Models · Best vision
Gemma 4 31B (free)
by Google
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.
Our verdict
We have not reviewed Gemma 4 31B (free) 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 4 31B (free)
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.
Notes
Gemma 4 31B (free) is listed in the EDNA Models directory from the OpenRouter catalogue.
Key facts
What we have checked
- Price on chutes
- $0.012 per million cached input tokens
- Price on chutes
- $0.120 per million input tokens
- Price on chutes
- $0.370 per million output tokens
- Price on coreweave
- $0.100 per million cached input tokens
- Price on coreweave
- $0.100 per million input tokens
- Price on coreweave
- $0.340 per million output tokens
- Price on crusoe
- $0.140 per million cached input tokens
- Price on crusoe
- $0.140 per million input tokens
- Price on crusoe
- $0.400 per million output tokens
- Gpqa diamond
- 75.8% (for 2 Apr 2026)
- Simpleqa verified
- 10.4% (for 2 Apr 2026)
- Dtbench
- 82.7% (for 2 Apr 2026)
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-4-31b-it:free`.
- openrouter ·
google/gemma-4-31b-it:free· Docs
OpenRouter id: google/gemma-4-31b-it:free
Price
What Gemma 4 31B (free) costs, over time
Prices by host
| Host | Price | Over time | Checked |
|---|---|---|---|
| chutesCached input | $0.012 per million cached input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| chutesInput | $0.120 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| chutesOutput | $0.370 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| coreweaveCached input | $0.100 per million cached input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| coreweaveInput | $0.100 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| coreweaveOutput | $0.340 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| crusoeCached input | $0.140 per million cached input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| crusoeInput | $0.140 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| crusoeOutput | $0.400 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| deepinfraInput | $0.160 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| deepinfraOutput | $0.320 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| dekallmCached input | $0.050 per million cached input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| dekallmInput | $0.140 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| dekallmOutput | $0.400 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| friendliInput | $0.140 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| friendliOutput | $0.400 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| io-netCached input | $0.180 per million cached input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| io-netInput | $0.361 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| io-netOutput | $1.09 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| modalCached input | $0.100 per million cached input tokensSince 7 Nov 2026 | No change recorded | OpenRouter models API |
| modalInput | $0.340 per million input tokensSince 7 Nov 2026 | No change recorded | OpenRouter models API |
| modalOutput | $0.100 per million output tokensSince 7 Nov 2026 | No change recorded | OpenRouter models API |
| modelrunCached input | $0.200 per million cached input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| modelrunInput | $0.750 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| modelrunOutput | $1.00 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| nextbitCached input | $0.060 per million cached input tokensSince 7 Nov 2026 | No change recorded | OpenRouter models API |
| nextbitInput | $0.150 per million input tokensSince 7 Nov 2026 | No change recorded | OpenRouter models API |
| nextbitOutput | $0.400 per million output tokensSince 7 Nov 2026 | No change recorded | OpenRouter models API |
| novitaInput | $0.140 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| novitaOutput | $0.400 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| parasailCached input | $0.060 per million cached input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| parasailInput | $0.150 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| parasailOutput | $0.400 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| prime-intellectCached input | $0.100 per million cached input tokensSince 10 Nov 2026 | 1 change | OpenRouter models API |
| prime-intellectInput | $0.200 per million input tokensSince 10 Nov 2026 | 1 change | OpenRouter models API |
| prime-intellectOutput | $0.335 per million output tokensSince 10 Nov 2026 | 1 change | OpenRouter models API |
| sambanovaInput | $0.380 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| sambanovaOutput | $1.15 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| siliconflowCached input | $0.250 per million cached input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| siliconflowInput | $0.750 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| siliconflowOutput | $1.00 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| veniceCached input | $0.090 per million cached input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| veniceInput | $0.120 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| veniceOutput | $0.360 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
Scores
How Gemma 4 31B (free) 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 |
|---|---|---|---|
| Dtbench (best-across-versions) | 82.7percentAs of 2 Apr 2026 | Epoch AI (CC BY 4.0) | |
| Gpqa diamond (best-across-versions) | 75.8percentAs of 2 Apr 2026 | Epoch AI (CC BY 4.0) | |
| Lmca (best-across-versions) | 39.3percentAs of 2 Apr 2026 | Epoch AI (CC BY 4.0) | |
| Otis mock aime 2024 2025 (best-across-versions)Saturated | 73.3percentAs of 2 Apr 2026 | Epoch AI (CC BY 4.0) | |
| Simpleqa verified (best-across-versions) | 10.4percentAs of 2 Apr 2026 | Epoch AI (CC BY 4.0) | |
| Surface evolver bench (best-across-versions) | 30.6percentAs of 2 Apr 2026 | Epoch AI (CC BY 4.0) | |
| Weirdml (best-across-versions) | 52.3percentAs of 2 Apr 2026 | Epoch AI (CC BY 4.0) |
- Saturated
- Top models score close to the maximum, so this test no longer separates them.
Compare
Compare Gemma 4 31B (free) side by side
Sources
Where this comes from
- OpenRouter models APIThird party
- 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
cached input per mtok: 0.2 to 0.1
Price changed
output per mtok: 0.67 to 0.335
Price changed
input per mtok: 0.4 to 0.2
Price changed
output per mtok: 0.34 to 0.4
Price changed
input per mtok: 0.09 to 0.2
Price changed
output per mtok: 0.55 to 0.34
Price changed
input per mtok: 0.22 to 0.09
Price changed
output per mtok: 0.35 to 0.55
Price changed
input per mtok: 0.12 to 0.22
MODEL FIELD GUIDE / SOURCE EVIDENCE
What you can do with Gemma 4 31B (free).
Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-07. Hosting routes and app features can differ.
google/gemma-4-31b-it:free- Tool calling
- Listed support
- Structured output
- Listed support
- Reasoning controls
- Listed support
- Availability
- available
- Price basis
- token
- Licence verification
- Apache 2.0, open weights
- Context length
- 262K tokens
- Knowledge cutoff
- Not established
- Developer release date
- Not established
- First seen in the catalogue
- 2 Apr 2026
- Listed retirement date
- Not established
Inspect the sources and their scope
google/gemma-4-31b-it:free: listed route capabilities, availability and prices; provider endpoints can differ.
Checked 2026-11-07Source for reasoning controls, first seen, tool calling, context length, input, output, structured output.
Checked 2026-11-07Licence declared in the google/gemma-4-31B-it model repository on Hugging Face, which holds the weights files. Read the licence terms before use.
Checked 2026-11-07FROM 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
No token price is known for this model yet. 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.
Intelligence Index: 4.4 (2026-11-09) ↗Coding Index: 43.4 (2026-11-09) ↗Agentic Index: 4.2 (2026-11-09) ↗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.