Google: Gemma 4 26B A4B

Coming soonQuick Start

Gemma 4 26B A4B is a Mixture-of-Experts model from Google, released 2026-04, with 25.2B total parameters and only 3.8B active per token. It handles video up to 60 seconds at 1fps and is instruction-tuned for near-31B quality at a fraction of the compute cost.

This model is not routed on MirAPI yet — prices shown are the official list prices. Create an account to get notified when it goes live.

Modalities
inImageinTextinVideooutText
Price / 1M
$0.07 / $0.34
Context
262K
Knowledge cutoff

Capabilities

ReasoningVisionTool useLong contextStructured output

Benchmarks

bar = score (0–100) · ▏ median

Scores from vendor reports and public leaderboards. No private evals.

Intelligence Index
General ability
26.1
#56
Coding Index
Code
39.3
#56
Agentic Index
Agentic
11.0
#59
GPQA Diamond
Science QA
74.6
#67
τ-bench (airline)
Agentic tool use
68.6
#54

Showcase

Three fixed prompts, identical for every chat model. Outputs are archived verbatim — copy the prompt to reproduce.

Task prompt · identical for all models
Build a single-file HTML page using three.js from a CDN: a low-poly planet with a tilted ring of ~200 orbiting particles, a soft key light plus rim light, slow auto-rotation, and drag-to-orbit controls. No build tools — one file only.
Archived output
Archive not published yet

Every model will run this exact prompt; the output lands here verbatim, with tokens and per-run cost.

Quick Start

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.mirapi.ai/v1",   # changed
    api_key=os.environ["MIRAPI_API_KEY"],   # changed
)

resp = client.chat.completions.create(
    model="google/gemma-4-26b-a4b-it",
    messages=[{"role": "user", "content": "Hello"}],
)
Wire Gemma 4 26B A4B into your product

1M free tokens to start · no card · OpenAI-compatible, one base_url change

Start free