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 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.

  • Reasoning
  • Vision
  • Video Input
  • Structured Output

Added Apr 2, 2026

Model weights

Pricing

Auto routing · per 1M tokens
Input
$0.021
Output
$0.064
Cache read
$0.011
Compare provider prices

Specifications

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

Benchmarks

Sourced from Vectara.

Hallucination Rate

5.2%

Hallucination Rate: 5.2
Better than 87% of models compared

Factual Consistency

94.8%

Factual Consistency: 94.8
Better than 87% of models compared

Answer Rate

99.8%

Answer Rate: 99.8
Better than 64% of models compared

Avg Summary Length

Average generated summary length

67.1

Last updated 2026-10-22 · Matched as google/gemma-4-26b-a4b-it

Vectara Leaderboard

Leaderboard results

These leaderboards tested Gemma 4 26B A4B, another version of this model.

BenchmarkScoreRank on NanoGPT
Epoch AI Benchmarking Hub

Epoch AI data, CC BY 4.0 · Updated Nov 14, 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 14, 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)
$0.0675$0.225$0.0375N/AN/A
Auto
Auto (Anonymized)
$0.021$0.064$0.011N/AN/A
PrimeIntellect
PrimeIntellect
BF16
UNK
$0.0221$0.0672$0.0115N/AN/A
Darkbloom
Darkbloom
INT4
GLB
$0.042$0.157N/AN/AN/A
io.net
io.net
BF16
US
$0.0703$0.305$0.041N/AN/A
NextBit
NextBit
25% off
BF16
EU
$0.0945$0.0709$0.315$0.236$0.0525$0.0394N/AN/A
Akash
Akash
FP4
GLB
$0.0735$0.252$0.0483N/AN/A
CoreWeave
CoreWeave
BF16
US
$0.105$0.315$0.0525N/AN/A
Uomi
Uomi
FP8
GLB
$0.116$0.408N/AN/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 unclear
Batch API
ProviderInputOutputCached input
Auto
Autogoogle/gemma-4-26b-a4b-it:thinking
$0.021/M$0.064/M$0.011/M

Batch rows for this model use normal routing and cost the same as standard API requests. Set provider in a row to choose a provider.

Related text models

Compare Gemma 4 26B A4B Thinking 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

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

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.

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.