Singularity Logs

THE MODEL, IN DETAIL / Google

gemma-4-26b-a4b

google/gemma-4-26b-a4b-itOpen weightsReasoning

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

OpenRouter
Source-linked model intelligenceCatalog added 3 Apr 2026Specifications observed 17 Oct 2026

Text models

#90

Arena rating

Context window

262.1K

235.9K max output tokens

Input price

$0.0675

USD / million input tokens

Output price

$0.225

USD / million output tokens

Inference providers

13

13 provider routes observed

Measured output speed

—

No model-level measurement

01 / PERFORMANCE

A clearer view of capability.

Read the score, understand the context, and explore where this model sits among its peers.

Performance fingerprint

Individual published accuracy scores · not a composite index

At least three published accuracy scores are needed for this view.

Performance meets price

Text models · same published source and version

Higher score · lower cost1,470$01,487.5$2.8751,505$5.751,522.5$8.6251,540$11.5Gemini 4 Argon (High) Text models: 1,532.3 Input: $2/M tokensClaude Opus 5.5 (High) Text models: 1,515.8 Input: $4/M tokensClaude Fable 5.1 (Max) Text models: 1,511.6 Input: $10/M tokensClaude Opus 5 (Max) Text models: 1,507.6 Input: $5/M tokensClaude Opus 5 (High) Text models: 1,502.5 Input: $5/M tokensClaude Opus 4.6 (High) Text models: 1,501.7 Input: $5/M tokensMuse Wonder (Max) Text models: 1,501 Input: $4/M tokensGemini 3.8 Flash (High) Text models: 1,498.9 Input: $0.825/M tokensClaude Opus 4.6 Text models: 1,497.5 Input: $5/M tokensClaude Fable 5 (High) Text models: 1,491.2 Input: $10/M tokensmimo-v2.6-pro Text models: 1,490.7 Input: $0.435/M tokensMuse Spark 1.3 (Max) Text models: 1,490 Input: $1.25/M tokensClaude Opus 4.7 (High) Text models: 1,489.8 Input: $5/M tokensGemini 3.7 Flash (High) Text models: 1,487.3 Input: $0.75/M tokensMuse Spark 1.2 (xHigh) Text models: 1,483.6 Input: $1.25/M tokensClaude Opus 4.7 Text models: 1,482.9 Input: $5/M tokensInput price · USD / million tokens
GoogleAnthropicMetaxiaomi

In good company

Text models · Arena · official dataset

1,532.3
Google
1,515.8
Anthropic
1,511.6
Anthropic
1,507.6
Anthropic
1,502.5
Anthropic
1,501.7
Anthropic
1,501
Meta
1,498.9
Google
1,497.5
Anthropic
1,491.2
Anthropic

416 models in the source cohort. Showing selected nearby models. Evaluation settings can differ.

Evidence, by task.

Coverage is not a capability score.

0published results
0 evaluation sources
ReasoningAwaiting evidence
CodingAwaiting evidence
MathematicsAwaiting evidence
VisionAwaiting evidence
AgenticAwaiting evidence
Long contextAwaiting evidence

Documented features, task evaluations, and preference rankings describe different things. Missing coverage does not imply a model cannot perform a task.

Explore our methodology

Where people rank it

Published rankings for this exact model or configuration. Each source keeps its original metric.

Text modelsArena rating · 15 Oct 2026#901,434.1Confidence interval: 1,426.7–1,441.5Web developmentArena rating · 13 Oct 2026#1071,359.2Confidence interval: 1,342.2–1,376.1VisionArena rating · 9 Oct 2026#551,259.7Confidence interval: 1,253.2–1,266.2

02 / BENCHMARK EXPLORER

The numbers behind the model.

Original results, exact versions, and a direct path to the evidence behind every score.

0 published results

Percentage-based evaluations will appear here when published.

0 percentage-based evaluations. Each benchmark measures a different task; compare results within the same evaluation and protocol.

Artificial Analysis indices

Published in the OpenRouter catalog · source-defined index values

Coding Index39.3
Agentic Index2.9
Intelligence Index16.7

Catalog observation: 17 Oct 2026. Index versions and evaluation settings are not supplied in this feed. These are not Singularity composite scores.

Artificial Analysis

03 / COST & VALUE

Know what your workload costs.

Explore token prices, see where the spend goes, and model a workload of your own.

Input$0.0675per million tokens
Output$0.225per million tokens
Cache read$0.0375per million tokens
Cache write—per million tokens

Workload cost calculator

Change the numbers. See the trade-offs.

Token estimate only. Excludes cache writes, tools, and other provider fees. Actual token usage and provider limits vary.

Your estimated spend

1,000 requests · 11M tokens

$0.9estimated total
Uncached input$0.675
Cached input$0
Output$0.225
Per request$0.0009
Without cache discount$0.9
Estimated cache savings$0

04 / INFERENCE NETWORK

One model. Different ways to run it.

Compare inference routes by price, context, quantization, and reported availability.

13 providers · 13 routes
Provider routes for gemma-4-26b-a4b, observed 17 Oct 2026
Provider / routeInput / MOutput / MCache / MContextOutput limitSpeedLatencyAvailability · 1dRates
DDarkbloomQuantization not disclosed$0.042$0.22$0.021131.1K32.8K——100%
DDekaLLMBF16$0.06$0.33$0.04262.1K235.9K——100%
NNextBitBF16$0.0675$0.225$0.0375262.1K235.9K——100%
DDeepInfraFP8$0.07$0.34—262.1K16.4K——99.86%
IIo NetBF16$0.09$0.31$0.041262.1K235.9K——100%
MMakoraQuantization not disclosed$0.1$0.18$0.05256K128K——99.17%
CCoreWeaveBF16$0.1$0.3$0.05262.1K235.9K——99.93%
CCloudflareQuantization not disclosed$0.1$0.3$0.05256K230.4K——100%
VVeniceBF16$0.13$0.4$0.05256K8.2K——100%
PParasailBF16$0.13$0.4$0.05262.1K235.9K——98.75%
NNovitaBF16$0.13$0.4—262.1K131.1K——100%
SSiliconFlowFP8$0.14$0.4$0.05262.1K235.9K——98.61%
GGoogleQuantization not disclosed$0.15$0.6—262.1K235.9K——85.57%

Snapshot observed 17 Oct 2026. Speed and latency are the reported 30-minute median when available. This is a dated snapshot, not live monitoring.

Provider price comparison

USD per million tokens · input and output rates

InputOutput
Darkbloom
Input
$0.042
Output
$0.22
DekaLLMbf16
Input
$0.06
Output
$0.33
NextBitbf16
Input
$0.0675
Output
$0.225
DeepInfrafp8
Input
$0.07
Output
$0.34
Io Netbf16
Input
$0.09
Output
$0.31
Makora
Input
$0.1
Output
$0.18
CoreWeavebf16
Input
$0.1
Output
$0.3
Cloudflare
Input
$0.1
Output
$0.3
Venicebf16
Input
$0.13
Output
$0.4
Parasailbf16
Input
$0.13
Output
$0.4

Reported availability

Provider availability over the selected observation window

Darkbloom100%
DekaLLM · BF16100%
NextBit · BF16100%
DeepInfra · FP899.86%
Io Net · BF16100%
Makora99.17%
CoreWeave · BF1699.93%
Cloudflare100%
Venice · BF16100%
Parasail · BF1698.75%

Output speed

Reported 30-minute p50 · tokens per second

No provider throughput measurements were returned in this snapshot.

Response latency

Reported 30-minute p50 · seconds

No provider latency measurements were returned in this snapshot.

Context by provider

Actual route limits can differ from the catalog maximum

Darkbloom131.1K
DekaLLM · BF16262.1K
NextBit · BF16262.1K
DeepInfra · FP8262.1K
Io Net · BF16262.1K
Makora256K
CoreWeave · BF16262.1K
Cloudflare256K
Venice · BF16256K
Parasail · BF16262.1K

05 / CAPABILITIES & MODALITIES

What goes in. What comes out.

A map of documented interfaces and API features, separate from benchmark performance.

INPUT MODALITIES

ImageTextVideo
gemma-4-26b-a4bReasoning supported

OUTPUT MODALITIES

Text

Feature support

Listed catalog API parameters and documented pricing features

ReasoningSupported
Tool callingSupported
Tool choiceSupported
Structured outputsSupported
Response formatSupported
Reasoning detailsSupported
Seed controlSupported
Stop sequencesSupported
Prompt cachingSupported
TemperatureSupported

Room to work

Context capacity and completion limits

262.1Ktotal context tokens
Context window
235.9Kmax output

Output tokens share the total context budget. The maximum completion length is a separate limit, and individual provider routes may have smaller limits.

Catalog context
262,144 tokens
Maximum output
235,929 tokens
Top-provider context
262,144 tokens

Features vary by route

Check the provider before depending on a specific API feature.

API feature support by provider
Provider routeReasoningToolsStructured outputResponse formatImplicit caching
DarkbloomSupportedSupportedSupportedSupportedSupported
DekaLLM · BF16SupportedSupportedNot listedSupportedSupported
NextBit · BF16SupportedSupportedSupportedSupportedSupported
DeepInfra · FP8SupportedSupportedSupportedSupportedNot listed
Io Net · BF16SupportedSupportedNot listedNot listedSupported
MakoraSupportedSupportedNot listedSupportedSupported
CoreWeave · BF16SupportedNot listedSupportedSupportedSupported
CloudflareSupportedSupportedNot listedSupportedSupported
Venice · BF16SupportedSupportedSupportedSupportedSupported
Parasail · BF16SupportedNot listedSupportedSupportedSupported
Novita · BF16SupportedSupportedNot listedSupportedNot listed
SiliconFlow · FP8SupportedNot listedSupportedSupportedSupported
GoogleSupportedSupportedSupportedSupportedNot listed

06 / UNDER THE HOOD

The complete specification sheet.

Exact identities, model architecture, limits, and the defaults that shape a request.

Identity & architecture

Developer
Google
Exact identity
gemma-4-26b-a4b
Subject
Model Configuration
Access
Open weights
License
Apache 2.0
Parameters
Not disclosed
Tokenizer
Gemma
Instruction format
Not disclosed

Reasoning & controls

Reasoning
Supported
Mandatory reasoning
No
Reasoning by default
Disabled
Published configuration
Not disclosed
Supported reasoning efforts
Not documented
Default reasoning effort
Not disclosed
API parameters
19
Provider moderation
No
Quantization variants
bf16, fp8

Dates & limits

Catalog added
3 Apr 2026
Knowledge cutoff
Not disclosed
Catalog expiration
Not documented
Specifications observed
17 Oct 2026
Providers observed
17 Oct 2026
Request limits
Provider-specific / not supplied
Canonical catalog ID
google/gemma-4-26b-a4b-it-20260403

API parameters & defaults

Availability is catalog-wide. Defaults can vary across providers.

frequency_penaltySupported · default not supplied
include_reasoningSupported · default not supplied
logit_biasSupported · default not supplied
logprobsSupported · default not supplied
max_tokensSupported · default not supplied
min_pSupported · default not supplied
presence_penaltySupported · default not supplied
reasoningSupported · default not supplied
repetition_penaltySupported · default not supplied
response_formatSupported · default not supplied
seedSupported · default not supplied
stopSupported · default not supplied
structured_outputsSupported · default not supplied
temperatureDefault: 1
tool_choiceSupported · default not supplied
toolsSupported · default not supplied
top_kDefault: 64
top_logprobsSupported · default not supplied
top_pDefault: 0.95

07 / BUILD WITH THIS MODEL

From exploration to your first request.

Use the documented catalog identifier and keep your API key in an environment variable.

Make an API request

const response = await fetch(
  "https://openrouter.ai/api/v1/chat/completions",
  {
    method: "POST",
    headers: {
      Authorization: `Bearer ${process.env.OPENROUTER_API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      "model": "google/gemma-4-26b-a4b-it",
      "messages": [
        {
          "role": "user",
          "content": "Explain the trade-offs in this design."
        }
      ]
    }),
  },
);
if (!response.ok) throw new Error(`HTTP ${response.status}`);
const data = await response.json();
console.log(data.choices[0].message.content);

08 / PROVENANCE & HISTORY

Every number has a story.

Follow the source, check the observation date, and distinguish published results from model specifications.

The source register

Direct links to the underlying records

01
OpenRouter model catalog

Architecture, modalities, parameters, and starting prices

Observed 17 Oct 2026
02
OpenRouter provider routes

Provider limits, prices, availability, and reported measurements

Observed 17 Oct 2026
03
Text models ranking

Arena rating · source-reported ranking

Observed 15 Oct 2026
04
Web development ranking

Arena rating · source-reported ranking

Observed 13 Oct 2026
05
Vision ranking

Arena rating · source-reported ranking

Observed 9 Oct 2026

The observation trail

Recorded events, in chronological order

Added to the model catalog

Catalog creation date, as recorded by OpenRouter.

Model specifications observed

Catalog pricing, limits, and supported parameters captured.

Provider routes observed

13 inference routes in this snapshot.

Observation dates describe when data was captured. They do not represent newly run evaluations or continuous performance monitoring.

Published observation ledger

Historical evidence, with source and version preserved.

No published benchmark observations for this selection. Published preference rankings appear separately above.

09 / A FEW MORE DETAILS

Questions worth asking.

Quick answers, drawn from this model’s connected specifications.

How much does gemma-4-26b-a4b cost?

Catalog starting rates are $0.0675 per million input tokens and $0.225 per million output tokens. Cache-read pricing is $0.0375 per million tokens. Compare provider routes and service tiers above for their specific prices.

How much context can it handle?

262,144 tokens in the catalog context window. The catalog lists a maximum of 235,929 completion tokens. Provider limits can differ.

Does it support tools and structured output?

Tool calling: listed as supported. Structured outputs: listed as supported. See the provider feature matrix for route-specific differences.

How should I interpret these benchmark results?

Read the benchmark name, exact version, metric, source, and model configuration together. Different evaluation settings can change the result. Preference ratings and source-defined composite indices remain separate from task accuracy.

Are these prices and provider measurements live?

This page uses dated source snapshots. Catalog data was observed on 17 Oct 2026. Provider routes were observed on 17 Oct 2026. Missing measurements are not estimated or treated as zero.

KEEP EXPLORING

More from Google.

Explore related identities from the same developer, or take them into a side-by-side comparison.

THE RIGHT MODEL STARTS WITH THE RIGHT CONTEXT.

Put the details side by side.

Explore the trade-offs in a direct model comparison.

Compare gemma-4-26b-a4b
Source-backed evidence. Different tasks. A clearer picture.
AboutMethodologyBenchmark dashboard