---
title: "Gemma 4 26B vision API: cheap per token or hourly key"
description: "BroadNet's build of Google's Gemma 4 26B: text and image chat through an OpenAI-compatible API, usable on the starting credit or as a flat-price hourly key."
url: https://broadrouter.com/models/gemma-4-vl-26b/
lang: en
updated: 2026-11-16
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# BroadNet Gemma 4 VL 26B API

Updated 2026-11-16

BroadNet Gemma 4 VL 26B, based on Google's Gemma 4, runs on BroadNet Inference as `broadnet/gemma-4-26b-a4b` through the OpenAI-compatible `https://inference.broadnet.ai/v1`. It costs $0.10 input and $0.22 output per 1M tokens, with a 32,768-token context. It can use the starting credit, and inference content is not retained.

## At a glance

-   Text
-   Vision (image input)

-   Starting credit eligible: no top-up needed
-   Gemma hourly key: one hour, one stream, a separate product from the Meteor plan
-   Text and image input
-   BroadNet runs it in production with a hot backup
-   BroadNet reports it matched Claude Sonnet on 5 of 6 steps of its chatbot pipeline in a blind evaluation

_[image: A café chalkboard reading "Coffee قهوة" and "Tea شاي" beside a cup of coffee, with the text "AI that reads the real world.", "BroadRouter" and "Vision & document AI".]_

| Price and limits |  |
| --- | --- |
| Model ID | `broadnet/gemma-4-26b-a4b` |
| Endpoint | `/v1/chat/completions` |
| Supported inputs | text, image (vision: understanding, not generation) |
| Context | 32,768 tokens, prompt and answer together |
| Input | $0.10 per 1M tokens |
| Cached input | Not published |
| Output | $0.22 per 1M tokens |
| Pay-as-you-go limits | 30 requests a minute, 4 in flight per key |
| Access | Starting credit eligible |
| Hourly key | $0.50 for one hour, one stream (a separate product from the Meteor plan) |

Prices on this page are from BroadNet's price feed snapshot dated 2026-11-14, not checked live here. See [official pricing](https://inference.broadnet.ai/pricing?utm_source=broadrouter&utm_medium=referral&utm_campaign=models-gemma-4-vl-26b&utm_content=feed-status) for current rates.

[Open the comparison](https://broadrouter.com/models/#compare)

[Report a wrong price or number](mailto:info@broadnet.ai?subject=Wrong%20price%20or%20number%20on%20BroadNet%20Gemma%204%20VL%2026B%20on%20BroadNet%20Inference&body=Page%3A%20https%3A%2F%2Fbroadrouter.com%2Fmodels%2Fgemma-4-vl-26b%2F%0A%0AWhat%20looks%20wrong%20(model%2C%20figure%20shown%2C%20correct%20figure%20and%20a%20source%20link%20if%20you%20have%20one)%3A%0A) (email to info@broadnet.ai, with this page's link filled in).

## What does BroadNet publish about BroadNet Gemma 4 VL 26B?

From [the BroadNet Gemma 4 VL 26B page on broadnet.ai](https://www.broadnet.ai/inference/models/gemma-4-vl-26b), checked 15 November 2026. Measurements are BroadNet's, on its hardware, unless a public leaderboard is named; we have not reproduced them.

| What BroadNet publishes about this model |  |
| --- | --- |
| Architecture | Mixture of experts: 26B parameters in total, about 4B active per token |
| Serving | 4-bit AWQ weights, multi-token-prediction speculative decoding (k=2), fp8 KV cache, BroadNet conversational chat template |
| Modalities | Text and image in, text out |
| Context on the API | 32K tokens; BroadNet suggests one page per request for long documents |
| Hardware | NVIDIA Blackwell-class GPUs with a hot backup; failover is automatic |
| Licence | Apache-2.0 (Google) |

### BroadNet's measurements

-   Internal quality battery: 90.86 of 100, the best local model BroadNet says it has measured.
-   Blind three-judge evaluation on 240 production conversations across 11 tenants: matched Claude Sonnet on 5 of 6 steps of BroadNet's chatbot pipeline, and answered 1.2 to 6.5 times faster per step.
-   About 136 tokens per second on a single stream with speculative decoding.
-   The 26B mixture of experts beat the dense Gemma 4 31B on 5 of 6 pipeline steps with about one eighth of the active parameters.
-   The same weights served by a hosted provider scored 0.13 lower on average than BroadNet's own serving.

Base weights: [google/gemma-4-26B-A4B-it](https://huggingface.co/google/gemma-4-26B-A4B-it) on Hugging Face.

How BroadNet chooses and serves models: [its GPU hardware and serving approach](https://broadrouter.com/blog/broadnet-gpu-fleet-and-serving/) and [the models it evaluated and ruled out](https://broadrouter.com/blog/models-broadnet-ruled-out/).

## Published benchmark results

BroadNet did not run these benchmarks; results are as published by the Google model card and Epoch AI and may use different settings. BroadRouter is BroadNet's site. They refer to the published model [`google/gemma-4-26B-A4B-it`](https://huggingface.co/google/gemma-4-26B-A4B-it); BroadNet serves its own 4-bit AWQ build of it, so results on BroadNet can differ.

Published benchmark results for BroadNet Gemma 4 VL 26B, with sources
| Benchmark | Result | Setting or note | Source |
| --- | --- | --- | --- |
| MMLU Pro | 82.6% | Instruction-tuned model | [Google model card](https://huggingface.co/google/gemma-4-26B-A4B-it), checked 2026-11-16 |
| GPQA Diamond | 82.3% | Instruction-tuned model | [Google model card](https://huggingface.co/google/gemma-4-26B-A4B-it), checked 2026-11-16 |
| LiveCodeBench v6 | 77.1% | Instruction-tuned model | [Google model card](https://huggingface.co/google/gemma-4-26B-A4B-it), checked 2026-11-16 |
| AIME 2026 no tools | 88.3% | Instruction-tuned model | [Google model card](https://huggingface.co/google/gemma-4-26B-A4B-it), checked 2026-11-16 |
| MMMU Pro | 73.8% | Instruction-tuned model | [Google model card](https://huggingface.co/google/gemma-4-26B-A4B-it), checked 2026-11-16 |
| MATH-Vision | 82.4% | Instruction-tuned model | [Google model card](https://huggingface.co/google/gemma-4-26B-A4B-it), checked 2026-11-16 |
| GPQA Diamond | 0.732 | Minimal reasoning setting; Epoch run gemma-4-26b-a4b-it\_minimal, mean score on a 0 to 1 scale | [Epoch AI](https://epoch.ai/benchmarks/use-this-data), checked 2026-11-16 |
| OTIS Mock AIME 2024-2025 | 0.822 | Minimal reasoning setting; Epoch run gemma-4-26b-a4b-it\_minimal, mean score on a 0 to 1 scale | [Epoch AI](https://epoch.ai/benchmarks/use-this-data), checked 2026-11-16 |

Epoch AI rows: [Epoch AI, Capabilities & benchmarking](https://epoch.ai/benchmarks/use-this-data), licensed [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/), shown as the mean score on a 0 to 1 scale, rounded to three decimals (hover a value for the exact figure in Epoch's data file).

Side by side: [BroadNet Gemma 4 VL 26B vs DeepSeek V4.1 Flash](https://broadrouter.com/compare/deepseek-v4.1-flash-vs-gemma-4-vl-26b/), [BroadNet Gemma 4 VL 26B vs GLM 5.3](https://broadrouter.com/compare/gemma-4-vl-26b-vs-glm-5.3/) and [BroadNet Gemma 4 VL 26B vs Qwen3.8 27B](https://broadrouter.com/compare/gemma-4-vl-26b-vs-qwen3.8-27b/), with prices, context and workload costs. Gemma 4 26B A4B is also sold by 11 other providers, from $0.07 input and $0.34 output per 1M tokens on their own pricing pages: [Gemma 4 26B A4B API pricing by provider](https://broadrouter.com/llm-api-pricing/gemma-4-26b-a4b-it/). The same text is a different number of tokens on each model: see how BroadNet Gemma 4 VL 26B's tokenizer compares on Arabic, English and code in the [tokenizer efficiency dataset](https://broadrouter.com/data/tokenizer-efficiency/).

## Call it in Python

Install the OpenAI SDK with `pip install openai`, export `BROADNET_API_KEY`, then run:

Python

```python
from openai import OpenAI
import base64, os

client = OpenAI(base_url="https://inference.broadnet.ai/v1", api_key=os.environ["BROADNET_API_KEY"])
image = base64.b64encode(open("invoice.jpg", "rb").read()).decode()

response = client.chat.completions.create(
    model="broadnet/gemma-4-26b-a4b",
    max_tokens=2000,
    messages=[{"role": "user", "content": [
        {"type": "text", "text": "What is the total on this invoice?"},
        {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64," + image}},
    ]}],
)
print(response.choices[0].message.content)
```

## Or with curl

curl

```bash
curl https://inference.broadnet.ai/v1/chat/completions \
  -H "Authorization: Bearer $BROADNET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"broadnet/gemma-4-26b-a4b","messages":[{"role":"user","content":"Reply with one short sentence."}]}'
```

## Guides for BroadNet Gemma 4 VL 26B

-   [Use the OpenAI Python SDK with BroadNet Inference](https://broadrouter.com/guides/openai-python-sdk/)
-   [Use the OpenAI Node.js SDK with BroadNet Inference](https://broadrouter.com/guides/openai-node-sdk/)
-   [Try BroadNet Inference in your browser, no account](https://broadrouter.com/guides/try-broadnet-inference-playground/)
-   [First request to BroadNet Inference with curl](https://broadrouter.com/guides/curl-quickstart/)
-   [Stream chat completions and handle dropped connections](https://broadrouter.com/guides/streaming-chat-completions/)
-   [Use Cline with BroadNet Inference (OpenAI Compatible provider)](https://broadrouter.com/guides/cline-openai-compatible/)
-   [Connect Open WebUI to BroadNet Inference](https://broadrouter.com/guides/open-webui-openai-api/)
-   [Add BroadNet Inference to LibreChat as a custom endpoint](https://broadrouter.com/guides/librechat-custom-endpoint/)
-   [Use BroadNet Inference in n8n (OpenAI credential, Base URL)](https://broadrouter.com/guides/n8n-openai-compatible/)
-   [Use the Vercel AI SDK with BroadNet Inference](https://broadrouter.com/guides/vercel-ai-sdk-openai-compatible/)
-   [Route LiteLLM to BroadNet Inference (SDK and proxy)](https://broadrouter.com/guides/litellm-proxy-custom-provider/)
-   [Read Arabic invoices and receipts with a vision model](https://broadrouter.com/guides/read-arabic-invoices-with-vision/)
-   [Use Jan with BroadNet Inference as a custom OpenAI-compatible provider](https://broadrouter.com/guides/jan-custom-endpoint/)
-   [Connect SillyTavern to BroadNet Inference (Custom OpenAI-compatible)](https://broadrouter.com/guides/sillytavern-custom-openai-endpoint/)
-   [Call BroadNet Inference from Go with the openai-go SDK](https://broadrouter.com/guides/openai-go-sdk/)
-   [Use Haystack pipelines and agents with BroadNet Inference](https://broadrouter.com/guides/haystack-openai-compatible/)
-   [Use DSPy with BroadNet Inference (set model\_type="chat")](https://broadrouter.com/guides/dspy-openai-compatible/)
-   [Evaluate BroadNet models with promptfoo](https://broadrouter.com/guides/promptfoo-openai-compatible/)
-   [Connect Flowise to BroadNet Inference (OpenAI Custom Model)](https://broadrouter.com/guides/flowise-openai-compatible/)
-   [Connect Langflow to BroadNet Inference](https://broadrouter.com/guides/langflow-openai-compatible/)

## Use BroadNet Gemma 4 VL 26B in the console

The BroadNet console on inference.broadnet.ai manages accounts and keys. It does not receive your choice from this page, so:

1.  Sign in or create an account.
2.  Create a pay-as-you-go key; the starting credit covers this model.
3.  Send this model ID as `model` to `/v1/chat/completions`: `broadnet/gemma-4-26b-a4b`

[Open the BroadNet console](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=models-gemma-4-vl-26b&utm_content=model-console) · [Estimate the cost](https://broadrouter.com/pricing/?model=gemma-4-vl-26b#estimate) · [Read the API reference](https://inference.broadnet.ai/docs?utm_source=broadrouter&utm_medium=referral&utm_campaign=models-gemma-4-vl-26b&utm_content=docs#models) ·

## Compare BroadNet Gemma 4 VL 26B

-   [DeepSeek V4.1 Flash vs BroadNet Gemma 4 VL 26B](https://broadrouter.com/compare/deepseek-v4.1-flash-vs-gemma-4-vl-26b/)
-   [BroadNet Gemma 4 VL 26B vs GLM 5.3](https://broadrouter.com/compare/gemma-4-vl-26b-vs-glm-5.3/)
-   [BroadNet Gemma 4 VL 26B vs Qwen3.8 27B](https://broadrouter.com/compare/gemma-4-vl-26b-vs-qwen3.8-27b/)

Free tools for BroadNet Gemma 4 VL 26B

-   [LLM API cost calculator](https://broadrouter.com/tools/llm-api-cost-calculator/) Price a workload on every model at once, with cache hits, reasoning and a flat-plan check.
-   [LLM token counter](https://broadrouter.com/tools/token-counter/) Exact token counts with each model's real tokenizer, with a token view and cost.
-   [Context window calculator](https://broadrouter.com/tools/context-window-calculator/) Will it fit? Window used per model, room left for output, cost to send.

[All free tools](https://broadrouter.com/tools/)

## Questions

### What is the model ID for BroadNet Gemma 4 VL 26B?

Pass `broadnet/gemma-4-26b-a4b` as `model` to `/v1/chat/completions`. The base URL is `https://inference.broadnet.ai/v1`.

### How much does BroadNet Gemma 4 VL 26B cost?

$0.10 input and $0.22 output per 1M tokens, from your account balance. It is also the model on the Gemma hourly key, a separate flat-price product.

### What is the context window of BroadNet Gemma 4 VL 26B?

32,768 tokens per request, prompt and answer together.

### Can I use BroadNet Gemma 4 VL 26B without a top-up?

Yes. It can use the starting credit for new accounts.

### Where does BroadNet Gemma 4 VL 26B run?

BroadNet's model page says: NVIDIA Blackwell-class GPUs with a hot backup; failover is automatic. Its privacy statement adds that processing locations for data-residency needs are agreed with BroadNet before you send data.

### How does BroadNet Gemma 4 VL 26B score on benchmarks?

As published, [the Google model card](https://huggingface.co/google/gemma-4-26B-A4B-it) reports 82.6% on MMLU Pro and 82.3% on GPQA Diamond; [Epoch AI](https://epoch.ai/benchmarks/use-this-data) measured 0.732 on GPQA Diamond in its own run, as a mean score on a 0 to 1 scale (checked 2026-11-16). BroadNet did not run these benchmarks, and sources may use different settings, so the figures are not directly comparable. Every published result we found, with its setting and source.

### Is my data stored?

Inference content is not retained: prompts, images and answers are processed for the request only. Necessary account, billing and security metadata, such as timings, token counts and cost, is retained as described in BroadNet's privacy statement. [Read how](https://broadrouter.com/zero-data-retention/).

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=models-gemma-4-vl-26b&utm_content=page-cta) ·

**Sources**

-   [BroadNet Inference pricing](https://inference.broadnet.ai/pricing?utm_source=broadrouter&utm_medium=referral&utm_campaign=models-gemma-4-vl-26b&utm_content=sources)
-   [Model IDs and request shapes](https://inference.broadnet.ai/docs?utm_source=broadrouter&utm_medium=referral&utm_campaign=models-gemma-4-vl-26b&utm_content=sources#models)
-   [BroadNet model catalogue](https://www.broadnet.ai/inference/models)
-   [The BroadNet Gemma 4 VL 26B page on broadnet.ai (checked 2026-11-15)](https://www.broadnet.ai/inference/models/gemma-4-vl-26b)
