Models · Best vision
Gemma 3 27B
by Google
Gemma 3 introduces multimodality, supporting vision-language input and text outputs.
Our verdict
We have not reviewed Gemma 3 27B yet
No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.
From the listing
About Gemma 3 27B
Gemma 3 introduces multimodality, supporting vision-language input and text outputs.
Notes
Gemma 3 27B is listed in the EDNA Models directory from the OpenRouter catalogue.
Key facts
What we have checked
- Input price
- $0.080 per million tokens
- Output price
- $0.160 per million tokens
- Price on deepinfra
- $0.064 per million input tokens
- Price on deepinfra
- $0.128 per million output tokens
- Price on nebius
- $0.040 per million cached input tokens
- Price on nebius
- $0.100 per million input tokens
- Price on nebius
- $0.300 per million output tokens
- Price on nextbit
- $0.040 per million cached input tokens
- Price on nextbit
- $0.080 per million input tokens
- Gpqa diamond
- 47.7% (for 12 Mar 2025)
- Aider polyglot
- 4.9% (for 12 Mar 2025)
- Dtbench
- 52.5% (for 12 Mar 2025)
Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.
API access
How to call it
Call via OpenRouter with model id `google/gemma-3-27b-it`.
- openrouter ·
google/gemma-3-27b-it· Docs
OpenRouter id: google/gemma-3-27b-it
Price
What Gemma 3 27B costs, over time
$0.080 to $0.080
$0.450 to $0.160
Prices by host
| Host | Price | Over time | Checked |
|---|---|---|---|
| deepinfraInput | $0.064 per million input tokensSince 15 Nov 2026 | 1 change | OpenRouter models API |
| deepinfraOutput | $0.128 per million output tokensSince 15 Nov 2026 | 1 change | OpenRouter models API |
| nebiusCached input | $0.040 per million cached input tokensSince 27 Oct 2026 | No change recorded | OpenRouter models API |
| nebiusInput | $0.100 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| nebiusOutput | $0.300 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| nextbitCached input | $0.040 per million cached input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| nextbitInput | $0.080 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| nextbitOutput | $0.350 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| novitaInput | $0.119 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| novitaOutput | $0.200 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| parasailCached input | $0.040 per million cached input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| parasailInput | $0.080 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| parasailOutput | $0.450 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
Usage
How much Gemma 3 27B is used
3.9B to 2.3B
Scores
How Gemma 3 27B scores
Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.
| Score | Value | Source | Checked |
|---|---|---|---|
| Artificial Analysis Intelligence Index | 4.9indexAs of 26 Oct 2026 | Artificial Analysis via OpenRouter | |
| Artificial Analysis Coding Index | 10.1indexAs of 17 Nov 2026 | Artificial Analysis via OpenRouter | |
| Artificial Analysis Agentic Index | 0.1indexAs of 17 Nov 2026 | Artificial Analysis via OpenRouter | |
| Aider polyglot (best-across-versions) | 4.9percentAs of 12 Mar 2025 | Epoch AI (CC BY 4.0) | |
| Dtbench (best-across-versions) | 52.5percentAs of 12 Mar 2025 | Epoch AI (CC BY 4.0) | |
| Fiction livebench (best-across-versions) | 33.3percentAs of 11 Mar 2025 | Epoch AI (CC BY 4.0) | |
| Geobench (best-across-versions) | 52percentAs of 12 Mar 2025 | Epoch AI (CC BY 4.0) | |
| Gpqa diamond (best-across-versions) | 47.7percentAs of 12 Mar 2025 | Epoch AI (CC BY 4.0) | |
| Lech mazur writing (best-across-versions) | 79.9percentAs of 12 Mar 2025 | Epoch AI (CC BY 4.0) | |
| Lmca (best-across-versions) | 12.3percentAs of 12 Mar 2025 | Epoch AI (CC BY 4.0) | |
| Math level 5 (best-across-versions) | 74percentAs of 12 Mar 2025 | Epoch AI (CC BY 4.0) | |
| Otis mock aime 2024 2025 (best-across-versions)Saturated | 22.5percentAs of 12 Mar 2025 | Epoch AI (CC BY 4.0) |
- Saturated
- Top models score close to the maximum, so this test no longer separates them.
Sources
Where this comes from
- OpenRouter models APIThird party
- OpenRouter models APIOfficial
- Epoch AI (CC BY 4.0)Third party
- Epoch AI (CC BY 4.0)Third party
- Epoch AI (CC BY 4.0)Third party
A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.
Changelog
What changed
Price changed
output per mtok: 0.45 to 0.16
Price changed
output per mtok: 0.35 to 0.45
Price changed
output per mtok: 0.16 to 0.128
Price changed
input per mtok: 0.08 to 0.064
Price changed
output per mtok: 0.45 to 0.35
Price changed
output per mtok: 0.35 to 0.45
Price changed
output per mtok: 0.3 to 0.45
Price changed
input per mtok: 0.1 to 0.08
Price changed
output per mtok: 0.45 to 0.3
Price changed
input per mtok: 0.08 to 0.1
Price changed
output per mtok: 0.16 to 0.45
USAGE / OPENROUTER
How much Gemma 3 27B is used
Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.
- Tokens, last 7 days
- 18B ▼50.5%
- Requests, last 7 days
- 12M
- Tool calls, last 7 days
- 7.4K
- Average cost per request
- 2.0¢
- Price per million tokens
- $0.08 in · $0.16 out
MODEL FIELD GUIDE / SOURCE EVIDENCE
What you can do with Gemma 3 27B.
Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-19. Hosting routes and app features can differ.
google/gemma-3-27b-it- Tool calling
- Listed support
- Structured output
- Listed support
- Reasoning controls
- Not established
- Availability
- available
- Price basis
- token
- Licence verification
- Gemma Terms of Use, open weights (access request)
- Context length
- 131K tokens
- Knowledge cutoff
- 31 Aug 2024
- Developer release date
- Not established
- First seen in the catalogue
- 12 Mar 2025
- Listed retirement date
- Not established
Inspect the sources and their scope
google/gemma-3-27b-it: listed route capabilities, availability and prices; provider endpoints can differ.
Checked 2026-11-19Source for first seen, tool calling, context length, input, knowledge cutoff, output, structured output.
Checked 2026-11-19Licence declared in the google/gemma-3-27b-it model repository on Hugging Face, which holds the weights files behind an access request. Read the licence terms before use.
Checked 2026-11-14FROM SPECIFICATIONS TO YOUR WORK
Is this the right model for your job?
Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.
What would it cost?
Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.
Enter a whole number of runs from 1 to 100,000,000.
Working out the cost...
Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗
Check the source
Price date: 18 Nov 2026, from OpenRouter models API. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.
Model source & availability ↗Understand the evidence
Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.
Coding Index: 10.1 (2026-11-17) ↗Agentic Index: 0.1 (2026-11-17) ↗Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.