Models / PrismML
Chat
Reasoning
Vision

Coming soon

Prism ML Ternary Bonsai 2 27B

Near-lossless 27B-class intelligence at 1.76 bits per weight

Notify me

This model is coming soon to Together’s Serverless API

Related models
View All
Chat
Kimi K3

  • Cached/1M

    $0.27

  • Input/1M

    $2.70

  • Output/1M

    $13.50
Serverless
Dedicated
Provisioned Throughput
Chat
Reasoning
Vision

moonshotai/Kimi-K3

Moonshot AI

Chat
Qwen3.8-2.4T-A95B

  • Cached/1M

    $0.25

  • Input/1M

    $2.00

  • Output/1M

    $6.00
Serverless
Dedicated
Chat
Reasoning
Vision

Qwen/Qwen3.8-2.4T-A95B

Qwen

Chat
NVIDIA Nemotron 3.5 Lightning
  • Parameters
    30B
Dedicated
Chat

nvidia/nemotron-3.5-lightning

NVIDIA

Chat
Muse Glimmer 30B

  • Cached/1M

    $0.04

  • Input/1M

    $0.35

  • Output/1M

    $1.50
Serverless
Dedicated
Chat
Vision

meta-models/Muse-Glimmer-30B

Meta

Chat
DeepSeek V4 Pro 0813

  • Cached/1M

    $0.13

  • Input/1M

    $1.32

  • Output/1M

    $3.96
Serverless
Dedicated
Reasoning
Chat
Code
LLM

deepseek-ai/DeepSeek-V4-Pro-0813

DeepSeek

Chat
GLM-5.3

  • Cached/1M

    $0.26

  • Input/1M

    $1.40

  • Output/1M

    $4.40
Serverless
Dedicated
Chat
Reasoning

zai-org/GLM-5.3

ZAI

new
Chat
GLM-5.3-Flash

  • Cached/1M

    $0.03

  • Input/1M

    $0.15

  • Output/1M

    $0.50
Serverless
Dedicated
Chat
Reasoning
Vision

zai-org/GLM-5.3-Flash

ZAI

new
Chat
DeepSeek V4.1 Flash

  • Cached/1M

    $0.006

  • Input/1M

    $0.30

  • Output/1M

    $1.20
Serverless
Dedicated
Chat
Reasoning
Vision

deepseek-ai/DeepSeek-V4.1-Flash

DeepSeek

new
Chat
Tev1 4B Experimental

  • Input/1M

    $0.04

  • Output/1M

    Free
  • Parameters
    4.7B
Serverless
Dedicated
Chat

together/Tev1-4B-experimental

Together AI

Free
Chat
Ternary Bonsai 27B

  • Input/1M

    $0.00

  • Output/1M

    $0.00
  • Parameters
    27B
Serverless
Chat
Reasoning
Vision

Prism-ML/Ternary-Bonsai-27B

PrismML

Chat
DeepSeek V4 Flash 0731

  • Cached/1M

    $0.03

  • Input/1M

    $0.14

  • Output/1M

    $0.28
Serverless
Dedicated
Chat
Reasoning

deepseek-ai/DeepSeek-V4-Flash-0731

DeepSeek

new
Chat
Qwen3.8 Flash

  • Input/1M

    $0.15

  • Output/1M

    $0.47
  • Parameters
    125B
Serverless
Chat
Reasoning
Vision

Qwen/Qwen3.8-Flash

Qwen

View All
Model specifications
Model data
  • Model provider
    PrismML
  • Type
    Chat
    Reasoning
    Vision
  • Parameters
    27B
  • Context length
    262.1K
  • Category
    Chat

Launching soon

Want to be notified when the model is available on Together AI?

You're on the list

We'll email you when the endpoint goes live. Until then, 200+ models are ready to call.

Browse Models
Continue