Kimi models

Kimi K3.1 Pro added to Dedicated catalog, with image inputs and reasoning levels

Cerebras · Kimi K3.1 Pro

Kimi K3.1 Pro (Highspeed) now available on Amazon BedrockGA

AWS · Kimi K3.1 Pro

moonshotai/Kimi-K3.1-Pro on serverless, with 1,048,576-token context

Together AI · Kimi K3.1 Pro

Workers AI - Planned model deprecations on Workers AIDeprecation

Cloudflare · Kimi K2.6 · Due Nov 15, 2026

Kimi-K3.1-Pro available for LoRA post-training on B200-SXM

Together AI · Kimi K3.1 Pro

Kimi K3, GLM 5.3 Flash and three more models added to Dedicated catalog

Cerebras · Kimi K3

Kimi-K3 post-training context raised to 163,840 tokens from 65,536

Together AI · Kimi K3

Kimi-K3 available for deployment on dedicated endpoints

Together AI · Kimi K3

Kimi-K3 price rises to $3.00 input and $15.00 output per 1M tokens

Together AI · Kimi K3

Serverless deprecation takes effect for DeepSeek V4, Kimi K2 and GLM 5.2 models

Fireworks AI · Kimi K2.6

Kimi K3 by Moonshot AI is now generally available on Amazon BedrockGA

AWS · Kimi K3

Fireworks serverless decommissions DeepSeek V4, GLM 5.2 and Kimi K2 models on Sept 25

Fireworks AI · Kimi K2.6

MiniMax M2.7, GPT OSS 20B and three more models deprecated from serverless

Fireworks AI · Kimi K2.6 Turbo

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

Together AI · Kimi K2.7 Code

FLUX.1-schnell, Qwen2.5-7B and Kimi-K2.6 deprecated on serverless

Together AI · Kimi K2.6

Many Qwen, Kimi, GLM, DeepSeek and Llama models deprecated for fine-tuning

Together AI · Kimi K2.5

Workers AI - Select models now require the Workers Paid planPrice

Cloudflare · Kimi K2.6 · Kimi K2.7 Code

Kimi K3 available on serverless with a 1,000,000-token context length

Together AI · Kimi K3

Kimi K2.5 and Qwen 3.6 Plus deprecated from serverless

Fireworks AI · Kimi K2.5 · Kimi K2.6

Fine-tuning now supports Kimi-K2.7-Code and Kimi-K2.6

Together AI · Kimi K2.7 Code · Kimi K2.6

Kimi-K2.7-Code available on serverless with 262,144 context, $0.95 input per 1M

Together AI · Kimi K2.7 Code

Kimi K2.7 Code, MiniMax M3 and Qwen 3.7 Plus added to the Model Library

Fireworks AI · Kimi K2.7 Code

Workers AI - Moonshot AI Kimi K2.7 Code now available on Workers AIGA

Cloudflare · Kimi K2.7 Code

Kimi-K2.5 deprecated and removed from serverless

Together AI · Kimi K2.5

Workers AI - Planned model deprecations on Workers AIDeprecation

Cloudflare · Kimi K2.5 · Was due May 30, 2026

GLM 5, GLM 5.1 and Kimi K2.6 supported on Cerebras Dedicated Endpoints

Cerebras · Kimi K2.6

Kimi-K2.6 from Moonshot AI now available on serverless

Together AI · Kimi K2.6

Workers AI - Moonshot AI Kimi K2.6 now available on Workers AIGA

Cloudflare · Kimi K2.6

Workers AI - Moonshot AI Kimi K2.5 now available on Workers AIGA

Cloudflare · Kimi K2.5

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

Together AI · Kimi K2 Thinking · Kimi-K2-Instruct

Kimi-K2.5 now available on serverless

Together AI · Kimi K2.5

Kimi-K2, DeepSeek-V3 and DeepSeek-R1 now redirect to upgraded versions

Together AI · Kimi-K2

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

AWS · Kimi K2 Thinking

Kimi K2 Thinking on serverless, GitHub evaluator templates and RFT step endpoints

Fireworks AI · Kimi K2 Thinking

GLM-4.6 and Kimi-K2-Thinking now available on serverless

Together AI · Kimi K2 Thinking

Kimi-K2-Instruct-0905, an upgraded 1 trillion parameter MoE model, added

Together AI · Kimi-K2-Instruct

Moonshot AI's Kimi-K2-Instruct 1T-parameter MoE model now available

Together AI · Kimi-K2-Instruct