Gemma 4 26B A4B
The cheapest provider for Gemma 4 26B A4B is Darkbloom at $0.0865 per 1M tokens (blended), charging $0.042 per 1M input and $0.22 per 1M output tokens. 12 providers serve it; the most expensive charges 3.0× as much. Context window: 256K tokens. Prices tracked since Oct 3, 2026.
Best price
$0.0865
at Darkbloom
Input / output
$0.042 / $0.22
per 1M tokens
Providers
12
3.0× spread
7 days
—
best price
30 days
—
best price
Context
256K
tokens
Providers
Active offers ranked by blended price. Bars are relative to the most expensive.
| Provider | Input | Output | Blended | vs cheapest | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
DarkbloomCheapest | $0.042 | $0.22 | $0.0865 | best | |||
| bf16·−25% discount | $0.0675 | $0.225 | $0.107 | +24% | |||
| bf16 | $0.06 | $0.33 | $0.128 | +47% | |||
| fp8 | $0.07 | $0.34 | $0.138 | +59% | |||
| $0.10 | $0.30 | $0.15 | +73% | ||||
| bf16 | $0.10 | $0.30 | $0.15 | +73% | |||
| bf16 | $0.13 | $0.40 | $0.198 | +128% | |||
| bf16 | $0.13 | $0.40 | $0.198 | +128% | |||
| bf16 | $0.13 | $0.40 | $0.198 | +128% | |||
| fp8 | $0.14 | $0.40 | $0.205 | +137% | |||
| bf16 | $0.15 | $0.50 | $0.238 | +175% | |||
Googleglobal | $0.15 | $0.60 | $0.263 | +203% |
- DarkbloomCheapest$0.0865$0.042 in · $0.22 outbest128K ctx100% uptime
- $0.107$0.0675 in · $0.225 out+24%256K ctx99.6% uptimebf16·−25% discount
- $0.128$0.06 in · $0.33 out+47%256K ctx99.9% uptimebf16
- $0.138$0.07 in · $0.34 out+59%256K ctx99.8% uptimefp8
- $0.15$0.10 in · $0.30 out+73%250K ctx99.9% uptime
- $0.15$0.10 in · $0.30 out+73%256K ctx100% uptimebf16
- $0.198$0.13 in · $0.40 out+128%256K ctx99.9% uptimebf16
- $0.198$0.13 in · $0.40 out+128%256K ctx99.8% uptimebf16
- $0.198$0.13 in · $0.40 out+128%250K ctx99.8% uptimebf16
- $0.205$0.14 in · $0.40 out+137%256K ctx96.7% uptimefp8
- $0.238$0.15 in · $0.50 out+175%262K ctx99.2% uptimebf16
- global$0.263$0.15 in · $0.60 out+203%256K ctx97.7% uptime
Blended = (3 × input + output) / 4.
Price history
Hover to compare providers at any point in time. Click a legend item to hide it.
USD per 1M tokens · each step is a price change
Not enough history yet
Tracking since Oct 3, 2026. The chart fills in as new crawls arrive every 6 hours.
Other pricing
Cache, reasoning and per-call fees. Token rates per 1M; others per unit.
| Offered by | Cache read |
|---|---|
| Darkbloom | $0.021 |
| NextBit | $0.0375 |
| DekaLLM | $0.04 |
| Cloudflare, CoreWeave +3 | $0.05 |
| Io Net | $0.15 |
Change log
Every recorded change for this model since Oct 3, 2026.
No changes yet
Tracking since Oct 3, 2026. Price changes, new providers and delistings will show up here.
About this model
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...
- Released
- Apr 3, 2026
- First tracked
- Oct 3, 2026
- Canonical slug
- google/gemma-4-26b-a4b-it-20260403
- Weights
- google/gemma-4-26B-A4B-it