Gemma 4 26B A4B pricing & benchmarks
Gemma 4 26B A4B is available from Google at $0.090 per million input tokens and $0.300 per million output tokens ($0.143 blended at 3:1). It accepts up to 262,144 tokens of context. Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
Pricing
Per million tokens · OpenRouter
Input$0.090
Output$0.300
Blended (3:1)$0.143
Specification
google/gemma-4-26b-a4b-it
Context window262K
Max output236K
ReleasedApr 2026
LicenceOpen weights
Modalitiesin:text, in:image, in:video, out:text
No independently-run benchmark scores are published for Gemma 4 26B A4B yet. We show nothing rather than reprinting an unverified figure.
Where to run Gemma 4 26B A4B
13 hosts · 3.0× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Weights | Uptime 24h |
|---|---|---|---|---|---|
| Darkbloom ⚠ 131K context, not 262K |
$0.086 | $0.042 / $0.220 | 131K | — | 100.0% |
| Makora | $0.113 | $0.070 / $0.240 | 256K | — | 99.9% |
| DekaLLM | $0.128 | $0.060 / $0.330 | 262K | bf16 | 99.9% |
| DeepInfra | $0.138 | $0.070 / $0.340 | 262K | fp8 | 99.4% |
| NextBit | $0.143 | $0.090 / $0.300 | 262K | bf16 | 100.0% |
| Io Net | $0.145 | $0.090 / $0.310 | 262K | bf16 | 100.0% |
| CoreWeave | $0.150 | $0.100 / $0.300 | 262K | bf16 | 100.0% |
| Cloudflare | $0.150 | $0.100 / $0.300 | 256K | — | 100.0% |
| Venice | $0.198 | $0.130 / $0.400 | 256K | bf16 | 99.9% |
| Parasail | $0.198 | $0.130 / $0.400 | 262K | bf16 | 99.7% |
| Novita | $0.198 | $0.130 / $0.400 | 262K | bf16 | 100.0% |
| SiliconFlow | $0.205 | $0.140 / $0.400 | 262K | fp8 | 98.0% |
| Google (global) | $0.262 | $0.150 / $0.600 | 262K | — | 93.7% |
Host prices and uptime from OpenRouter, synced 2026-10-22. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare Gemma 4 26B A4B
FAQ
How much does Gemma 4 26B A4B cost?
Gemma 4 26B A4B costs $0.090 per million input tokens and $0.300 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.143 per million tokens.
What is Gemma 4 26B A4B 's context window?
Gemma 4 26B A4B accepts up to 262,144 tokens of context, and can generate up to 235,929 output tokens.