AI Recommendation
Should you use gemma-4-26b-a4b-it?
gemma-4-26b-a4b-it is listed for chat workloads and supports a 256K context window.
Use it when Cloudflare Workers AI's free tier is enough for evaluation, demos, or light production traffic.
gemma-4-26b-a4b-it Free API on Cloudflare Workers AI
Free API VerifiedOpen Gemma instruction model for efficient chat and self-hosted deployments
Free APIOpenAI compatibleReasoningTool callingJSON modeTextImage
API Details
Copy-ready connection details
Base URL
https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run Model ID
@cf/google/gemma-4-26b-a4b-it API format Cloudflare Workers AI native run + OpenAI Chat Completions
Technical Details
gemma-4-26b-a4b-it specifications
Context window 256K
Max output 131K
Status Online
Family gemma
Released Apr 2, 2026
Last updated Aug 6, 2026
Free listing since Apr 2, 2026
Input text, image
Output text
Capabilities reasoning, tool calling, structured output, file attachments, temperature control
Open weights Yes
Weights Hugging Face
Best for
- Chat
Strengths & Weaknesses
Strengths
- Long context window
- Reasoning mode listed
- Tool calling support
- Structured JSON output
Watch outs
- Free-tier rate limits apply
Benchmark Overview
Benchmark signals for gemma-4-26b-a4b-it
Intelligence General reasoning and instruction following
25.7/100 Coding Programming and code generation
39.3/100 Agentic Tool use and multi-step tasks
11/100 Context Maximum listed context window
256K Pricing
gemma-4-26b-a4b-it pricing per 1M tokens
Input $0.13 per 1M tokens
Output $0.4 per 1M tokens
Free access Available Cloudflare Workers AI
Rate limit 10K neurons/day (shared) provider policy
Availability
gemma-4-26b-a4b-it availability by provider
We found 3 provider listings for gemma-4-26b-a4b-it. Check model ID, quota, pricing, and API format before switching providers.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | @cf/google/gemma-4-26b-a4b-it | Free tier | 256K | Native | 10K neurons/day (shared) |
| | Google: Gemma 4 26B A4B (free) | Free tier | 262K | OpenAI-style | 200 req/day (free tier) |
| | Gemma 4 26B A4B IT | Free tier | 262K | Native | Varies |
Compare
gemma-4-26b-a4b-it alternatives to consider
| Model | Provider | Context | Access |
|---|---|---|---|
| Google: Gemma 4 26B A4B (free) | OpenRouter | 262K | Free tier |
| Gemma 4 26B A4B IT | Google Gemini | 262K | Free tier |
| Mistral 7B | Cloudflare Workers AI | 33K | Free tier |
| Qwen 1.5 7B | Cloudflare Workers AI | 33K | Free tier |
| @cf/meta/llama-3.3-70b-instruct-fp8-fast | Cloudflare Workers AI | 131K | Free tier |
Typical Use Cases
gemma-4-26b-a4b-it use cases
Chat
gemma-4-26b-a4b-it is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
FAQ
gemma-4-26b-a4b-it free API FAQ
Is gemma-4-26b-a4b-it free to use?
gemma-4-26b-a4b-it is listed with free API access on Cloudflare Workers AI, subject to the provider's quota and account policy.
What is the gemma-4-26b-a4b-it model ID?
The model ID shown in this catalog is @cf/google/gemma-4-26b-a4b-it.
What are the gemma-4-26b-a4b-it free tier rate limits on Cloudflare Workers AI?
The listed free tier limit is 10K neurons/day (shared). Limits can change per account tier, so confirm against the provider dashboard.
What context window does gemma-4-26b-a4b-it support?
The listed context window is 256K tokens with up to 131K output tokens.
More about gemma-4-26b-a4b-it
Gemma 4 26B is Google's latest open model, running on Cloudflare Workers AI with a 256K context window and a 26B-parameter architecture using 4 active experts (MoE). It brings Google's latest advances in small-model efficiency to the edge, making it suitable for long-form text tasks, summarization, and instruction-following workloads. The 256K context window is particularly useful for processing full-length documents or long conversation histories. Operates on Cloudflare's shared 10,000 Neurons/day free allocation; API access uses Cloudflare's native format, not the OpenAI SDK.
For API keys, setup steps, and provider-level limits, see the Cloudflare Workers AI provider page.