Google · language model
Gemma 2 27B: pricing, context and benchmarks
Gemma 2 27B is a language model from Google released on July 13, 2024. It costs $0.65 per million input tokens and $0.65 per million output tokens, with a 8.2K-token context window. Epoch AI ranks it #122 of 125 rated models.
What you need to know about Gemma 2 27B
Gemma 2 27B was released by Google (United States) on July 13, 2024. It accepts text as input and produces text. Its context window reaches 8,192 tokens, larger than 3 % of the models in the registry, and it can write up to 2,048 tokens in one go.
Released more than 2 years ago, it belongs to a generation most vendors have since superseded.
Gemma 2 27B pricing
On OpenRouter, Gemma 2 27B costs $0.65 per million input tokens and $0.65 per million output tokens. Counting three tokens read for every token written, its average price is $0.65 per million, more expensive than 46 % of paid models (1.2 times cheaper than the median of $0.76).
A concrete example: a task that sends 2,000 tokens (about 1,500 words) and receives a 500-token answer costs $0.0016. At 1,000 tasks a day, budget $49 a month. The price calculator redoes this with your own volumes.
Performance and benchmarks
The Epoch Capabilities Index (ECI), which aggregates published results across many benchmarks, gives Gemma 2 27B a score of 122.1 (range 115.5 to 124.2). That places it #122 of 125 rated models.
Scores published by Epoch AI on the benchmarks the site tracks:
| Benchmark | What it measures | Score | Date |
|---|---|---|---|
| GPQA Diamond | PhD-level science questions | 36.5 % | Jun 24, 2024 |
| OTIS Mock AIME | maths competition problems | 1.4 % | Jun 24, 2024 |
For at least equal performance, Claude Haiku 5.5, GPT-6 Luna, and GPT-5.6 Luna cost at least 30% less.
Features, privacy and local use
- It does not support tool calling: it is not suited to driving an AI agent that has to act.
- It can answer in an enforced JSON format (structured outputs).
- Its knowledge stops at June 2024.
Its weights are open and downloadable from Hugging Face (gemma licence): you can run it on your own machines without sending your data to a third party. With 27,227,128,320 billion parameters, it needs about 15,214,343,548 GB of memory at 4-bit quantisation. Check with the VRAM calculator. It was downloaded 20,232 times on Hugging Face last month.
Other Google models
| Model | Released | Avg. price | ECI |
|---|---|---|---|
| Gemini 4 Argon | Oct 13, 2026 | $4 | 166.5 |
| Nano Banana 2.1 | Oct 6, 2026 | $3 | — |
| Gemini 3.8 Flash | Sep 2, 2026 | $1.65 | 157.4 |
| Gemini 3.7 Flash | Aug 13, 2026 | $1.5 | 158 |
| Gemini 3.6 Flash | Jul 21, 2026 | $1.5 | 154.5 |
| Gemini 3.5 Flash Lite | Jul 21, 2026 | $0.85 | 144.9 |
| Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | Jun 30, 2026 | $0.56 | — |
| Nano Banana 2 (Gemini 3.1 Flash Image) | Jun 18, 2026 | $1.13 | — |
Verdict
Gemma 2 27B scores 24/100 on our grid, which only uses published figures.
Strengths
- Open weights: self-hostable, your data stays with you.
Limitations
- Short context (8.2K tokens): long documents must be split.
- No tool calling: unusable as an agent's brain.
- Modest performance: behind 97 % of rated models.
- Older generation, often replaced by a newer model from the same vendor.
- Text only: reads neither images nor files.
Avoid if…
- you are building an agent that must call tools;
- you analyse long documents in one go;
- you want to host it on a single consumer computer (≈ 15,214,343,548 GB needed at 4-bit).
Alternatives
- Mistral Medium 3$0.8
- DeepSeek V3 0324$0.5
- DeepSeek V3$0.45
- GPT-4o-mini$0.26
- GPT-4o-mini (2024-07-18)$0.26
- Mistral Large$3
Comparisons and tools
Learn more
Frequently asked questions
How much does Gemma 2 27B cost?
$0.65 per million input tokens and $0.65 per million output tokens on OpenRouter (checked October 25, 2026). A task with 2,000 tokens read and 500 written costs $0.0016.
How big is Gemma 2 27B's context window?
8,192 tokens, roughly 6,000 words, with a maximum of 2,048 output tokens.
Can Gemma 2 27B run locally?
Yes, its weights are published under the gemma licence. Expect about 15,214,343,548 GB of memory at 4-bit.
Is Gemma 2 27B suitable for an AI agent?
No: without tool calling it cannot act, only answer.
How good is Gemma 2 27B?
Epoch AI ranks it #122 of 125 rated models (ECI 122.1). On GPQA Diamond, it scores 36.5%.
What are the alternatives to Gemma 2 27B?
The closest models on price and performance are Mistral Medium 3, DeepSeek V3 0324, and DeepSeek V3.
Related articles
- Mistral AI: models, pricing and agentsOctober 25, 2026
- LLM benchmarks: how to read model rankingsOctober 24, 2026
- Running a local LLM: hardware, software, and limitationsOctober 24, 2026
- Open-source or closed models for your AI agents?October 5, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score