Gemma 4 26B A4B
Launched 2026-04-02 · Listed on OpenRouter 2026-04-03
Prices updated . Benchmarks updated .
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...
You send / 1M
$0.076
tokens in
It replies / 1M
$0.255
tokens out
Context
256K
tokens it can read at once
Typical request
$0.0002
1,000 words in, 400 out
Benchmarks
| Benchmark | Score | Kind | Date | Source |
|---|---|---|---|---|
| Epoch Capabilities Index | 141.9 | Independent | 2026-04-02 | Epoch AI |
| GPQA Diamond | 73.2% | Independent | 2026-08-06 | Epoch AI |
| OTIS Mock AIME | 82.2% | Independent | 2026-08-28 | Epoch AI |
| CritPt | 0.0% | Independent | 2026-04-02 | CritPt, republished by Epoch AI |
| Arena Elo (text) | 1,434 | Independent | 2026-10-28 | LMArena |
| Arena Elo (webdev) | 1,359 | Independent | 2026-10-28 | LMArena |
| Arena Elo (vision) | 1,260 | Independent | 2026-10-19 | LMArena |
Rankings on this site use the Epoch Capabilities Index, an independent composite. Lab-reported rows are the lab's own figures and are kept separate.
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| AkashML · fp4 | $0.070 | $0.240 | 97% | Read |
| NextBit · bf16 | $0.076 | $0.255 | 100% | Read |
| PrimeIntellect · bf16 | $0.086 | $0.257 | 100% | Read |
| Makora | $0.090 | $0.280 | 100% | n/a |
| Io Net · bf16 | $0.067 | $0.290 | 100% | Read |
| CoreWeave · bf16 | $0.100 | $0.300 | 100% | Read |
| Cloudflare | $0.100 | $0.300 | 100% | Read |
| DekaLLM · bf16 | $0.060 | $0.330 | 99% | Read |
| DeepInfra · fp8 | $0.070 | $0.340 | 100% | Read |
| SiliconFlow · fp8 | $0.140 | $0.400 | 99% | Read |
| Venice · bf16 | $0.130 | $0.400 | 100% | Read |
| Parasail · bf16 | $0.130 | $0.400 | 100% | Read |
| Novita · bf16 | $0.130 | $0.400 | 100% | Read |
| $0.150 | $0.600 | 99% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: image, text, video
- Writes: text
- Weights: Open weights
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 33K tokens
- Repeated text is billed at $0.043 per 1M (prompt caching)
Compare with
Appears in
Estimate your monthly cost with Gemma 4 26B A4B
Sources and licenses
- OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
- Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
- models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
- Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
- LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
- Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
- What a score measures: the benchmark guide.
