Llama models

Llama-3.3-70B-Instruct-Turbo and DeepSeek-V4-Flash-0731 deprecated on serverless

Together AI · Llama-3.3-70B-Instruct-Turbo

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

Together AI · Llama-Guard-4-12B

Qwen3-235B-A22B-Instruct-2507-tput, Llama-3-8B-Instruct-Lite and GLM-5.1 deprecated on serverless

Together AI · Llama Meta-Llama-3-8B-Instruct-Lite

GLM-5.1 and four other models deprecated on serverless

Together AI · Llama Meta-Llama-3-8B-Instruct-Lite

Price increases for Qwen3.5-9B, Llama 3 8B Lite and Llama 3.3 70B Turbo

Together AI · Llama Meta-Llama-3-8B-Instruct-Lite · Llama-3.3-70B-Instruct-Turbo

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

Together AI · Llama Meta Llama 3.2 3B Instruct

Workers AI - Planned model deprecations on Workers AIDeprecation

Cloudflare · Llama 3.1 70B Instruct · Llama 3.1 8B Instruct · Was due May 30, 2026

Llama-4-Maverick-17B-128E-Instruct-FP8 deprecated

Together AI · Llama-4-Maverick-17B-128E-Instruct-FP8

Amazon SageMaker AI now supports serverless reinforcement fine-tuning for 12 additional models

AWS · Llama Meta Llama 3.2 3B Instruct

Kimi-K2-Thinking and Mxbai-Rerank-Large-V2 deprecated, with two other models

Together AI · Llama-3.2-3B-Instruct-Turbo

FLUX.1-dev, Qwen3-VL-32B-Instruct and 11 other models deprecated

Together AI · Llama Meta-Llama-3.1-70B-Instruct-Turbo

Ten models deprecated, including Llama-4-Scout-17B-16E and Qwen2.5-72B-Instruct-Turbo

Together AI · Llama-4-Scout-17B-16E-Instruct · Llama Meta-Llama-3.1-405B-Instruct-Turbo

DeepSeek-R1-Distill-Llama-70B, Llama 3 70B Turbo and two other models deprecated

Together AI · Llama Meta-Llama-3-70B-Instruct-Turbo · Llama Meta-Llama-Guard-3-8B

Streaming supported for all models, plus reasoning_format parameter for reasoning models

Cerebras · Llama 3.3 70B

Announcing on-demand deployment for custom Meta Llama models in Amazon Bedrock

AWS · Llama 3.3

Fine-tuning adds gpt-oss-120b, DeepSeek-V3.1 and Llama 4 models

Together AI

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

Together AI · Llama-3.2-90B-Vision-Instruct-Turbo

Llama 4 Maverick in preview as llama-4-maverick-17b-128e-instruct

Cerebras · Llama 4 Maverick

Supervised fine-tuning supports Llama 4 Scout and Llama 4 Maverick, text only

Fireworks AI · Llama 4 Scout · Llama 4 Maverick

Amazon Bedrock models get FedRAMP High and DoD IL-4/5 approval in AWS GovCloud (US)

AWS · Llama 3 8B · Llama 3 70B

Meta’s Llama 4 now available fully managed in Amazon BedrockGA

AWS · Llama 4 Scout 17B · Llama 4 Maverick 17B

Workers AI for Developer Week - faster inference, new models, async batch API, expanded LoRA support

Cloudflare · llama-3.3-70b-instruct-fp8-fast

Llama 4 Scout added as llama-4-scout-17b-16e-instruct, with better tool calling

Cerebras · Llama 4 Scout

Meta’s Llama 4 now available in Amazon SageMaker JumpStartGA

AWS · Llama 4 Scout 17B · Llama 4 Maverick 17B

Meta’s Llama 3.2 models are now available for fine-tuning in Amazon BedrockGA

AWS · Llama 3.2 1B · Llama 3.2 3B · Llama 3.2 11B · Llama 3.2 90B

AI Gateway adds Cerebras, ElevenLabs, and Cartesia as new providers

Cloudflare · Llama 3.1 8B · Llama 3.3 70B