Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. Models
  2. Text
  3. Google

Gemma 4 26B A4B

Google's Gemma 4 26B A4B instruction-tuned model built for scalable reasoning, coding, long-context, and multimodal workflows. This route is tuned for faster direct answers while preserving multimodal and structured output support. Requests containing video cost $0.10 per million input tokens and $0.40 per million output tokens.

  • Reasoning
  • Vision
  • Video Input
  • Structured Output

Added Apr 2, 2026

Model weights

Pricing

Auto routing · per 1M tokens
Input
$0.0354
Output
$0.0943
Cache read
$0.0177
Compare provider prices

Specifications

Context window
262.1K
Max output
131.1K
Parameters
26B / 4B
Total / active

Benchmarks

Sourced from LMArena.

Arena Score

1437.5

Overall Rank

#101 / 421

Votes

6,075

Confidence Interval

1430.0 - 1444.9

Category Scores

Coding

#110 / 416

1,441 votes

1482.5

Math

#55 / 404

387 votes

1469.3

Longer Query

#98 / 399

1,714 votes

1447.1

Creative Writing

#112 / 419

1,003 votes

1399.6

Instruction Following

#82 / 421

1,730 votes

1438.1

Hard Prompts

#97 / 421

3,463 votes

1461.2

Additional Categories
18

Industry Mathematical

#51 / 401

309 votes

1478.8

Industry Legal And Government

#72 / 393

415 votes

1463.6

Chinese

#75 / 395

523 votes

1493.8

French

#75 / 301

263 votes

1473.1

Expert

#84 / 371

452 votes

1476.0

Hard Prompts English

#88 / 419

1,268 votes

1471.5

Industry Business And Management And Financial Operations

#93 / 414

1,114 votes

1444.5

Multi Turn

#95 / 419

1,137 votes

1448.5

Russian

#96 / 385

895 votes

1437.6

English

#99 / 421

2,234 votes

1449.1

Industry Entertainment And Sports And Media

#99 / 419

1,107 votes

1406.6

Exclude Ties

#102 / 421

4,164 votes

1434.1

Industry Software And It Services

#102 / 421

2,206 votes

1476.1

Industry Life And Physical And Social Science

#104 / 419

928 votes

1454.2

Non English

#105 / 421

3,841 votes

1423.1

Industry Writing And Literature And Language

#116 / 420

1,393 votes

1406.6

Spanish

#126 / 303

202 votes

1415.9

Industry Medicine And Healthcare

#137 / 390

388 votes

1435.9

Published 2026-11-09 · Matched as Gemma 4 26B A4B · CC BY 4.0

LMArena Dataset

Leaderboard results

BenchmarkScoreRank on NanoGPT
Epoch AI Benchmarking Hub

Epoch AI data, CC BY 4.0 · Updated Nov 12, 2026

Epoch Capabilities Index

141.6

#90 of 115

GPQA Diamond

73.2%

#90 of 119

OTIS Mock AIME 2024–2025

82.2%

#80 of 121

EQ-Bench

EQ-Bench data, MIT · Updated Nov 12, 2026

Creative Writing v3

1305

#73 of 96

Longform Writing

50.7

#70 of 97

EQ-Bench 3

1455

#24 of 49

UGI Leaderboard

UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026

UGI Score

25.2

#119 of 149

UGI Willingness

1.8

#132 of 149

UGI Writing

43.8

#70 of 149

Filtered and ranked to models on NanoGPT.

Providers

Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)

Auto
Auto (ZDR)
$0.0354$0.0943$0.0177N/AN/A
Auto
Auto (Anonymized)
$0.0354$0.0943$0.0177N/AN/A
PrimeIntellect
PrimeIntellect
BF16
UNK
$0.0115$0.0346$0.00525N/AN/A
Darkbloom
Darkbloom
INT8
GLB
$0.042$0.157N/AN/AN/A
DeepInfra
DeepInfra
FP8
US
$0.0735$0.357$0.0105N/AN/A
Akash
Akash
FP4
GLB
$0.0735$0.252$0.0483N/AN/A
io.net
io.net
BF16
US
$0.0851$0.293$0.0387N/AN/A
NextBit
NextBit
BF16
EU
$0.0945$0.315$0.0525N/AN/A
CoreWeave
CoreWeave
BF16
US
$0.105$0.315$0.0525N/AN/A
Kitani
Kitani
INT4
GLB
$0.113$0.378$0.0567N/AN/A
Uomi
Uomi
FP8
GLB
$0.116$0.408N/AN/AN/A
Aoru AI
Aoru AI
FP8
KR
$0.126$0.399$0.063N/AN/A
Novita
Novita
BF16
US
$0.136$0.42N/AN/AN/A
Parasail
Parasail
BF16
US
$0.136$0.42$0.0525N/AN/A
SiliconFlow
SiliconFlow
FP8
SG
$0.147$0.42$0.0525N/AN/A
Google Vertex
Google Vertex
US
$0.157$0.63N/AN/AN/A
Privacy:ZDR, prompts not retainedNo training on promptsRetention and training unclearRetains prompts, training unclear
Batch API
ProviderInputOutputCached input
Aoru AI
Aoru AIgoogle/gemma-4-26b-a4b-it
$0.06/M$0.19/M$0.03/M

Related text models

Compare Gemma 4 26B A4B with similar models from the same provider or model family.

Gemma 4 26B A4B Cybersecurity

google/gemma-4-26b-a4b-it-cybersecurity

Gemma 4 26B A4B Cybersecurity is a cybersecurity-focused variant based on the uncensored model, with provider moderation for illegal activities. It supports optional reasoning, image understanding, tool calling, and a 262,144-token context window.

Gemma 4 26B A4B Thinking

google/gemma-4-26b-a4b-it:thinking

Google's Gemma 4 26B A4B instruction-tuned model with structured reasoning for more deliberate coding, multimodal analysis, and long-context problem solving. Requests containing video cost $0.10 per million input tokens and $0.40 per million output tokens.

Gemma 4 31B

google/gemma-4-31b-it

Google's Gemma 4 31B instruction-tuned model for heavier reasoning, coding, agentic workflows, and long-context multimodal understanding. This route keeps tokenizer thinking disabled for faster direct answers. Requests containing video cost $0.14 per million input tokens and $0.40 per million output tokens.

Gemma 4 31B Thinking

google/gemma-4-31b-it:thinking

Google's Gemma 4 31B instruction-tuned model with thinking explicitly enabled, exposing reasoning traces for complex multimodal and coding workflows. Requests containing video cost $0.14 per million input tokens and $0.40 per million output tokens.

DiffusionGemma

google/diffusiongemma

DiffusionGemma is a high-speed diffusion-based version of Gemma 4 26B A4B. It supports optional reasoning and a 262,144-token context window. Temperature, min-p, seed, minimum output tokens, logit bias, bad words, and allowed token IDs are unavailable; omit these parameters to use native diffusion sampling.

Gemma 4 26B A4B Chimera X Heretic

gemma-4-26b-a4b-it-chimeraxheretic

Chimera X Heretic is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.