5 providers · 7 free models · Last updated: 01 Nov 2026
Google Gemma 4 models (26B and 31B parameter models with 256K context) are accessible for free on SambaNova Cloud, OpenRouter, and Requesty with zero credit card required.
Total available in this directory: 5 providers, 7 free models. Verified limits below.
Google Gemma 4 31B parameter model via SambaNova.
Base URL: https://api.sambanova.ai/v1
Model: gemma-4-31B-it
Provider: SambaNova Cloudfrom openai import OpenAI
client = OpenAI(
base_url="https://api.sambanova.ai/v1",
api_key="your-api-key", # from SambaNova Cloud
)
response = client.chat.completions.create(
model="gemma-4-31B-it",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)| Model | Provider | Cost | Context | RPM | TPM | RPD | Day tokens | Verified |
|---|---|---|---|---|---|---|---|---|
| google/gemma-4-26b-a4b-it:free | OpenRouter | $0 | 256K | 20 | Provider-dependent | 50 (below $10 credits) / 1,000 ($10+ credits) | Not published | 2026-11-01 |
| google/gemma-4-31b-it:free | OpenRouter | $0 | 256K | 20 | Provider-dependent | 50 (below $10 credits) / 1,000 ($10+ credits) | Not published | 2026-11-01 |
| gemma-4-26b-a4b-it | Google AI Studio (Gemini API) | $0 | 256K | 15 | 1M | 1,500 | Not published | 2026-11-01 |
| gemma-4-31b-it | Google AI Studio (Gemini API) | $0 | 256K | 15 | 1M | 1,500 | Not published | 2026-11-01 |
| ~80 free models (Llama 3.x/4, Qwen, Gemma, DeepSeek-R1 distills, FLUX, Whisper, BGE embeddings) | Cloudflare Workers AI | $0 | 8K-128K+ (model-dependent) | 300 text gen (720-1,500 other tasks) | Model-dependent | Not published | 10,000 neurons/day | 2026-08-30 |
| gemma-4-31B-it | SambaNova Cloud | $0 | 128K | 20 | Not published | 20 | 200K tokens/day | 2026-11-01 |
| google/gemma-4-31b-it | Requesty | $0 | 256K | Not published | Not published | 200/day shared | Not published | 2026-11-01 |
Machine-readable: Markdown Twin · providers.json · sitemap.xml