How much does Gemma 4 26B A4B cost?

Gemma 4 26B A4B costs $0.02/M input tokens and $0.059/M output tokens, with separate rates for Cache Read at $0.01/M tokens.

What is the context length of Gemma 4 26B A4B?

Gemma 4 26B A4B has a 262,144 token context window. It supports up to 32,768 completion tokens.

Does Gemma 4 26B A4B support tool calling and structured outputs?

Yes. Gemma 4 26B A4B accepts tools and tool_choice for function calling on 12 of the 15 providers serving it, and requests that send tools are routed to those providers. It also supports structured outputs via a JSON schema in response_format.

What inputs and outputs does Gemma 4 26B A4B support?

Gemma 4 26B A4B accepts images, text, and video as input and returns text.

Which providers serve Gemma 4 26B A4B?

Gemma 4 26B A4B is served by 15 providers on OpenRouter: Prime Intellect, Darkbloom, DekaLLM, io.net, NextBit, AkashML, DeepInfra, Makora and 7 more. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

When was Gemma 4 26B A4B released?

Gemma 4 26B A4B was released on April 3, 2026.

Google: Gemma 4 26B A4B

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

Model weights

Compare

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 a fraction of the compute cost. Supports multimodal input including text, images, and video (up to 60s at 1fps). Features a 256K token context window, native function calling, configurable thinking/reasoning mode, and structured output support. Released under Apache 2.0.

Modalities

In / out price

$0.02 / $0.059per 1M

Context

262K

Released

Apr 3, 2026

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput


	$0.09	$0.28	$0.049	0.55s	107 tok/s	99.90%
25% off	$0.09$0.0675	$0.30$0.225	$0.05$0.0375	0.39s	70 tok/s	100.00%
	$0.014	$0.043	$0.007	0.55s	68 tok/s	98.42%
	$0.07	$0.34	--	0.38s	60 tok/s	99.96%
	$0.13	$0.40	$0.05	0.46s	83 tok/s	100.00%
	$0.067	$0.29	$0.039	0.75s	62 tok/s	100.00%
	$0.14	$0.40	$0.05	0.99s	74 tok/s	100.00%
	$0.10	$0.30	$0.05	0.77s	45 tok/s	100.00%
	$0.10	$0.30	$0.05	0.27s	31 tok/s	99.24%
	$0.07	$0.24	$0.046	0.40s	127 tok/s	97.84%
	$0.04	$0.15	$0.01	0.40s	66 tok/s	99.90%
	$0.06	$0.33	$0.04	0.79s	69 tok/s	96.93%
	$0.13	$0.40	$0.05	0.88s	72 tok/s	100.00%
	$0.15	$0.60	--	2.58s	28 tok/s	93.48%
	$0.13	$0.40	--	0.69s	90 tok/s	94.02%

Input $0.09Output $0.28
107 tok/s99.90% uptime
Input $0.0675Output $0.225
25% off
70 tok/s100.00% uptime
Input $0.014Output $0.043
68 tok/s98.42% uptime
Input $0.07Output $0.34
60 tok/s99.96% uptime
Input $0.13Output $0.40
83 tok/s100.00% uptime
Input $0.067Output $0.29
62 tok/s100.00% uptime
Input $0.14Output $0.40
74 tok/s100.00% uptime
Input $0.10Output $0.30
45 tok/s100.00% uptime
Input $0.10Output $0.30
31 tok/s99.24% uptime
Input $0.07Output $0.24
127 tok/s97.84% uptime
Input $0.04Output $0.15
66 tok/s99.90% uptime
Input $0.06Output $0.33
69 tok/s96.93% uptime
Input $0.13Output $0.40
72 tok/s100.00% uptime
Input $0.15Output $0.60
28 tok/s93.48% uptime
Input $0.13Output $0.40
90 tok/s94.02% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.06999/M tokens

Output

$0.2751/M tokens

Gemma 4 26B A4B — Price history

Price history

No effective price data for this selection

$0.0286	$0.0867	8.7%	7.4%
$0.0381	$0.1464	5.4%	5.6%
$0.0554	$0.3275	22.3%	2.9%
$0.0598	$0.2230	25.1%	28.4%
$0.0628	$0.2881	14.7%	4.6%
$0.0664	$0.2382	14.7%	3.5%
$0.0698	$0.3375	0.0%	4.8%
$0.0833	$0.2781	16.0%	29.1%
$0.0862	$0.2972	27.0%	2.3%
$0.0966	$0.2995	6.6%	5.3%
$0.1071	$0.3987	28.5%	0.6%
$0.1113	$0.3977	23.1%	2.4%
$0.1253	$0.3984	16.2%	0.4%
$0.1299	$0.3995	0.0%	1.7%
$0.1498	$0.5995	60.4%	1.0%

Effective in $0.0286Effective out $0.0867
Token share
7.4%
Effective in $0.0381Effective out $0.1464
Token share
5.6%
Effective in $0.0554Effective out $0.3275
Token share
2.9%
Effective in $0.0598Effective out $0.2230
Token share
28.4%
Effective in $0.0628Effective out $0.2881
Token share
4.6%
Effective in $0.0664Effective out $0.2382
Token share
3.5%
Effective in $0.0698Effective out $0.3375
Token share
4.8%
Effective in $0.0833Effective out $0.2781
Token share
29.1%
Effective in $0.0862Effective out $0.2972
Token share
2.3%
Effective in $0.0966Effective out $0.2995
Token share
5.3%
Effective in $0.1071Effective out $0.3987
Token share
0.6%
Effective in $0.1113Effective out $0.3977
Token share
2.4%
Effective in $0.1253Effective out $0.3984
Token share
0.4%
Effective in $0.1299Effective out $0.3995
Token share
1.7%
Effective in $0.1498Effective out $0.5995
Token share
1.0%

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

127tok/s

P50, best across providers

Latency

0.27s

P50, best provider

Latency / throughput

AutoExacto benchmarks

GPQA DiamondTAU-BenchCoreWeave77.3%--Parasail77.1%--SiliconFlow76.8%--Prime Intellect79.0%68.4%Cloudflare80.3%65.9%

+11 more providers

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

99.72%

Availability over the last 3 days

Last 72 hours

Availability 99.72%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.76%

Without Routing

95.90%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Google: Gemma 4 26B A4B (Artificial Analysis)
Source	Benchmark	Score
Artificial Analysis	Gemma 4 26B A4B (Non-reasoning) GPQA Diamond	71.4%
Artificial Analysis	Gemma 4 26B A4B (Non-reasoning) HLE	11.5%
Artificial Analysis	Gemma 4 26B A4B (Non-reasoning) IFBench	45.4%
Artificial Analysis	Gemma 4 26B A4B (Non-reasoning) τ²-Bench Telecom	40.4%
Artificial Analysis	Gemma 4 26B A4B (Non-reasoning) AA-LCR	42.3%
Artificial Analysis	Gemma 4 26B A4B (Non-reasoning) CritPt	0.0%
Artificial Analysis	Gemma 4 26B A4B (Non-reasoning) Terminal-Bench Hard	25.0%
Artificial Analysis	Gemma 4 26B A4B (Reasoning) Coding Index	39.3
Artificial Analysis	Gemma 4 26B A4B (Reasoning) Agentic Index	2.9
Artificial Analysis	Gemma 4 26B A4B (Reasoning) GPQA Diamond	79.2%
Artificial Analysis	Gemma 4 26B A4B (Reasoning) HLE	19.3%
Artificial Analysis	Gemma 4 26B A4B (Reasoning) IFBench	72.4%
Artificial Analysis	Gemma 4 26B A4B (Reasoning) τ²-Bench Telecom	43.6%
Artificial Analysis	Gemma 4 26B A4B (Reasoning) AA-LCR	65.7%
Artificial Analysis	Gemma 4 26B A4B (Reasoning) τ-Bench Banking	12.0%
Artificial Analysis	Gemma 4 26B A4B (Reasoning) GDPval-AA	3.6%
Artificial Analysis	Gemma 4 26B A4B (Reasoning) CritPt	0.0%
Artificial Analysis	Gemma 4 26B A4B (Reasoning) SciCode	40.0%
Artificial Analysis	Gemma 4 26B A4B (Reasoning) Terminal-Bench Hard	13.6%
Artificial Analysis	Gemma 4 26B A4B (Reasoning) Terminal-Bench 2.1	39.0%

Not currently available through EU in-region routing. In-region routing docs

More models from Google

Gemini 4 Hydrogen

Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than Gemini 4 Carbon. It takes text, image, audio, video and file input, supports long decode of up to 1M output tokens through continuation, and controls thinking depth with low, medium, high and xhigh reasoning effort.

Text1.0M context$1.50 / $7.50

Gemini 4 Hydrogen (batch)

Text1.0M context$0.75 / $3.75

Gemini Decision 1

Gemini Decision 1 is Google's model for the Decisions API. It answers structured questions about an input state (true/false, multiple choice with up to 255 options, and score with up to 255 levels) and returns a confidence for every answer, plus a legend and probabilities for score questions.

It reads text, images, audio, video, and documents (PDF, CSV, and Office files) sent inline as base64 or by public URL. Every question needs instructions.

Decisions$0.10 / $0

Gemini 4 Carbon

Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. It takes text, image, audio, video and file input, supports long decode of up to 1M output tokens through continuation, and controls thinking depth with low, medium and high reasoning effort.

Text1.0M context$2 / $10

Gemini 4 Carbon (batch)

Text1.0M context$1 / $5

Gemini Omni 1.2 Flash

Gemini Omni 1.2 Flash is Google's native multimodal video generation and editing model, the successor to Gemini Omni 1.1 Flash. It generates clips up to 15 seconds long with native audio in 16:9 or 9:16, from 360p drafts up to 4K, and supports text-to-video, image-to-video, first and last frame interpolation, subject and video references with improved reference management, and editing or extending an uploaded video. Multi-turn editing and extension of a prior generation is supported through previous_job_id.

Note: video generation is only supported through the Video Generation API. See the guide: https://openrouter.ai/docs/guides/overview/multimodal/video-generation

Text131K context$1.50 / $9

Gemini Omni 1.1 Flash

Gemini Omni 1.1 Flash is Google's native multimodal video generation and editing model, the generally available successor to Gemini Omni Flash Preview. It is suited for text-to-video, image-to-video, first and last frame interpolation, subject and video references (up to three reference clips), and editing or extending an uploaded video, and generates clips from 360p drafts up to 4K with native audio in 16:9 or 9:16. Multi-turn editing and extension of a prior generation is supported through previous_job_id, up to 40 seconds of total video.

Note: video generation is only supported through the Video Generation API. See the guide: https://openrouter.ai/docs/guides/overview/multimodal/video-generation

Text131K context$1.50 / $9

Gemini 4 Argon

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across long, multi-step tasks and to turn long documents mixing text, tables, charts and images into a single grounded output. It leads the Vals Index across finance, legal, coding and tax work, and supports long decode of up to 1M output tokens in a single response.

Text1.0M context$2 / $10

Gemini 4 Argon (batch)

Text1.0M context$1 / $5

Nano Banana 2.1

Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization, mask- and ink-based editing, and factual accuracy, and renders photorealistic skin tones, detailed materials, lighting, and coherent backgrounds. It accepts text and image inputs, returns images with optional text, and supports 1K, 2K, and 4K output plus extended aspect ratios via the image_config API Parameter.

Image66K context$1.50 / $30

Gemini 3.5 Transcribe

Gemini 3.5 Transcribe is a speech-to-text model from Google. It is suited for synchronous transcription that needs word-level timestamps or speaker diarization, with support for up to eight speakers. Audio can be up to one hour, or 30 minutes when timestamps or diarization are enabled.

Transcription$2 / $12

Gemini 3.8 Flash Lite TTS

Gemini 3.8 Flash Lite TTS is a text-to-speech model from Google and the fast, high-throughput member of the 3.8 TTS family alongside Gemini 3.8 Flash TTS. It is suited for conversational voice-agent pipelines, high-volume read-aloud, and voice replication workloads where latency and cost matter more than maximum expressiveness.

It accepts the same speech configuration as Gemini 3.1 Flash TTS Preview, including the 30 prebuilt studio voices, and supports Google's Voice Design and Voice Replication through voice_... identifiers.

Speech$0.50 / $6

Gemini 3.8 Flash TTS

Gemini 3.8 Flash TTS is a text-to-speech model from Google and the successor to Gemini 3.1 Flash TTS Preview. It is the creative tier of the 3.8 TTS family, suited for narration, character work, and multi-speaker dialogue where voice fidelity, acting nuance, and regional dialect coverage matter more than latency.

It accepts the same speech configuration as its predecessor, including the 30 prebuilt studio voices, and supports Google's Voice Design (custom voices from a text description) and Voice Replication (voices cloned from a short sample) through voice_... identifiers.

Speech$0.50 / $9

Gemini 3.8 Flash

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

Text1.0M context$0.75 / $3.75

Gemini 3.8 Flash (batch)

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

Text1.0M context$0.375 / $1.875

Gemini 3.7 Flash

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.

Text1.0M context$0.75 / $3.75

Gemini 3.7 Flash (batch)

Text1.0M context$0.375 / $1.875

Gemini 3.6 Flash

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and less hedging, while reducing token use and the number of model calls needed to complete a task.

Text1.0M context$0.75 / $3.75

Gemini 3.6 Flash (batch)

Text1.0M context$0.375 / $1.875

Gemini 3.5 Flash Lite

Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.

Text1.0M context$0.30 / $2.50

Google: Gemma 4 26B A4B

Providers