Google: Gemma 4 26B A4B
google/gemma-4-26b-a4b-it
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 measured across providers over the last 30 minutes of live traffic. Atlas’s router weighs these per call (with the eval-gate signal) when picking a variant for Standard and Batch tiers.
| Provider | Quant | Input $/1M | Output $/1M | Latency p50 / p95 | Throughput p50 / p95 | Uptime 30m | Success |
|---|---|---|---|---|---|---|---|
| DekaLLM | full· bf16 | $0.0600 | $0.3300 | — | — | 87.44% | — |
| DeepInfra | q8· fp8 | $0.0700 | $0.3400 | — | — | 99.89% | — |
| Cloudflare | undisclosed | $0.1000 | $0.3000 | — | — | 99.69% | — |
| SiliconFlow | q8· fp8 | $0.1200 | $0.4000 | — | — | 98.28% | — |
| Novita | full· bf16 | $0.1300 | $0.4000 | — | — | 99.89% | — |
| Parasail | full· bf16 | $0.1300 | $0.4000 | — | — | 97.57% | — |
| undisclosed | $0.1500 | $0.6000 | — | — | 99.57% | — | |
| NextBit | full· bf16 | $0.1500 | $0.4000 | — | — | 98.42% | — |
| Venice | full· bf16 | $0.1625 | $0.5000 | — | — | 97.44% | — |
“—” 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.
- ·google gemma lg family base
Want a curated score? File a benchmark report and we’ll add it to the next sync.
How Atlas routes Google: Gemma 4 26B A4B
- Realtime tier — direct passthrough at the upstream’s native precision. Best for hard latency / quality guarantees.
- Standard tier — Atlas picks the cheapest provider variant whose quantization has stayed green on your operation’s eval gates. For Google: Gemma 4 26B A4B that’s currently DekaLLM at $0.06/1M.
- Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.