---
id: "google/gemma-4-26b-a4b-it"
also: ["google/gemma-4-26b-a4b-it-20260403", "google/gemma-4-26B-A4B-it", "hf/google/gemma-4-26B-A4B-it", "requesty/google/gemma-4-26b-a4b-it", "vercel/google/gemma-4-26b-a4b-it"]
cheapest_list_usd_per_m: "0.011 in, 0.032 out, at primeintellect/bf16 on openrouter"
cheapest_effective_usd_per_m: "0.0103 in, 0.029 out, at primeintellect/bf16 on openrouter"
context: 262144
max_output: 128000
input: ["image", "text", "video"]
output: ["text"]
released: "2026-04-03"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_completion_tokens", "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"]
endpoints: 28
gateways: "openrouter (15), vercel (6), hf (4), requesty (3)"
no_training: 20
trains: 2
retains_prompts: 3
coding: 39.3000
agentic: 2.9000
---
# Google: Gemma 4 26B A4B 

Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on small models) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages.