GeekRadar / The comparison desk

COMPARE.

AI models

google

Gemma 3 27B IT

AI model Released Mar 12, 2025

API mode: Chat^*
Context window: 131,072 tokens
Maximum output: 131,072 tokens
Open weights: Yes

Capability & preference

Human preference · Arena

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

Gemma 3 27B IT 1357.7 Gemma 3 27B IT · 95% interval 1354.1–1361.4 · 46,670 votes · 2026-10-28

Model performance

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

Gemma 3 27B IT

Tested configuration Radar task score

Unrated

1/4 core tests · not enough evidence

2 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

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

Gemma 3 27B IT 47.7^*% Approx. 95% interval: 42.4–53.0% · 2026-08-27

Novel problem solving

Mystery Game Puzzles · 25%

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

Gemma 3 27B IT Not available

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

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

Gemma 3 27B IT Not available

Factual answers

SimpleQA Verified · 25%

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

Gemma 3 27B IT 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.

Gemma 3 27B IT 22.5^*% Approx. 95% interval: 12.2–32.8% · 2026-08-27

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

Recorded results

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

Test version

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

Gemma 3 27B IT

1,346.14 rating

Confidence interval: 1,334.94 – 1,357.34

2852 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,321.67 rating

Confidence interval: 1,314.83 – 1,328.51

8023 votes

Oct 28, 2026

Category: coding
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,345.21 rating

Confidence interval: 1,337.57 – 1,352.84

6305 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,376.51 rating

Confidence interval: 1,371.85 – 1,381.16

23047 votes

Oct 28, 2026

Category: english
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,321.25 rating

Confidence interval: 1,316.15 – 1,326.34

32666 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,303.57 rating

Confidence interval: 1,290.94 – 1,316.19

2263 votes

Oct 28, 2026

Category: expert
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,368.57 rating

Confidence interval: 1,344.92 – 1,392.23

657 votes

Oct 28, 2026

Category: french
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,361.94 rating

Confidence interval: 1,344.63 – 1,379.26

1208 votes

Oct 28, 2026

Category: german
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,340.13 rating

Confidence interval: 1,335.00 – 1,345.26

17704 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,353.05 rating

Confidence interval: 1,346.47 – 1,359.64

8933 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,359.47 rating

Confidence interval: 1,351.86 – 1,367.08

6497 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,319.84 rating

Confidence interval: 1,313.01 – 1,326.66

8000 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,375.26 rating

Confidence interval: 1,363.69 – 1,386.82

2663 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,383.00 rating

Confidence interval: 1,375.93 – 1,390.07

7870 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,327.30 rating

Confidence interval: 1,317.24 – 1,337.35

3211 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,390.82 rating

Confidence interval: 1,378.30 – 1,403.33

2344 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,353.84 rating

Confidence interval: 1,348.32 – 1,359.36

14081 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,347.18 rating

Confidence interval: 1,341.06 – 1,353.31

10588 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,320.47 rating

Confidence interval: 1,314.82 – 1,326.12

12501 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,286.88 rating

Confidence interval: 1,267.96 – 1,305.79

1052 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,307.54 rating

Confidence interval: 1,286.97 – 1,328.11

889 votes

Oct 28, 2026

Category: korean
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,332.98 rating

Confidence interval: 1,325.59 – 1,340.36

6674 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,312.19 rating

Confidence interval: 1,302.72 – 1,321.65

3588 votes

Oct 28, 2026

Category: math
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,344.55 rating

Confidence interval: 1,337.06 – 1,352.05

6732 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,334.26 rating

Confidence interval: 1,329.63 – 1,338.88

23613 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,357.72 rating

Confidence interval: 1,354.06 – 1,361.37

46670 votes

Oct 28, 2026

Category: overall
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,345.06 rating

Confidence interval: 1,333.31 – 1,356.82

2828 votes

Oct 28, 2026

Category: polish
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,348.76 rating

Confidence interval: 1,339.08 – 1,358.43

3436 votes

Oct 28, 2026

Category: russian
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,348.94 rating

Confidence interval: 1,328.94 – 1,368.95

893 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: Gemma 3 27B IT
Evaluation type: human preference

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

Gemma 3 27B IT

1,346.51 rating

Confidence interval: 1,335.31 – 1,357.71

2849 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,321.90 rating

Confidence interval: 1,315.06 – 1,328.75

8021 votes

Oct 15, 2026

Category: coding
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,345.49 rating

Confidence interval: 1,337.86 – 1,353.13

6308 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,376.55 rating

Confidence interval: 1,371.89 – 1,381.20

23044 votes

Oct 15, 2026

Category: english
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,321.38 rating

Confidence interval: 1,316.29 – 1,326.47

32660 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,303.78 rating

Confidence interval: 1,291.17 – 1,316.40

2263 votes

Oct 15, 2026

Category: expert
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,368.13 rating

Confidence interval: 1,344.48 – 1,391.79

657 votes

Oct 15, 2026

Category: french
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,361.59 rating

Confidence interval: 1,344.27 – 1,378.90

1206 votes

Oct 15, 2026

Category: german
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,340.26 rating

Confidence interval: 1,335.13 – 1,345.39

17699 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,353.04 rating

Confidence interval: 1,346.46 – 1,359.62

8932 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,359.51 rating

Confidence interval: 1,351.90 – 1,367.13

6495 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,320.07 rating

Confidence interval: 1,313.25 – 1,326.90

8004 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,375.03 rating

Confidence interval: 1,363.46 – 1,386.60

2661 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,383.00 rating

Confidence interval: 1,375.93 – 1,390.07

7867 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,327.31 rating

Confidence interval: 1,317.26 – 1,337.37

3211 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,391.08 rating

Confidence interval: 1,378.55 – 1,403.60

2342 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,354.05 rating

Confidence interval: 1,348.53 – 1,359.56

14077 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,347.31 rating

Confidence interval: 1,341.19 – 1,353.43

10592 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,320.52 rating

Confidence interval: 1,314.87 – 1,326.17

12503 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,286.72 rating

Confidence interval: 1,267.83 – 1,305.60

1052 votes

Oct 15, 2026

Category: japanese
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,307.66 rating

Confidence interval: 1,287.09 – 1,328.23

889 votes

Oct 15, 2026

Category: korean
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,333.15 rating

Confidence interval: 1,325.77 – 1,340.54

6675 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,312.15 rating

Confidence interval: 1,302.68 – 1,321.61

3587 votes

Oct 15, 2026

Category: math
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,344.59 rating

Confidence interval: 1,337.10 – 1,352.09

6728 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,334.40 rating

Confidence interval: 1,329.78 – 1,339.03

23612 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,357.80 rating

Confidence interval: 1,354.14 – 1,361.46

46666 votes

Oct 15, 2026

Category: overall
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,345.12 rating

Confidence interval: 1,333.38 – 1,356.87

2830 votes

Oct 15, 2026

Category: polish
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,348.89 rating

Confidence interval: 1,339.21 – 1,358.56

3433 votes

Oct 15, 2026

Category: russian
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

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

Gemma 3 27B IT

1,348.87 rating

Confidence interval: 1,328.87 – 1,368.88

893 votes

Oct 15, 2026

Category: spanish
Evaluated configuration: gemma-3-27b-it
Evaluation type: human preference

Run it locally

Inference · memory estimate

Gemma 3 27B IT

51.1 GiB checkpoint tensor payload · 27.43 B stored tensor elements · BF16

Stored tensors can include buffers and repeated shared weights. A verified unique parameter count is unavailable. Checkpoint size is not the memory required to run the model.

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.

Gemma 3 27B IT

Provider offer

Gemma 3 27B IT / Pricing tiers 1

Provider / scope	Rate	Currency	Amount / unit
DeepInfragoogle/gemma-3-27b-itStandard	Input	USD	0.08 / 1M tokens
DeepInfragoogle/gemma-3-27b-itStandard	Output	USD	0.16 / 1M tokens

Capabilities

Context window: 131,072 tokens
Maximum input: 128,000 tokens^*
Maximum output: 131,072 tokens
Reasoning: No
Tool calling: Yes
Structured output: Yes^*
Open weights: Yes
Knowledge cutoff: 2024-08
API mode: Chat^*
Image input: Yes^*
Audio input: No^*
System messages: Yes^*
Model license: Gemma
Checkpoint tensor payload: 51.10 GiB

Input modalities

text
image

Output modalities

text

System configuration

Detailed specifications

Specifications · 19 fields

deprecation date

2027-03-30^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: google.gemma-3-27b-it^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per token

2.3e-7^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: google.gemma-3-27b-it^*
pricing_scope: Literal source field names 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

1.2e-7^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: google.gemma-3-27b-it^*
pricing_scope: Literal source field names 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

1.2e-7^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: google.gemma-3-27b-it^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per token priority

4.0e-7^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: google.gemma-3-27b-it^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

litellm provider

bedrock_converse^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: google.gemma-3-27b-it^*
pricing_scope: Literal source field names 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

128,000^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: google.gemma-3-27b-it^*
pricing_scope: Literal source field names 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

8,000^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: google.gemma-3-27b-it^*
pricing_scope: Literal source field names 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

8,000^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: google.gemma-3-27b-it^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

mode

chat^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: google.gemma-3-27b-it^*
pricing_scope: Literal source field names 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

3.8e-7^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: google.gemma-3-27b-it^*
pricing_scope: Literal source field names 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

1.9e-7^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: google.gemma-3-27b-it^*
pricing_scope: Literal source field names 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

1.9e-7^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: google.gemma-3-27b-it^*
pricing_scope: Literal source field names 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

6.7e-7^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: google.gemma-3-27b-it^*
pricing_scope: Literal source field names 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

No^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: google.gemma-3-27b-it^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports function calling

Yes^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: google.gemma-3-27b-it^*
pricing_scope: Literal source field names 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: bedrock_converse^*
mode: chat^*
full_native_model_id: google.gemma-3-27b-it^*
pricing_scope: Literal source field names 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: bedrock_converse^*
mode: chat^*
full_native_model_id: google.gemma-3-27b-it^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports vision

Yes^*

Scope and conditions

native_context

provider: bedrock_converse^*
mode: chat^*
full_native_model_id: google.gemma-3-27b-it^*
pricing_scope: Literal source field names 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