Questions? hello@viberation.devGet supportBlogDocsChangelog
Get started

Gemma

Google's open models — Gemini's research, small enough to self-host.

Gemma is Google DeepMind's open-weight family, built from the same research as Gemini but published so you can download and run it. Sizes run from a few billion parameters up to about thirty, they read text and images, and the current line has a 256K context with a switchable thinking mode. The obvious starting point if you want a capable model on your own machine or on cheap hardware.

At a glance — Gemma 4 26B A4B

Cost
$0.068 in · $0.225 out per 1M tokensBudgetFree version too
Memory
262K tokens — about 400 pages
Reads
Text · Images · Video
Can do
  • Use tools (agents)
  • Structured output
  • Thinking mode
Good at
Coding: better than 38%
Reliability
99.98% uptime, last 24h
Released
Apr 3, 2026
Advanced details
API model ID
google/gemma-4-26b-a4b-it
Free version
google/gemma-4-26b-a4b-it:free
Max output
236K tokens
Cached input
$0.038 per 1M
Tokenizer
Gemma
Coding index
39.3

Providers

The same model, hosted by different companies. OpenRouter picks one per request and falls back to the next if it fails.

ProviderInput /1MOutput /1MCached /1MMax outputUptime 24h
Darkbloom$0.042$0.22—33K99.98%
DekaLLM · bf16$0.06$0.33—236K99.91%
NextBit · bf16$0.068$0.225$0.038236K99.87%
DeepInfra · fp8$0.07$0.34—16K99.79%
Makora$0.08$0.32$0.032128K99.61%
Reka$0.09$0.30$0.05131K99.32%
CoreWeave · bf16$0.10$0.30$0.05236K99.83%
Cloudflare$0.10$0.30—230K99.91%
Venice · bf16$0.13$0.40$0.058K99.27%
Parasail · bf16$0.13$0.40$0.05236K99.25%
Novita · bf16$0.13$0.40—131K99.89%
SiliconFlow · fp8$0.14$0.40$0.05236K97.54%
Io Net · bf16$0.15$0.50$0.15236K99.19%
Google · globalDegraded$0.15$0.60—236K96.22%

Supported parameters

  • frequency_penalty
  • include_reasoning
  • logit_bias
  • logprobs
  • max_tokens
  • min_p
  • presence_penalty
  • reasoning
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_logprobs
  • top_p

Live from OpenRouter, refreshed hourly. Scores from Artificial Analysis.

Key info

Pricing
Open source
Category
Models
Best for
Intermediate
Made by
Google DeepMind
Weights
Open
Good for
Running a capable model on your own machine

More in Models

  • France's frontier lab, with the small models everyone self-hosts.

    Models
  • Meta's current line, built for long multi-agent runs.

    Models
  • The open-weight family everyone else gets benchmarked against.

    Models
  • Z.ai's open-weight family, behind the cheap coding subscriptions.

    Models