NEWMEN
← back to all models

Google: Gemma 4 26B A4B

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

Googleopen-weight262K context9 providersIntelligence 65.0· est.

Cheapest provider

$0.06 / 1M

DekaLLM

Fastest provider (p95)

No throughput data yet — populated as traffic accumulates

Intelligence (estimated)

65.0

Family + generation + popularity + price tier

Per-provider performance

Latency / throughput / uptime / price measured across providers over the last 30 minutes of live traffic. This is what proves “sourced cheapest” — Atlas mode draws on these per call to serve the cheapest path that holds quality.

ProviderQuantInput $/1MOutput $/1MLatency p50 / p95Throughput p50 / p95Uptime 30mSuccess
DekaLLMfull· bf16$0.0600$0.330086.10%
DeepInfraq8· fp8$0.0700$0.3400100.00%
Cloudflareundisclosed$0.1000$0.300099.60%
SiliconFlowq8· fp8$0.1200$0.400098.94%
NextBitfull· bf16$0.1300$0.400099.84%
Novitafull· bf16$0.1300$0.400099.78%
Parasailfull· bf16$0.1300$0.400099.59%
Googleundisclosed$0.1500$0.600090.98%
Venicefull· bf16$0.1625$0.500099.78%

“—” means live telemetry hasn’t accumulated enough recent traffic for that endpoint. “undisclosed” means the provider serves the model but doesn’t expose the quantization label (typically running fp8 / int8 internally).

Intelligence estimate

No public benchmark numbers indexed for this model yet, so the leaderboard score is derived from the catalogue data we sync: model family standing, generation, and live usage rank — applied identically to open- and closed-weight models. The heuristic ceiling sits below confirmed-benchmark frontier models so curated rankings stay clearly on top.

Want a curated score? File a benchmark report and we’ll add it to the next sync.

How Atlas mode sources Google: Gemma 4 26B A4B

  • Strict mode — pin Google: Gemma 4 26B A4B exactly and we pass it straight through, sourced from the cheapest provider above. The same model, no substitutions — currently DekaLLM at $0.06/1M.
  • Atlas mode — the default. Each call is auto-optimized for the cheapest path that holds quality, at least 5% off going direct from call one and climbing as it ramps. You always see which model served the call and exactly what you saved — thumbs-down anything you don’t like for a full refund.