Model family
Gemma on FlexAI.Every variant. One key
Gemma is Google's open model line on FlexAI. 2 variants run serverless on the OpenAI-compatible API, with 2 more available as dedicated endpoints, spanning chat, multimodal, vision. One API key serves every variant.
Variants
Every served variant in the family, with live serverless pricing.
Serverless · pay per token
| Model | Context | Price | Status |
|---|---|---|---|
| Gemma 4 31B IT | 256K | $0.108 / $0.315 per M | Serving |
| Gemma 4 26B A4B | 256K | $0.054 / $0.27 per M | Serving |
Dedicated endpoints · reserved GPUs
| Model | Context | Price | Status |
|---|---|---|---|
| Gemma 3 27B IT | 128K | Dedicated | Dedicated |
| Gemma 3n E4B Instruct | 32K | Dedicated | Dedicated |
Which variant for what
Pick by the role you're filling. Same key for all of them.
Fast & economical
Gemma 4 26B A4B
Gemma 4 26B A4B is the smallest serverless variant. Lowest latency and cost.
Gemma 4 31B IT runs describe & qa in multimodal generation
Call the flagship
OpenAI-compatible. Swap the model id for any variant above.
curl https://tokens.flex.ai/v1/chat/completions \
-H "Authorization: Bearer $FLEXAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemma-4-31b-it",
"messages": [{"role": "user", "content": "Hello from FlexAI"}]
}'Where it runs
Use cases that put Gemma to work in a pipeline.
Run Gemma on one API key
Every Gemma variant, serverless and dedicated, behind one OpenAI-compatible key.
$10/month in free credits for your first 3 months