Lite

Radar task score

Unrated

2/4 core tests · not enough evidence

3 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

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

Gemini 3.5 Flash Lite 75.8*% Approx. 95% interval: 69.8–81.7%

Novel problem solving

Mystery Game Puzzles · 25%

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

Gemini 3.5 Flash Lite 19.0*% Approx. 95% interval: 11.3–26.7%

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

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

Gemini 3.5 Flash Lite Not available

Factual answers

SimpleQA Verified · 25%

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

Gemini 3.5 Flash Lite Not available

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.

Gemini 3.5 Flash Lite 60.0*% Approx. 95% interval: 45.5–74.5%

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.

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

Gemini 3.5 Flash Lite

1,466.93 rating

Confidence interval: 1,454.96 – 1,478.90

2728 votes

Category
chinese
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,453.02 rating

Confidence interval: 1,446.14 – 1,459.91

9922 votes

Category
coding
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,421.16 rating

Confidence interval: 1,413.20 – 1,429.11

7405 votes

Category
creative_writing
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,438.39 rating

Confidence interval: 1,432.42 – 1,444.37

14610 votes

Category
english
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,429.49 rating

Confidence interval: 1,423.70 – 1,435.28

26808 votes

Category
exclude_ties
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,433.81 rating

Confidence interval: 1,424.10 – 1,443.53

4183 votes

Category
expert
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,450.17 rating

Confidence interval: 1,431.19 – 1,469.14

1098 votes

Category
french
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,450.34 rating

Confidence interval: 1,427.33 – 1,473.35

660 votes

Category
german
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,441.20 rating

Confidence interval: 1,435.97 – 1,446.44

23729 votes

Category
hard_prompts
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,440.59 rating

Confidence interval: 1,433.62 – 1,447.56

9635 votes

Category
hard_prompts_english
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,423.07 rating

Confidence interval: 1,415.13 – 1,431.01

6600 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,415.11 rating

Confidence interval: 1,407.81 – 1,422.40

9216 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,430.61 rating

Confidence interval: 1,419.22 – 1,442.00

3038 votes

Category
industry_legal_and_government
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,451.35 rating

Confidence interval: 1,443.07 – 1,459.62

5844 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,433.73 rating

Confidence interval: 1,420.26 – 1,447.20

2036 votes

Category
industry_mathematical
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,438.70 rating

Confidence interval: 1,426.54 – 1,450.87

2597 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,450.53 rating

Confidence interval: 1,444.49 – 1,456.57

14365 votes

Category
industry_software_and_it_services
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,427.99 rating

Confidence interval: 1,420.91 – 1,435.07

9708 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,419.89 rating

Confidence interval: 1,413.56 – 1,426.22

12867 votes

Category
instruction_following
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,427.89 rating

Confidence interval: 1,401.61 – 1,454.17

594 votes

Category
japanese
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,407.57 rating

Confidence interval: 1,384.53 – 1,430.61

717 votes

Category
korean
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,435.09 rating

Confidence interval: 1,429.12 – 1,441.06

17043 votes

Category
longer_query
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,435.83 rating

Confidence interval: 1,421.20 – 1,450.47

1626 votes

Category
math
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,445.26 rating

Confidence interval: 1,436.82 – 1,453.71

5877 votes

Category
multi_turn
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,427.45 rating

Confidence interval: 1,422.12 – 1,432.79

21126 votes

Category
non_english
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,435.48 rating

Confidence interval: 1,431.02 – 1,439.94

35740 votes

Category
overall
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,436.55 rating

Confidence interval: 1,411.11 – 1,461.99

523 votes

Category
polish
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,444.95 rating

Confidence interval: 1,435.23 – 1,454.68

4041 votes

Category
russian
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

Gemini 3.5 Flash Lite

1,441.62 rating

Confidence interval: 1,421.96 – 1,461.27

958 votes

Category
spanish
Evaluated configuration
Gemini 3.5 Flash-Lite
Evaluation type
human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,467.33 rating

Confidence interval: 1,455.39 – 1,479.27

2750 votes

Category
chinese
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,452.69 rating

Confidence interval: 1,445.80 – 1,459.58

9924 votes

Category
coding
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,420.06 rating

Confidence interval: 1,412.12 – 1,428.01

7473 votes

Category
creative_writing
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,437.91 rating

Confidence interval: 1,431.94 – 1,443.88

14626 votes

Category
english
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,428.15 rating

Confidence interval: 1,422.36 – 1,433.94

26885 votes

Category
exclude_ties
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,434.02 rating

Confidence interval: 1,424.30 – 1,443.74

4189 votes

Category
expert
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,450.82 rating

Confidence interval: 1,431.79 – 1,469.85

1100 votes

Category
french
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,453.85 rating

Confidence interval: 1,430.71 – 1,477.00

654 votes

Category
german
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,440.30 rating

Confidence interval: 1,435.06 – 1,445.54

23813 votes

Category
hard_prompts
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,439.92 rating

Confidence interval: 1,432.95 – 1,446.89

9647 votes

Category
hard_prompts_english
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,421.92 rating

Confidence interval: 1,413.97 – 1,429.87

6602 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,413.76 rating

Confidence interval: 1,406.47 – 1,421.05

9265 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,431.21 rating

Confidence interval: 1,419.85 – 1,442.56

3060 votes

Category
industry_legal_and_government
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,451.15 rating

Confidence interval: 1,442.87 – 1,459.42

5856 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,433.23 rating

Confidence interval: 1,419.76 – 1,446.69

2041 votes

Category
industry_mathematical
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,438.14 rating

Confidence interval: 1,425.98 – 1,450.30

2610 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,449.99 rating

Confidence interval: 1,443.95 – 1,456.03

14375 votes

Category
industry_software_and_it_services
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,426.99 rating

Confidence interval: 1,419.92 – 1,434.07

9785 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,419.00 rating

Confidence interval: 1,412.66 – 1,425.33

12907 votes

Category
instruction_following
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,427.14 rating

Confidence interval: 1,400.48 – 1,453.79

583 votes

Category
japanese
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,407.39 rating

Confidence interval: 1,384.33 – 1,430.46

715 votes

Category
korean
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,434.57 rating

Confidence interval: 1,428.60 – 1,440.54

17112 votes

Category
longer_query
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,433.22 rating

Confidence interval: 1,418.56 – 1,447.88

1624 votes

Category
math
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,444.00 rating

Confidence interval: 1,435.54 – 1,452.46

5866 votes

Category
multi_turn
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,426.47 rating

Confidence interval: 1,421.13 – 1,431.80

21221 votes

Category
non_english
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,434.52 rating

Confidence interval: 1,430.06 – 1,438.98

35851 votes

Category
overall
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,436.99 rating

Confidence interval: 1,411.51 – 1,462.46

522 votes

Category
polish
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,443.33 rating

Confidence interval: 1,433.62 – 1,453.04

4098 votes

Category
russian
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

Gemini 3.5 Flash Lite

1,440.99 rating

Confidence interval: 1,421.30 – 1,460.67

963 votes

Category
spanish
Evaluated configuration
gemini-3.5-flash-lite
Evaluation type
human preference

Run it locally

Inference · memory estimate

Gemini 3.5 Flash Lite

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

API cost

USD / month

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

Gemini 3.5 Flash Lite

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
2026-03
API mode
Chat*
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
  • pdf

Output modalities

  • text

System configuration

Detailed specifications

Specifications · 42 fields
cache read input token cost
3.0e-8*
Scope and conditions
native_context
provider
vertex_ai-language-models*
mode
chat*
full_native_model_id
gemini-3.5-flash-lite*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
cache read input token cost batches
1.5e-8*
Scope and conditions
native_context
provider
vertex_ai-language-models*
mode
chat*
full_native_model_id
gemini-3.5-flash-lite*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
cache read input token cost flex
1.5e-8*
Scope and conditions
native_context
provider
vertex_ai-language-models*
mode
chat*
full_native_model_id
gemini-3.5-flash-lite*
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
5.4e-8*
Scope and conditions
native_context
provider
vertex_ai-language-models*
mode
chat*
full_native_model_id
gemini-3.5-flash-lite*
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
2027-07-21*
Scope and conditions
native_context
provider
vertex_ai-language-models*
mode
chat*
full_native_model_id
gemini-3.5-flash-lite*
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-lite*
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
3.0e-7*
Scope and conditions
native_context
provider
vertex_ai-language-models*
mode
chat*
full_native_model_id
gemini-3.5-flash-lite*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
input cost per token batches
1.5e-7*
Scope and conditions
native_context
provider
vertex_ai-language-models*
mode
chat*
full_native_model_id
gemini-3.5-flash-lite*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
input cost per token flex
1.5e-7*
Scope and conditions
native_context
provider
vertex_ai-language-models*
mode
chat*
full_native_model_id
gemini-3.5-flash-lite*
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
5.4e-7*
Scope and conditions
native_context
provider
vertex_ai-language-models*
mode
chat*
full_native_model_id
gemini-3.5-flash-lite*
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-lite*
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-lite*
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
65,536*
Scope and conditions
native_context
provider
vertex_ai-language-models*
mode
chat*
full_native_model_id
gemini-3.5-flash-lite*
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
65,536*
Scope and conditions
native_context
provider
vertex_ai-language-models*
mode
chat*
full_native_model_id
gemini-3.5-flash-lite*
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-lite*
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
2.5e-6*
Scope and conditions
native_context
provider
vertex_ai-language-models*
mode
chat*
full_native_model_id
gemini-3.5-flash-lite*
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
2.5e-6*
Scope and conditions
native_context
provider
vertex_ai-language-models*
mode
chat*
full_native_model_id
gemini-3.5-flash-lite*
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
1.25e-6*
Scope and conditions
native_context
provider
vertex_ai-language-models*
mode
chat*
full_native_model_id
gemini-3.5-flash-lite*
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
1.25e-6*
Scope and conditions
native_context
provider
vertex_ai-language-models*
mode
chat*
full_native_model_id
gemini-3.5-flash-lite*
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
4.5e-6*
Scope and conditions
native_context
provider
vertex_ai-language-models*
mode
chat*
full_native_model_id
gemini-3.5-flash-lite*
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-lite*
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-lite*
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-lite*
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-lite*
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-lite*
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-lite*
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-lite*
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-lite*
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-lite*
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-lite*
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-lite*
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-lite*
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-lite*
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-lite*
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
vertex_ai-language-models*
mode
chat*
full_native_model_id
gemini-3.5-flash-lite*
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-lite*
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-lite*
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-lite*
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-lite*
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-lite*
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-lite*
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-lite*
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