Skip to content
  • Models
  • Rankings
  • Ori
Sign Up
Sign Up
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube

By subscribing you agree to receive the OpenRouter newsletter: model usage data, product updates, and research reports, about one email a week. Unsubscribe anytime via the link in every email. See our Privacy Policy.

Favicon for google

Google: Gemma 4 26B A4B (free)

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

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

Price

Free

Context

262K

Released

Apr 3, 2026

Compare
ProvidersPerformanceUptimeBenchmarksAppsActivityFAQExplore

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 Exacto (highest tool-calling accuracy).

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).

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.

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.

Benchmark score summary for Google: Gemma 4 26B A4B (free) (Artificial Analysis)
SourceBenchmarkScore
Artificial AnalysisGemma 4 26B A4B (Non-reasoning) GPQA Diamond71.4%
Artificial AnalysisGemma 4 26B A4B (Non-reasoning) HLE11.5%
Artificial AnalysisGemma 4 26B A4B (Non-reasoning) IFBench45.4%
Artificial AnalysisGemma 4 26B A4B (Non-reasoning) τ²-Bench Telecom40.4%
Artificial AnalysisGemma 4 26B A4B (Non-reasoning) AA-LCR42.3%
Artificial AnalysisGemma 4 26B A4B (Non-reasoning) CritPt0.0%
Artificial AnalysisGemma 4 26B A4B (Non-reasoning) Terminal-Bench Hard25.0%
Artificial AnalysisGemma 4 26B A4B (Non-reasoning) AA-Omniscience Accuracy15.5%
Artificial AnalysisGemma 4 26B A4B (Non-reasoning) AA-Omniscience Non-Hallucination Rate7.9%
Artificial AnalysisGemma 4 26B A4B (Reasoning) Coding Index39.3
Artificial AnalysisGemma 4 26B A4B (Reasoning) GPQA Diamond79.2%
Artificial AnalysisGemma 4 26B A4B (Reasoning) HLE19.3%
Artificial AnalysisGemma 4 26B A4B (Reasoning) IFBench72.4%
Artificial AnalysisGemma 4 26B A4B (Reasoning) τ²-Bench Telecom43.6%
Artificial AnalysisGemma 4 26B A4B (Reasoning) AA-LCR65.7%
Artificial AnalysisGemma 4 26B A4B (Reasoning) GDPval-AA9.7%
Artificial AnalysisGemma 4 26B A4B (Reasoning) CritPt0.0%
Artificial AnalysisGemma 4 26B A4B (Reasoning) SciCode40.0%
Artificial AnalysisGemma 4 26B A4B (Reasoning) Terminal-Bench Hard13.6%
Artificial AnalysisGemma 4 26B A4B (Reasoning) AA-Omniscience Accuracy19.1%
Artificial AnalysisGemma 4 26B A4B (Reasoning) AA-Omniscience Non-Hallucination Rate13.6%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

Quick Start

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Explore more models

AI Models with Vision: Multimodal LLMs for Image UnderstandingCollectionAI Model RankingsRanking

Frequently asked questions

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).

Yes. The pricing shown on this page for Gemma 4 26B A4B (free) is zero, so you are not charged for prompt or completion tokens. Free endpoints are rate limited — see the rate limit docs.

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

Yes. Gemma 4 26B A4B (free) accepts tools and tool_choice for function calling. It supports response_format for JSON output, without JSON-schema enforcement.

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

Gemini 3.8 Flash, Gemini 3.7 Flash, Gemini 3.6 Flash and 24 more are other text models from Google.

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