Together AI API

Together AI is a platform for running large language models in the cloud with fast inference.

Get startedTry in LoungeVisit company

Data & Privacy

HQ:US
Safety identifier:Not forwarded
API Training:No
Prompt Logging:No
Retention:0 days
SOC2:Type II Certified
Status Page
|Terms of Service
|Privacy Policy

Available Models

DeepSeek V4.1 Flash 1017

deepseek
deepseek-v4.1-flash-1017
Streaming
Vision
Tools
Reasoning
JSON Output
JSON Schema
Together AI
Context: 1.0M
Input
$0.3
/M tokens
Cached
$0.006
/M tokens
Output
$1.2
/M tokens
Get Started

DeepSeek V4.1 Flash

deepseek
deepseek-v4.1-flash
Streaming
Vision
Tools
Reasoning
JSON Output
JSON Schema
Together AI
Context: 1.0M
Input
$0.3
/M tokens
Cached
$0.006
/M tokens
Output
$1.2
/M tokens
Get Started

GLM-5.3 Flash

zai
glm-5.3-flash
Streaming
Vision
Tools
Reasoning
JSON Output
JSON Schema
Together AI
Context: 1.0M
Input
$0.15
/M tokens
Cached
$0.03
/M tokens
Output
$0.5
/M tokens
Get Started

GLM-5.3

zai
glm-5.3
Streaming
Tools
Reasoning
JSON Output
JSON Schema
Together AI
Context: 1.0M
Input
$1.4
/M tokens
Cached
$0.26
/M tokens
Output
$4.4
/M tokens
Get Started

Qwen3.8 2.4T A95B

alibaba
qwen3.8-2.4t-a95b
Streaming
Tools
Reasoning
JSON Output
JSON Schema
Together AI
Context: 1.0M
Input
$2
/M tokens
Cached
$0.25
/M tokens
Output
$6
/M tokens
Get Started

Muse Glimmer 30B

meta
muse-glimmer-30b
Streaming
Vision
Tools
Reasoning
JSON Output
JSON Schema
Together AI
Context: 131.1k
Input
$0.35
/M tokens
Cached
$0.04
/M tokens
Output
$1.5
/M tokens
Get Started

Kimi K3

moonshotPremium
kimi-k3
Streaming
Vision
Tools
Reasoning
JSON Output
Together AI
Context: 1MQuant: fp4
Input
$3
/M tokens
Cached
$0.3
/M tokens
Output
$15
/M tokens
Get Started

MiniMax M3

minimax
minimax-m3
Streaming
Reasoning
JSON Output
JSON Schema
Together AI
Context: 524.3kQuant: fp4
Input
$0.3
/M tokens
Cached
$0.06
/M tokens
Output
$1.2
/M tokens
Get Started

DeepSeek V4 Flash

deepseekScheduled for Deactivation
deepseek-v4-flash
Streaming
Tools
Reasoning
JSON Output
JSON Schema
Together AI
Context: 163.8k
Deactivating on Oct 22, 2026
Input
$0.14
/M tokens
Cached
$0.03
/M tokens
Output
$0.28
/M tokens
Get Started

DeepSeek V4 Pro

deepseek
deepseek-v4-pro
Streaming
Tools
Reasoning
JSON Output
JSON Schema
Together AI
Context: 1.0M
Input
$1.32
/M tokens
Cached
$0.13
/M tokens
Output
$3.96
/M tokens
Get Started

GLM-4.7

zai
glm-4.7
Streaming
Reasoning
Together AI
Context: 202.8k
Input
$0.45
/M tokens
Cached
—
/M tokens
Output
$2
/M tokens
Get Started

GPT OSS 120B

openai
gpt-oss-120b
Streaming
Tools
Reasoning
Together AI
Context: 131.1k
Input
$0.15
/M tokens
Cached
—
/M tokens
Output
$0.6
/M tokens
Get Started

Gemma 2 27B IT

google
gemma-2-27b-it-together
Streaming
Together AI
Context: 8.2k
Input
$0.08
/M tokens
Cached
—
/M tokens
Output
$0.08
/M tokens
Get Started

FAQ

Together AI API questions

Can't find an answer? Contact us

Create an LLM Gateway API key and point any OpenAI-compatible SDK at https://api.llmgateway.io/v1. Set the model to deepseek-v4.1-flash-1017. On pay-as-you-go keys, together-ai/deepseek-v4.1-flash-1017 pins every request to Together AI; DevPass coding plans do not support provider pinning. You do not need a separate Together AI account or SDK.