Google route
gemma-4-26b-abliterated
Gemma 4 26B Abliterated API access.
Google's Gemma 4 26B mixture-of-experts model (4B active), fine-tuned to stop refusing. $0.25 input and $0.75 output per 1M tokens; cached input is billed at the input rate. 256K context, 8K max output, tool calling, image input, no reasoning step, so replies start fast. See the Gemma 4 Abliterated API pricing notes.
Input / 1M tokens
$0.25
Output / 1M tokens
$0.75
Context window
256K
Provider
Workload calculator
Put the token rate into context.
These examples apply the published input and output rates directly. Actual cost follows the exact tokens your client sends and the model returns.
This route is the 17th cheapest of 71 comparable text models and cheaper than 54 on the same key. Its context window ranks 60th of 71.
Short request
$0.0032
10K input + 1K output
Agent turn
$0.033
100K input + 10K output
Exact token billing
No request minimum
One model ID change
OpenAI compatible
Cost neighbourhood
Nearby routes, same workload.
Every comparison uses the same 100K-input / 10K-output turn. Changing route is a one-line model ID edit.
Price does not measure task quality. For generation routes, see GPT Image 2.
First request
Route it in one call.
Use any OpenAI SDK or tool. Keep the request shape, point the base URL at RouterPlex, and set the model ID shown here.
Read the quickstartcurl https://api.routerplex.com/v1/chat/completions \-H "Authorization: Bearer $ROUTERPLEX_API_KEY" \-H "Content-Type: application/json" \-d '{"model": "gemma-4-26b-abliterated","messages": [{"role": "user", "content": "Hello!"}]}'
Route notes
Questions before production traffic.
01How much does the Gemma 4 26B Abliterated API cost?+
Through RouterPlex, Gemma 4 26B Abliterated costs $0.25 per 1M input tokens and $0.75 per 1M output tokens — RouterPlex's disclosed public reference rate, billed per token from a prepaid balance you top up from $5. A refusal-removed fine-tune of Google's Gemma 4 26B: the open weights retrained so the model stops refusing, served on RouterPlex through a third-party host. This is not Google's own model or price -- RouterPlex sets this rate. The model will answer requests the original declines, so you are responsible for how you use it under the RouterPlex terms.
02What does one Gemma 4 26B Abliterated agent turn cost?+
A 100K-token input with a 10K-token reply costs about $0.033 on Gemma 4 26B Abliterated. That makes it the 17th cheapest of 71 comparable text models on RouterPlex, roughly 2.7× the cost of the cheapest option (Muse Spark 1.2 Contributor).
03What is a cheaper alternative to Gemma 4 26B Abliterated?+
GPT-5.6 Luna from OpenAI is the closest cheaper model on RouterPlex — $0.032 per agent turn against $0.033 for Gemma 4 26B Abliterated, at $0.20/1M input and $1.20/1M output. Both run on the same key and the same endpoint, so switching is a one-line model ID change.
04Is Gemma 4 26B Abliterated cheaper than GLM-5.3 Flash Abliterated?+
Yes. Per agent turn, Gemma 4 26B Abliterated costs about $0.033 against $0.035 for GLM-5.3 Flash Abliterated — 7% less.
05What is the context window of Gemma 4 26B Abliterated?+
Gemma 4 26B Abliterated supports a 256K token context window on RouterPlex, the 60th largest of the 71 models that publish one.
06Can I use Gemma 4 26B Abliterated with the OpenAI SDK?+
Yes. RouterPlex serves Gemma 4 26B Abliterated through an OpenAI-compatible endpoint at https://api.routerplex.com/v1 — point any OpenAI SDK or tool at that base URL with your RouterPlex key and set model to "gemma-4-26b-abliterated".
Provider family
More from Google.
Deploy this route
Put Gemma 4 26B Abliterated behind one key.
Top up from $5 with no subscription required.