Gemma models

Workers AI - EmbeddingGemma 2 now available on Workers AIGA

Cloudflare · EmbeddingGemma 2 · Gemma EmbeddingGemma

gpt-oss-20b, gemma-4-31B-it and two other models deprecated on serverless

Together AI · gemma-4-31b-it

Gemma-4-31B-it-assistant and Gemma-4-31B-IT-NVFP4 models now available on Amazon SageMaker JumpStartGA

AWS · Gemma-4-31B-it-assistant · Gemma-4-31B-IT-NVFP4

gemma-4-31b removed from Cerebras public endpoints, still on Dedicated

Cerebras · Gemma 4 31B

Four serverless models deprecated, removal on September 14, 2026

Together AI · gemma-4-31b-it

Four models deprecated on serverless, including DeepSeek-V4-Pro and Kimi-K2.7-Code

Together AI · gemma-4-31b-it

Gemma 3n E4B and Llama Guard 4 12B deprecated on serverless

Together AI · gemma-3n-E4B-it

FLUX.2-small-decoder and gemma-4-12B-it models now available on Amazon SageMaker JumpStart

AWS · gemma-4-12B-it

Gemma 4 models are now available on Amazon Bedrock in AWS GovCloud (US-West)Region

AWS · Gemma 4 31B · Gemma 4 26B-A4B · Gemma 4 E2B

gemma-4-31b raises per-request image limit from 5 to 10 on public endpoints

Cerebras · Gemma 4 31B

gemma-4-31b added to Cline, Kilo Code, opencode and VS Code guides

Cerebras · Gemma 4 31B

google/gemma-4-12B-it available on serverless with 262,144-token context

Together AI · gemma-4-12B-it

Gemma-4-E2B-it for is now available in Amazon SageMaker JumpStart

AWS · Gemma-4-E2B-it

Fine-tuning now supports the vision-language model google/gemma-4-31B-it-VLM

Together AI · gemma-4-31B-it-VLM

Amazon SageMaker AI now supports serverless model customization for Gemma 4 models

AWS · Gemma 4 E4B · Gemma 4 31B

Gemma 4 31B in preview with image input via the Chat Completions API

Cerebras · Gemma 4 31B

GLM-5.1 and four other models deprecated on serverless

Together AI · gemma-3n-E4B-it

Gemma 4 models now available on Amazon BedrockGA

AWS · Gemma 4 31B · Gemma 4 26B-A4B · Gemma 4 E2B

Gemma, Qwen2.5 and Llama 3.2 among 17 models added to dedicated endpoints

Together AI · gemma-3-27b-it · gemma-3-1b-it

pearl-ai/gemma-4-31b-it available on serverless with 32,000 context length

Together AI · gemma-4-31b-it

google/gemma-4-31b-it price rises to $0.39 input, $0.97 output from May 21, 2026

Together AI · gemma-4-31b-it

Gemma 4 models are now available in Amazon SageMaker JumpStart

AWS · Gemma 4 E4B · Gemma 4 26B-A4B · Gemma 4 31B

Fine-tuning adds Qwen3.6-35B-A3B, Gemma 4 31B and Gemma 4 26B-A4B

Together AI · gemma-4-31b-it · gemma-4-26b-a4b-it

google/gemma-3n-E4B-it pricing rises to $0.06 input, $0.12 output per 1M tokens

Together AI · gemma-3n-E4B-it

Gemma 4 31B-it and GLM-5.1 available on serverless

Together AI · gemma-4-31b-it

AI Search - New Workers AI models for text generation and embedding in AI Search

Cloudflare · Gemma EmbeddingGemma-300M

Workers AI - Google Gemma 4 26B A4B now available on Workers AIGA

Cloudflare · Gemma 4 26B-A4B

gemma-4-26b-a4b-it and gemma-4-31b-it released in Gemini API and AI StudioGA

Google Gemini API · gemma-4-26b-a4b-it · gemma-4-31b-it

Playground category tabs, Contributor and Inference roles, and stop and resume for fine-tuning jobs

Fireworks AI · Gemma 3 12B Instruct · Gemma 3 4B Instruct

Amazon Bedrock adds 18 fully managed open weight models, the largest expansion of new models to dateGA

AWS · Gemma 3 27B

Fine-tuning context lengths increased for DeepSeek-R1-Distill, Gemma 3, Qwen and Llama models

Together AI · gemma-3-4b-it

Workers AI - Introducing EmbeddingGemma from Google on Workers AI

Cloudflare · Gemma EmbeddingGemma

17 models deprecated, including Llama 3.2 Vision and FLUX.1 canny, depth and redux

Together AI · gemma-2-27b-it

Experimental Gemini 2.0 Flash image generation, gemma-3-27b-it and YouTube URL inputPreview

Google Gemini API · gemma-3-27b-it