Gemma 4 26B a4b It API

Google's Gemma 4 26B a4b It, through an OpenAI-compatible API. 2 providers quote it now, and each request goes to the offer with the lowest estimated charge that meets your rules.

Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send gemma-4-26b-a4b-it as the model.
Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

Facts

Model name: gemma-4-26b-a4b-it
Maker: Google
Context window: 262.1K tokens
Input price: $0.050 to $0.065 per million tokens
Output price: $0.290 to $0.300 per million tokens
Providers: 2 independent providers
Regions: global, us

Providers

EmpirioLabs AI: global, $0.050 input and $0.290 output per million tokens, $0.025 cache read per million tokens, 262.1K tokens of context
muna: us, $0.065 input and $0.300 output per million tokens, $0.020 cache read per million tokens, 262.1K tokens of context

Scores

HLE: 19.3, #119 of 273
GPQA: 79.2, #106 of 250
AA-LCR: 65.7, #131 of 237
SciCode: 40.0, #96 of 123
Terminal-Bench Hard: 13.6, #114 of 166
τ²-Bench: 43.6, #112 of 169
IFBench: 72.4, #29 of 178
SimpleQA Verified: 10.4, #121 of 126

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Scores: Epoch AI, 'Capabilities & Benchmarking' (https://epoch.ai/benchmarks)

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemma-4-26b-a4b-it",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Gemma 4 26B a4b It?: Served by intent-router: each job goes to the cheapest healthy upstream for this model.
How much does Gemma 4 26B a4b It cost?: Offers now ask $0.050 to $0.065 per million input tokens and $0.290 to $0.300 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
What is the context length of Gemma 4 26B a4b It?: The largest offer takes 262,144 input tokens. One job can generate up to 65,536 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Gemma 4 26B a4b It do?: Its providers list Vision, Video input, Reasoning budget, Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
What inputs and outputs does Gemma 4 26B a4b It support?: Text · Images · Video → Text.
Which providers serve Gemma 4 26B a4b It?: 2 independent providers quote it now, with 2 offers. The table above ranks them by the cost of a typical job.
How do I call Gemma 4 26B a4b It?: Send "gemma-4-26b-a4b-it" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Gemma 4 26B a4b It listed?: The exchange first listed it on 10/8/2026. This is not its release date.