Gemma 4 26B A4B IT
Summary
Gemma 4 26B A4B IT is an open-weight language model from Google DeepMind, released on 2 Apr 2026. It accepts text and images and generates text, with a 262K-token context window and up to 33K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.09 per million input tokens and $0.30 per million output tokens (OpenRouter), across 10 providers we track.
Open Gemma instruction model for efficient chat and self-hosted deployments
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Google DeepMind |
|---|---|
| Release date | 2 Apr 2026 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | apache-2.0 [Hugging Face] |
| Parameters | 25.8B [Hugging Face] |
| Context window | 262K (262,144 tokens) [models.dev] |
| Max output | 33K tokens [models.dev] |
| Knowledge cutoff | Apr 2025 [models.dev] |
| Input | Text and images [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | Yes [models.dev] |
| Hugging Face | google/gemma-4-26B-A4B-it [Hugging Face] |
Gemma 4 26B A4B IT API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| Gemini API gemma-4-26b-a4b-it | Free | Free | – | 262K | models.dev, 18 Nov 2026 |
| DeepInfra google/gemma-4-26B-A4B-it | $0.07 | $0.34 | – | 262K | models.dev, 18 Nov 2026 |
| OpenRouter google/gemma-4-26b-a4b-it | $0.09 | $0.30 | $0.05 | 262K | OpenRouter, 18 Nov 2026 |
| Cloudflare Workers AI @cf/google/gemma-4-26b-a4b-it | $0.10 | $0.30 | $0.05 | 256K | models.dev, 18 Nov 2026 |
| Amazon Bedrock google.gemma-4-26b-a4b | $0.13 | $0.40 | – | 262K | models.dev, 18 Nov 2026 |
| Hugging Face Inference Providers google/gemma-4-26B-A4B-it | $0.13 | $0.40 | – | 262K | models.dev, 18 Nov 2026 |
| Novita AI google/gemma-4-26b-a4b-it | $0.13 | $0.40 | – | 262K | models.dev, 18 Nov 2026 |
| SiliconFlow google/gemma-4-26B-A4B-it | $0.14 | $0.40 | $0.05 | 262K | models.dev, 18 Nov 2026 |
| Google Vertex AI google/gemma-4-26b-a4b-it-maas | $0.15 | $0.60 | $0.01 | 262K | models.dev, 18 Nov 2026 |
| Vercel AI Gateway google/gemma-4-26b-a4b-it | $0.15 | $0.60 | $0.01 | 262K | models.dev, 18 Nov 2026 |
Running Gemma 4 26B A4B IT locally
Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 16 GB | 17 GB | 18 GB |
| Q8_0 (8-bit) | 27 GB | 29 GB | 30 GB |
| FP16 / BF16 (16-bit) | 52 GB | 53 GB | 54 GB |
At 4-bit with an 8K conversation, Gemma 4 26B A4B IT needs about 17 GB, so it fits on a graphics card with 24 GB or more, such as the NVIDIA GeForce RTX 3090 24 GB. Check your own hardware, or see Best GPU for local LLMs on our sister site AIPCs.
Frequently asked questions
What is the context window of Gemma 4 26B A4B IT?
Gemma 4 26B A4B IT has a context window of 262,144 tokens (262K) and can generate up to 32,768 tokens in a single response, according to models.dev.
How much does the Gemma 4 26B A4B IT API cost?
Through Gemini API, Gemma 4 26B A4B IT costs Free per million input tokens and Free per million output tokens. Prices last verified 18 Nov 2026.
Is Gemma 4 26B A4B IT open source?
Gemma 4 26B A4B IT is an open-weight model: its weights are published on Hugging Face as google/gemma-4-26B-A4B-it under the apache-2.0 license. Check the license terms before commercial use.
When was Gemma 4 26B A4B IT released?
Google DeepMind released Gemma 4 26B A4B IT on 2 Apr 2026, according to models.dev.
Which providers offer Gemma 4 26B A4B IT?
We track Gemma 4 26B A4B IT on 10 providers: Gemini API, DeepInfra, OpenRouter, Cloudflare Workers AI, Amazon Bedrock, Hugging Face Inference Providers, Novita AI, SiliconFlow, Google Vertex AI, Vercel AI Gateway.
How much VRAM does Gemma 4 26B A4B IT need?
About 17 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 29 GB at 8-bit. The 4-bit model fits on a graphics card with 24 GB or more, such as the NVIDIA GeForce RTX 3090 24 GB. These are estimates from the model's published parameter count and architecture.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| NVIDIA Nemotron 3 Super 120B A12B | NVIDIA | 11 Mar 2026 | 262K | $0.07 | $0.40 | Open |
| Step 3.5 Flash | StepFun | 29 Jan 2026 | 262K | $0.10 | $0.30 | Open |
| Qwen/Qwen3.5-9B | Alibaba (Qwen) | 23 Feb 2026 | 262K | $0.10 | $0.15 | Open |
| Mistral Small 4 | Mistral AI | 16 Mar 2026 | 262K | $0.15 | $0.60 | Open |
| Ministral 14B | Mistral AI | 2 Dec 2025 | 262K | $0.20 | $0.20 | Open |
| Hy3 preview | Tencent (Hunyuan) | 20 Apr 2026 | 262K | $0.18 | $0.60 | Open |
Change history
- OpenRouter price changed: input $0.07 → $0.09, output $0.23 → $0.30 per 1M tokens
- OpenRouter price changed: input $0.09 → $0.07, output $0.30 → $0.23 per 1M tokens
- OpenRouter price changed: input $0.08 → $0.09, output $0.10 → $0.30 per 1M tokens
- Gemini API price changed: input – → Free, output – → Free per 1M tokens
- OpenRouter price changed: input $0.09 → $0.08, output $0.30 → $0.10 per 1M tokens
- OpenRouter price changed: input $0.07 → $0.09, output $0.23 → $0.30 per 1M tokens
- OpenRouter price changed: input $0.09 → $0.07, output $0.30 → $0.23 per 1M tokens
- OpenRouter price changed: input $0.02 → $0.09, output $0.05 → $0.30 per 1M tokens
- OpenRouter price changed: input $0.08 → $0.02, output $0.24 → $0.05 per 1M tokens
- OpenRouter price changed: input $0.09 → $0.08, output $0.26 → $0.24 per 1M tokens
- OpenRouter price changed: input $0.07 → $0.09, output $0.20 → $0.26 per 1M tokens
- OpenRouter price changed: input $0.07 → $0.07, output $0.23 → $0.20 per 1M tokens
- OpenRouter price changed: input $0.09 → $0.07, output $0.30 → $0.23 per 1M tokens
- OpenRouter price changed: input $0.07 → $0.09, output $0.23 → $0.30 per 1M tokens
- OpenRouter price changed: input $0.09 → $0.07, output $0.30 → $0.23 per 1M tokens
- SiliconFlow price changed: input $0.12 → $0.14, output $0.40 → $0.40 per 1M tokens
- OpenRouter price changed: input $0.07 → $0.09, output $0.23 → $0.30 per 1M tokens
- OpenRouter price changed: input $0.09 → $0.07, output $0.30 → $0.23 per 1M tokens
- OpenRouter price changed: input $0.07 → $0.09, output $0.23 → $0.30 per 1M tokens
- OpenRouter price changed: input $0.09 → $0.07, output $0.30 → $0.23 per 1M tokens
- Now listed on Google Vertex AI
- OpenRouter price changed: input $0.07 → $0.09, output $0.23 → $0.30 per 1M tokens
Sources
- https://openrouter.ai/google/gemma-4-26b-a4b-it
- https://github.com/sst/models.dev/blob/dev/providers/google/models/gemma-4-26b-a4b-it.toml
- https://huggingface.co/google/gemma-4-26B-A4B-it
- https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/google/gemma-4-26B-A4B-it.toml
- https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/google/gemma-4-26b-a4b-it.toml
- https://github.com/sst/models.dev/blob/dev/providers/amazon-bedrock/models/google.gemma-4-26b-a4b.toml
- https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/google/gemma-4-26B-A4B-it.toml
- https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/google/gemma-4-26b-a4b-it.toml
- https://github.com/sst/models.dev/blob/dev/providers/siliconflow/models/google/gemma-4-26B-A4B-it.toml
- https://github.com/sst/models.dev/blob/dev/providers/google-vertex/models/google/gemma-4-26b-a4b-it-maas.toml
- https://github.com/sst/models.dev/blob/dev/providers/vercel/models/google/gemma-4-26b-a4b-it.toml