Capabilities and specifications
- Creator
- Model family
- gemma
- Knowledge cutoff
- Not documented
- License
- Not documented
- Release date
- 2026-04-02
- Model ID
google/gemma-4-26b-a4b-it
Open Gemma instruction model for efficient chat and self-hosted deployments
google/gemma-4-26b-a4b-itProvider-specific identifiers, limits, and prices per million tokens.
| Provider | Provider model ID | Context | Input | Output | Cache read | Capabilities | Source |
|---|---|---|---|---|---|---|---|
gemma-4-26b-a4b-it |
262.144K | Not listed | Not listed | - | ReasoningToolsJSON | Docs | |
google/gemma-4-26b-a4b-it |
262.144K | $0.06 | $0.33 | - | ReasoningToolsJSON | Docs | |
gemma-4-26b-a4b-it |
262.144K | $0.07 | $0.34 | - | ReasoningToolsJSON | Docs | |
google/gemma-4-26B-A4B-it |
262.144K | $0.07 | $0.34 | - | ReasoningToolsJSON | Docs | |
google/gemma-4-26b-a4b-it |
262.144K | $0.07 | $0.34 | - | ReasoningToolsJSON | Docs | |
@cf/google/gemma-4-26b-a4b-it |
256K | $0.1 | $0.3 | - | ReasoningToolsJSON | Docs | |
gemma4-26b |
256K | $0.1 | $0.5 | - | ReasoningToolsJSON | Docs | |
google/gemma-4-26B-A4B-it |
262.144K | $0.12 | $0.4 | - | ToolsJSON | Docs | |
google/gemma-4-26b-a4b-it |
262.144K | $0.12 | $0.4 | - | ReasoningTools | Docs | |
gemma-4-26b-a4b-it |
256K | $0.122 | $0.424 | - | ToolsJSON | Docs | |
google/gemma-4-26B-A4B-it |
262.144K | $0.13 | $0.4 | - | ReasoningToolsJSON | Docs | |
google/gemma-4-26b-a4b-it |
262.144K | $0.13 | $0.4 | - | ReasoningToolsJSON | Docs | |
google/gemma-4-26b-a4b-it |
262.144K | $0.13 | $0.4 | - | Reasoning | Docs | |
google/gemma-4-26b-a4b-it |
262.144K | $0.13 | $0.4 | - | ReasoningJSON | Docs | |
google/gemma-4-26B-A4B-it |
262.144K | $0.144 | $0.575 | - | ReasoningToolsJSON | Docs | |
google/gemma-4-26b-a4b-it |
262.144K | $0.15 | $0.6 | $0.015 | ReasoningToolsJSON | Docs | |
gemma-4-26b-a4b-it |
256K | $0.25 | $0.5 | - | ReasoningToolsJSON | Docs |
Capability badges appear only when the provider catalog explicitly lists support.
Observed serving measurements stay separate from model specifications and are never estimated from price or model size.
Generation speed; higher is faster.
Time until the first output token arrives.
Successful requests over a measured period.
Performance varies by inference provider, region, and load. Provider-level measurements appear only when a source reports them.
Raw results remain attached to their original source and version.
Detected changes from successful source imports.
Fetch the complete source-linked model record without an API key.
GET https://www.modelbench.lol/api/v1/models/google/gemma-4-26b-a4b-itcurl "https://www.modelbench.lol/api/v1/models/google/gemma-4-26b-a4b-it"