Google: Gemma 4 26B A4B
Open Gemma instruction model for efficient chat and self-hosted deployments
Price changes
Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.
- ↑ higherOutput $0.1 → $0.15
- ↑ higherInput $0.024 → $0.04
- ↑ higherOutput $0.048 → $0.1
- ↑ higherInput $0.016 → $0.024
- ↓ lowerOutput $0.09 → $0.048
- ↓ lowerInput $0.03 → $0.016
- ↓ lowerOutput $0.22 → $0.09
- ↓ lowerInput $0.042 → $0.03
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (3 omitted). Show free/$0 listings.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestgoogle/gemma-4-26b-a4b-it | Kilo Gateway | $0.04 | $0.15 | $0.01 | 262K |
| models.devgoogle/gemma-4-26b-a4b-it | OrcaRouter | $0.06 | $0.33 | $0.0075 | 262K |
| models.devgoogle/gemma-4-26b-a4b-it | NanoGPT | $0.07 | $0.24 | $0.046 | 262K |
| models.devgoogle/gemma-4-26b-a4b-it:thinking | NanoGPT | $0.07 | $0.24 | $0.046 | 262K |
| models.devgoogle/gemma-4-26B-A4B-it | DeepInfra | $0.07 | $0.34 | $0.007 | 262K |
| models.devdeepinfra/gemma-4-26b-a4b-it | LLM Gateway | $0.07 | $0.34 | $0 | 262K |
| models.devgemma-4-26b-a4b-it | DevPass (LLM Gateway) | $0.07 | $0.34 | $0 | 262K |
| models.devgemma-4-26b-a4b-it | Requesty | $0.07 | $0.34 | $0.07 | 262K |
| LiteLLMgoogle/gemma-4-26B-A4B-it | N/A | $0.07 | $0.34 | $0.007 | N/A |
| LiteLLMgemma-4-26B-A4B-it | N/A | $0.07 | $0.34 | $0.007 | N/A |
| models.devgoogle/gemma-4-26b-a4b-it | OpenRouter | $0.077 | $0.23 | $0.038 | 262K |
| OpenRoutergoogle/gemma-4-26b-a4b-it | OpenRouter | $0.081 | $0.242 | $0.04 | 262K |
| models.devgemma-4-26b-a4b-it | Charm Hyper | $0.098 | $0.334 | $0.049 | 256K |
| models.devgoogle/gemma-4-26B-A4B-it | CoreWeave | $0.1 | $0.3 | $0.05 | 262K |
| models.dev@cf/google/gemma-4-26b-a4b-it | Cloudflare | $0.1 | $0.3 | $0.05 | 256K |
| LiteLLM@cf/google/gemma-4-26b-a4b-it | N/A | $0.1 | $0.3 | $0.01 | N/A |
| LiteLLMcloudflare/@cf/google/gemma-4-26b-a4b-it | N/A | $0.1 | $0.3 | $0.01 | N/A |
| models.devgemma-4-26b-a4b-it | Cortecs | $0.111 | $0.557 | $0 | 262K |
| models.devgoogle/gemma-4-26B-A4B-it | Hugging Face | $0.13 | $0.4 | $0 | 262K |
| models.devnovita/gemma-4-26b-a4b-it | LLM Gateway | $0.13 | $0.4 | $0 | 262K |
| models.devgoogle/gemma-4-26b-a4b-it | Merge Gateway | $0.13 | $0.4 | $0 | 262K |
| models.devgoogle/gemma-4-26b-a4b-it | Novita AI | $0.13 | $0.4 | $0 | 262K |
| models.devgoogle-gemma-4-26b-a4b-it | Venice AI | $0.13 | $0.4 | $0.05 | 256K |
| LiteLLMnovita/google/gemma-4-26b-a4b-it | N/A | $0.13 | $0.4 | $0.013 | N/A |
| models.devgoogle/gemma-4-26B-A4B-it | SiliconFlow | $0.14 | $0.4 | $0.05 | 262K |
| LiteLLMaihubmix/gemma-4-26b-a4b-it | N/A | $0.14 | $0.4 | $0.014 | N/A |
| models.devgoogle/gemma-4-26B-A4B-it | Evroc | $0.144 | $0.575 | $0 | 262K |
| models.devgoogle/gemma-4-26b-a4b-it | Vercel AI Gateway | $0.15 | $0.6 | $0.015 | 262K |
| LiteLLMvertex_ai/gemma-4-26b-a4b-it | N/A | $0.15 | $0.6 | $0.015 | N/A |
| models.devgoogle/gemma-4-26b-a4b-it | AI/ML API | $0.1587 | $0.6348 | $0.1587 | 262K |
| LiteLLMgoogle/gemma-4-26b-a4b-it | N/A | $0.25 | $0.5 | $0.025 | N/A |
| LiteLLMscaleway/google/gemma-4-26b-a4b-it | N/A | $0.25 | $0.5 | $0.025 | N/A |
| models.devgemma-4-26b-a4b-it | Scaleway | $0.2804 | $0.5607 | $0 | 256K |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- Open weights
- In: text
- In: image
- In: video
- In: pdf
- Out: text
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
- AA intelligence16.7i
- AA coding39.3i
- AA agentic2.9i
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.