GeekRadar / The comparison desk

COMPARE.

AI models

google

Gemini 3.8 Flash

AI model Released Sep 2, 2026

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 3.8 Flash 157.6^* Gemini 3.8 Flash · 95% interval 155.5–160.9

Human preference · Arena

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

Gemini 3.8 Flash 1498.5 Gemini 3.8 Flash (High) · 95% interval 1494.1–1502.9 · 47,803 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 3.8 Flash

Tested configuration Radar task score

70.1^* / 100

4/4 core tests · experimental v1

7 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

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

Gemini 3.8 Flash 95.4^*% Approx. 95% interval: 92.6–98.1% · 2026-09-02

Novel problem solving

Mystery Game Puzzles · 25%

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

Gemini 3.8 Flash 47.0^*% Approx. 95% interval: 37.2–56.8% · 2026-09-02

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

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

Gemini 3.8 Flash 68.4^*% Approx. 95% interval: 63.0–73.8% · 2026-09-02

Factual answers

SimpleQA Verified · 25%

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

Gemini 3.8 Flash 69.7^*% Approx. 95% interval: 66.9–72.5% · 2026-09-02

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 3.8 Flash 98.9^*% Approx. 95% interval: 97.2–100.0% · 2026-09-02

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.

Gemini 3.8 Flash 22.0^*% Approx. 95% interval: 9.1–34.8% · 2026-09-02

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.

Gemini 3.8 Flash 31.7^*% Approx. 95% interval: 20.0–43.3% · 2026-09-10

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

Recorded results

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

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

Gemini 3.8 Flash

1,550.45 rating

Confidence interval: 1,540.12 – 1,560.77

3978 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,509.19 rating

Confidence interval: 1,502.58 – 1,515.80

12376 votes

Oct 28, 2026

Category: coding
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,491.18 rating

Confidence interval: 1,483.87 – 1,498.48

10581 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,498.26 rating

Confidence interval: 1,492.42 – 1,504.11

18714 votes

Oct 28, 2026

Category: english
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,514.33 rating

Confidence interval: 1,508.43 – 1,520.23

35338 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,526.24 rating

Confidence interval: 1,517.42 – 1,535.06

5549 votes

Oct 28, 2026

Category: expert
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,494.43 rating

Confidence interval: 1,478.25 – 1,510.61

1682 votes

Oct 28, 2026

Category: french
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,506.58 rating

Confidence interval: 1,484.40 – 1,528.76

760 votes

Oct 28, 2026

Category: german
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,508.28 rating

Confidence interval: 1,503.01 – 1,513.55

30731 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,504.12 rating

Confidence interval: 1,497.52 – 1,510.72

12039 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,480.11 rating

Confidence interval: 1,472.72 – 1,487.50

8607 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,481.29 rating

Confidence interval: 1,474.48 – 1,488.09

12638 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,499.53 rating

Confidence interval: 1,489.40 – 1,509.65

4087 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,523.36 rating

Confidence interval: 1,515.72 – 1,531.01

7897 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,519.09 rating

Confidence interval: 1,507.34 – 1,530.84

2891 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,506.18 rating

Confidence interval: 1,494.91 – 1,517.45

3353 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,506.57 rating

Confidence interval: 1,500.64 – 1,512.51

17809 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,495.22 rating

Confidence interval: 1,488.61 – 1,501.83

13501 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,492.67 rating

Confidence interval: 1,486.59 – 1,498.76

17179 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,508.38 rating

Confidence interval: 1,485.95 – 1,530.80

887 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,477.06 rating

Confidence interval: 1,454.55 – 1,499.56

844 votes

Oct 28, 2026

Category: korean
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,508.56 rating

Confidence interval: 1,502.69 – 1,514.44

21802 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,529.90 rating

Confidence interval: 1,517.42 – 1,542.38

2496 votes

Oct 28, 2026

Category: math
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,503.67 rating

Confidence interval: 1,495.63 – 1,511.70

7190 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,491.50 rating

Confidence interval: 1,486.21 – 1,496.79

29077 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,498.49 rating

Confidence interval: 1,494.06 – 1,502.92

47803 votes

Oct 28, 2026

Category: overall
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,499.46 rating

Confidence interval: 1,476.98 – 1,521.95

692 votes

Oct 28, 2026

Category: polish
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,516.41 rating

Confidence interval: 1,507.90 – 1,524.91

6256 votes

Oct 28, 2026

Category: russian
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

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

Gemini 3.8 Flash

1,486.98 rating

Confidence interval: 1,471.52 – 1,502.44

1649 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: Gemini 3.8 Flash (High)
Evaluation type: human preference

Run it locally

Inference · memory estimate

Gemini 3.8 Flash

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.

Gemini 3.8 Flash

Provider offer

Gemini 3.8 Flash / Pricing tiers 5

Provider / scope	Rate	Currency	Amount / unit
GoogleGemini 3.8 FlashStandard	Cached input	USD	0.075 / 1M tokens
	Input	USD	0.75 / 1M tokens
	Output	USD	3.75 / 1M tokens
Google Vertex AIGemini 3.8 FlashBatch Token tier: 0 – 200,000	Cached input	USD	0.0375 / 1M tokens
	Input	USD	0.375 / 1M tokens
	Output	USD	1.875 / 1M tokens
Google Vertex AIGemini 3.8 FlashBatch Token tier: 200,000 – No stated upper limit	Cached input	USD	0.0375 / 1M tokens
	Input	USD	0.375 / 1M tokens
	Output	USD	1.875 / 1M tokens
Google Vertex AIGemini 3.8 FlashStandard Token tier: 0 – 200,000	Cached input	USD	0.075 / 1M tokens
	Input	USD	0.75 / 1M tokens
	Output	USD	3.75 / 1M tokens
Google Vertex AIGemini 3.8 FlashStandard Token tier: 200,000 – No stated upper limit	Cached input	USD	0.075 / 1M tokens
	Input	USD	0.75 / 1M tokens
	Output	USD	3.75 / 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
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 · 43 fields

cache read input token cost

7.5e-8^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.8-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

3.75e-8^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.8-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

3.75e-8^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.8-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

1.35e-7^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.8-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-3.8-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

7.5e-7^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.8-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

3.75e-7^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.8-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

3.75e-7^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.8-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

1.35e-6^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.8-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-3.8-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-3.8-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

65,536^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.8-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

65,536^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.8-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-3.8-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

3.75e-6^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.8-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

3.75e-6^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.8-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

1.875e-6^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.8-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

1.875e-6^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.8-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

6.75e-6^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.8-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

4,096.0^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.8-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-3.8-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-3.8-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-3.8-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-3.8-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-3.8-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-3.8-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-3.8-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-3.8-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 minimal reasoning effort

No^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.8-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-3.8-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-3.8-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-3.8-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-3.8-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-3.8-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-3.8-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 sampling params

No^*

Scope and conditions

native_context

provider: vertex_ai-language-models^*
mode: chat^*
full_native_model_id: gemini-3.8-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-3.8-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-3.8-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-3.8-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-3.8-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-3.8-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-3.8-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-3.8-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.^*

* Provisional data