Overview
About this model
Gemma-4-31B-IT is a multimodal model that understands both images and text, served on EcoHash through an OpenAI-compatible API.
View model card on HuggingFaceSpecifications
Model details
- Provider
- Modality
- Vision
- Pricing
- $0.50 in · $0.50 out / 1M
API
Call it in code
Use the OpenAI-compatible endpoint below with your EcoHash API key and this model ID.
Python
from openai import OpenAI
client = OpenAI(
base_url="https://api.ecohash.com/v1",
api_key="YOUR_API_KEY",
)
response = client.chat.completions.create(
model="gemma-4-31b-it",
messages=[{"role": "user", "content": [
{"type": "text", "text": "Describe this image"},
{"type": "image_url", "image_url": {"url": "..."}},
]}],
)curl
curl https://api.ecohash.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d {
"model": "gemma-4-31b-it",
"messages": [{"role": "user", "content": [
{"type": "text", "text": "Describe this image"},
{"type": "image_url", "image_url": {"url": "..."}}
]}]
}Compare
Gemma-4-31B-IT vs other vision models
Same API, same billing. Rates come live from the EcoHash billing system.
| Model | Context | Price | Modalities |
|---|---|---|---|
| Gemma-4-31B-IT (this page) | — | $0.50 per 1M input tokens and $0.50 per 1M output tokens | — |
| Qwen2.5-VL-7B-Instruct | 32.8K tokens | $0.30 per 1M input tokens and $0.60 per 1M output tokens | text, image → text |
| Kimi-K2.6 | — | $1.08 per 1M input tokens and $4.50 per 1M output tokens | — |
| qwen3-omni-30b-a3b-instruct | — | $0.40 per 1M input tokens and $0.80 per 1M output tokens | text, image, audio, video → text, audio |
FAQ
Common questions
- How much does the Gemma-4-31B-IT API cost?
- Gemma-4-31B-IT is $0.50 per 1M input tokens and $0.50 per 1M output tokens on EcoHash. That figure comes live from the EcoHash billing system, so the price shown on this page is the price you are billed — there is no separate list price to reconcile.
- Gemma-4-31B-IT vs Qwen2.5-VL-7B-Instruct: which should I use?
- Both are vision models on the same OpenAI-compatible EcoHash API, so moving between them is a change of model id and nothing else. Gemma-4-31B-IT has $0.50 per 1M input tokens and $0.50 per 1M output tokens. Qwen2.5-VL-7B-Instruct has a 32.8K-token context window at $0.30 per 1M input tokens and $0.60 per 1M output tokens. Both prices come live from the EcoHash billing system; the comparison table on this page carries the current figures.
- Can I use Gemma-4-31B-IT commercially through EcoHash?
- EcoHash hosts Gemma-4-31B-IT under the model publisher's own licence and does not change its terms, so whether your use is permitted is decided by that licence — read it on the model card at https://huggingface.co/google/gemma-4-31B-it. The EcoHash Terms of Service additionally require you to comply with each model's licence and acceptable-use policy. Your EcoHash bill for API usage is separate from, and does not grant, any right under the model's licence.
More models
