G
Gemma 4 26B A4BOPEN
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.
Prices update automatically — checked daily against provider list prices.
- $0.14 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 70% of the 191 open-weight models tracked here
- 6 of 34 Google models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for Gemma 4 26B A4B, measured by Artificial Analysis. Higher is better. Measurement mode: Reasoning.
For the same budget, Gemma 4 26B A4B delivers 23 times more capability. Open weights also mean you can self-host it and pay nothing per token.
Models at this level cost $0.96 per 1M tokens (median of 15) — this one costs $0.14.
Cheaper and better on this index: GLM 5.3 Flash · DeepSeek V4 Flash 0731 · DeepSeek V4 Flash 0423 and 2 more
About this model
Gemma 4 26B A4B is an open-weight AI model by Google. You can download and self-host it for free; the prices below are hosted-API list prices, tracked daily, for when you prefer convenience over self-hosting.
Frequently asked questions
What is Gemma 4 26B A4B?
Gemma 4 26B A4B is an AI language model from Google. It is open-weight: you can download it and run it on your own hardware, for free. It scores 26.1 on the Artificial Analysis intelligence index.
Is Gemma 4 26B A4B free?
The weights are free and open — you can self-host Gemma 4 26B A4B and pay nothing per token. If you prefer a hosted API, list prices are $0.07 per million input tokens and $0.34 per million output tokens.
What is Gemma 4 26B A4B good at?
Independent benchmarks from Artificial Analysis give it GPQA 79.2%, Humanity's Last Exam 19.3%, Long Context Reasoning 61.7%, SciCode 40%, IFBench 72.4%, τ²-Bench 43.6%, τ-Bench Banking 12%, Terminal-Bench 39%, Terminal-Bench Hard 13.6%. It is particularly used for code generation.
Can I self-host Gemma 4 26B A4B?
Yes. Gemma 4 26B A4B has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.