TO

Together AI

Serverless Featured

Serverless and dedicated inference for open-source LLMs, image, video, and audio models. GPU clusters available.

Features

OpenAI Compatible
Streaming
Batching
Fine-tuning
Embeddings
Vision
Audio
Function Calling
JSON Mode

Compliance

SOC 2
HIPAA
GDPR

Pricing Model

per token
Free tier: Available

Details

Models 47
API Base https://api.together.xyz
EmbeddingsGPU CloudImage GenerationLLM Inference

Model Catalog (47)

Model Type Input $/1M Output $/1M Context Speed Status
DeepSeek R1 0528
DeepSeek · 671B MoE
llm $3.00 $7.00 — —
DeepSeek V3.1
DeepSeek · 671B MoE
llm $0.600 $1.70 — —
DeepSeek V4 Flash
DeepSeek
0731
llm $0.140 $0.280 1.0M —
DeepSeek V4 Pro
DeepSeek
0813
llm $1.32 $3.96 1.0M —
DeepSeek V4.1 Flash
DeepSeek
llm $0.300 $1.20 1M —
Flux 2 Dev
Black Forest Labs
image gen $0.015/img — — —
Flux 2 Pro
Black Forest Labs
image gen $0.030/img — — —
GLM 5
Zhipu AI · 744B
llm $1.00 $3.20 — —
GLM 5.2
Z.ai
llm $1.40 $4.40 1.0M —
GLM 5.3
Z.ai
llm $1.40 $4.40 1.0M —
GLM 5.3 Flash
Z.ai
llm $0.150 $0.500 1.0M —
GPT Image 1.5
OpenAI
image gen $0.034/img — — —
GPT Image 2
OpenAI
image gen $0.053/img — — —
GPT OSS 120B
OpenAI · 117B MoE (5.1B active)
llm $0.150 $0.600 131k —
Gemini 3 Pro Image
Google
image gen $0.134/img — — —
Gemini 3.1 Flash Image
Google
image gen $0.047/img — — —
Gemini 3.1 Flash Lite Image
Google
image gen $0.069/img — — —
Gemma 3 4B
Google · 4B
llm $0.060 $0.120 — —
Hailuo 02
MiniMax
video gen $0.490/req — — —
Ideogram 3.0
Ideogram
image gen $0.060/img — — —
Inkling
Thinking Machines
llm $1.00 $4.05 524k —
Kimi K2
Moonshot AI · 1T MoE (32B active)
llm $1.00 $3.00 — —
Kimi K2.5
Moonshot AI · 1T MoE (32B active)
llm $0.500 $2.80 — —
Kimi K2.6
Moonshot AI · 1T MoE (32B active)
llm $1.20 $4.50 262k —
Kimi K2.7 Code
Moonshot AI · 1T MoE (32B active)
code $0.950 $4.00 262k —
Kimi K3
Moonshot AI
llm $3.00 $15.00 1.0M —
Llama 3.3 70B
Meta · 70B
llm $1.04 $1.04 — —
MiniMax M2.5
MiniMax
llm $0.300 $1.20 — —
MiniMax M3
MiniMax
llm $0.300 $1.20 524k —
Muse Glimmer 30B
Meta
llm $0.350 $1.50 131k —
PixVerse V6
PixVerse
video gen $0.090/req — — —
Qwen 3 8B
Alibaba · 8B
llm $0.170 $0.250 — —
Qwen 3.6 Plus
Alibaba
llm $0.500 $3.00 1M —
Qwen Image
Alibaba
image gen $0.0058/img — — —
Qwen Image 2.0
Alibaba
image gen $0.035/img — — —
Qwen Image 2.0 Pro
Alibaba
image gen $0.075/img — — —
Qwen3.7 Max
Alibaba
llm $1.50 $4.50 — —
Qwen3.7 Plus
Alibaba
llm $0.320 $1.28 1M —
Qwen3.8 2.4T A95B
Alibaba
llm $2.00 $6.00 — —
Qwen3.8 Flash
Alibaba
llm $0.090 $0.282 1M —
Seedance 2.0
ByteDance
video gen $0.160/req — — —
Seedream 3.0
ByteDance
image gen $0.018/img — — —
Seedream 4.0
ByteDance
image gen $0.030/img — — —
Seedream 5.0 Lite
ByteDance
image gen $0.035/img — — —
Sonic
Cartesia
text to_speech — — — —
Veo 3.1
Google
video gen $0.080/req — — —
Whisper Large V3
OpenAI · 1.5B
speech to_text $0.0000/sec — — —

Together AI API FAQ

Is the Together AI API free?

Yes, Together AI has a free tier. Paid usage is billed per model.

What is the cheapest Together AI model?

Gemma 3 4B at $0.06 in / $0.12 out per 1M tokens, based on the 47 models we track for Together AI.

How many models does Together AI offer?

We track 47 Together AI models: 26 LLM, 14 image generation, 4 video generation, 1 coding, 1 text-to-speech, 1 speech-to-text.

Is the Together AI API OpenAI-compatible?

Yes. Together AI exposes an OpenAI-compatible endpoint, so you can use the OpenAI SDKs by changing the base URL and API key.

Subscribe to our newsletter

News and updates, 1–2 emails per month. No spam.