Google: Gemma 4 26B A4B
by GoogleGoogle: Gemma 4 26B A4B is a large language model from Google. It costs $0.090 per million input tokens and $0.300 per million output tokens. Its context window is 262K tokens.
- Input / 1M tokens
- $0.090
- Output / 1M tokens
- $0.300
- Cached input / 1M
- $0.050
- Context window
- 262K
On repeated prefixes
tokens
Who serves it cheapest
11 hosts serve Gemma 4 26B A4B . Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| DarkbloomCheapest | $0.042 | $0.220 | 131K | - | 99.9% |
| DekaLLMbf16 | $0.060 | $0.330 | 262K | - | 99.9% |
| DeepInfrafp8 | $0.070 | $0.340 | 262K | - | 99.8% |
| NextBitbf16 | $0.090 | $0.300 | 262K | - | 99.8% |
| Cloudflare | $0.100 | $0.300 | 256K | - | 99.9% |
| Makora | $0.100 | $0.340 | 262K | - | 99.0% |
| Venicebf16 | $0.130 | $0.400 | 256K | - | 99.1% |
| Parasailbf16 | $0.130 | $0.400 | 262K | - | 99.2% |
| Novitabf16 | $0.130 | $0.400 | 262K | - | 99.6% |
| SiliconFlowfp8 | $0.140 | $0.400 | 262K | - | 97.4% |
| $0.150 | $0.600 | 262K | - | 97.7% |
The spread between Darkbloom and Google is 3.0× for identical weights. Quantization and context limits differ, so check both columns before switching.
Benchmarks
Independent scores published alongside the catalogue.
- Coding index
- 39.3
About Gemma 4 26B A4B
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...
Specifications
| Model ID | google/gemma-4-26b-a4b-it |
|---|---|
| Provider | |
| Context window | 262K tokens |
| Max output | 236K tokens |
| Input modalities | image, text, video |
| Output modalities | text |
| Knowledge cutoff | - |
| Open weights | Yes - google/gemma-4-26B-A4B-it |
| Released | April 3, 2026 |
Cheaper alternatives
Models that cost less than Gemma 4 26B A4B while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does Google: Gemma 4 26B A4B cost?
$0.090 per million input tokens and $0.300 per million output tokens. Cached input reads cost $0.050 per million tokens.
What is the context window of Google: Gemma 4 26B A4B ?
262K tokens, with up to 236K tokens of output per request.
Which provider serves Google: Gemma 4 26B A4B cheapest?
Darkbloom at $0.042 per million input tokens - 3.0× cheaper than Google, the most expensive of the 11 hosts serving it.
Confirm against the source: Google official pricing.