Gemma 4 26B A4B: Intelligence, Performance & Price Analysis
Model summary
Verbosity
Gemma 4 26B A4B (Reasoning) supports text, image, and video input, outputs text, and has a 256k tokens context window.
Pricing for Gemma 4 26B A4B (Reasoning) is $0.09 per 1M input tokens (moderately priced, median: $0.13) and $0.32 per 1M output tokens (somewhat expensive, median: $0.30).
| Input modality | Supports: text, image, and video |
|---|---|
| Output modality | Supports: text |
| Context window | 256k ~384 A4 pages of size 12 Arial font |
| Total parameters | 25.2B |
| Active parameters | 3.8B Number of parameters active per token during inference |
| License | Apache 2.0 |
| Model weights | Hugging Face |
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Index vs. Cost per Task
Evaluations
Agentic knowledge work, Elo
Agentic SaaS workflows
Reasoning & knowledge
Agentic real-world work tasks, Elo
Kubernetes incident root-cause analysis
Visual reasoning
Openness Index
Artificial Analysis Openness Index: Score
Cost
Cost per Intelligence Index Task
Cost to Run Artificial Analysis Intelligence Index
Pricing: Cache Hit, Input, and Output
Performance
Measured by time per task (minutes), output speed (tokens per second), time to first answer token and time to first token (seconds)
Time per Intelligence Index Task
Output Speed
Time to First Answer Token
Context Window
Context Window
Model Size (Open Weights Models Only)
Model Size: Total and Active Parameters
Further details
Frequently Asked Questions
Common questions about Gemma 4 26B A4B
Gemma 4 26B A4B was released on April 2, 2026.
Gemma 4 26B A4B was created by Google.
Gemma 4 26B A4B has a time to first answer token of 23.60s (reasoning) and 1.63s (non-reasoning) (based on the median across providers serving the model). Gemma 4 26B A4B (Reasoning)'s time to first answer token is at the higher end compared to other open weight models of similar size (median: 4.61s).
Gemma 4 26B A4B costs $0.09 (reasoning) and $0.13 (non-reasoning) per 1M input tokens and $0.32 (reasoning) and $0.40 (non-reasoning) per 1M output tokens, based on the median across providers serving the model. Gemma 4 26B A4B (Reasoning) is better than average on input price (median: $0.13) and somewhat higher than average on output price (median: $0.30).
Gemma 4 26B A4B costs $0.09 (reasoning) and $0.13 (non-reasoning) per 1M input tokens and $0.32 (reasoning) and $0.40 (non-reasoning) per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.085 (reasoning) and $0.11 (non-reasoning) per 1M tokens. Pricing may vary by provider. Compare provider pricing
Yes, Gemma 4 26B A4B (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer. No, Gemma 4 26B A4B (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Gemma 4 26B A4B supports text, image, and video input.
Gemma 4 26B A4B supports text output.
Yes, Gemma 4 26B A4B supports image input and can analyze, describe, and answer questions about images.
Yes, Gemma 4 26B A4B is multimodal. It can process text, image, and video input and generate text output.
Gemma 4 26B A4B has a context window of 256k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Gemma 4 26B A4B is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Gemma 4 26B A4B has 25.2B parameters (3.8B active).
Gemma 4 26B A4B is a Mixture of Experts (MoE) model with 25.2B total parameters, but only 3.8B active parameters are used during inference.
Gemma 4 26B A4B is released under the Apache 2.0 license. This license allows commercial use. View license
Yes, Gemma 4 26B A4B is available via API through 8 providers. Compare API providers
Gemma 4 26B A4B is available through 8 API providers. Compare providers