Nous Capybara 7B V1.9 on Together AI

Capybara · Nous Research

ServerlessOpen Source

Last refreshed 2026-06-15. Next refresh: weekly.

Why use Nous Capybara 7B V1.9 on Together AI?

Together AI offers Nous Capybara 7B V1.9 with pay-as-you-go pricing at $0.20/1M input tokens. Together AI is a platform for running open-source and proprietary LLMs with fast serverless and dedicated endpoints at competitive inference pricing.

Compare Nous Capybara 7B V1.9 across 2 providers to find the best fit for your use case
Input / 1M
$0.20
Output / 1M
$0.20
Cache
Not sourced
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install together
Auth
export TOGETHER_API_KEY=...
Call
from together import Together
client = Together()  # reads TOGETHER_API_KEY from env
response = client.chat.completions.create(
    model="nous-capybara-7b-v1.9",
Model ID
nous-capybara-7b-v1.9

Request example

from together import Together

client = Together()  # reads TOGETHER_API_KEY from env
response = client.chat.completions.create(
    model="nous-capybara-7b-v1.9",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Gotchas

  • Together uses "organization/model-name" format, e.g. "meta-llama/Llama-4-Scout-17B-16E-Instruct" or "Qwen/QwQ-32B". See the Together model catalog for the exact ID.
  • The examples expect TOGETHER_API_KEY; rename it only if your application config maps the new variable.

Compare Nous Capybara 7B V1.9 Across Providers

ProviderInput (per 1M)Output (per 1M)
Fireworks AI$0.20$0.20
Together AI$0.20$0.20

Pricing

TypePrice (per 1M)
Input tokens$0.20
Output tokens$0.20

Capabilities

Structured Outputs

About Nous Capybara 7B V1.9

The Nous Capybara 7B V1.9 is a cutting-edge large language model created by NousResearch, featuring 7 billion parameters. It's an advancement in the Capybara series, utilizing the novel Amplify-Instruct data synthesis technique to create a focused training dataset comprising 20,000 curated conversational examples, most of which include new, innovative tokens. Built on the Mistral architecture, it excels in multi-turn conversations, adeptly summarizing complex topics and recalling information up to late 2022. Despite its innovative framework, it faces challenges due to a smaller dataset, which may limit its generalization and introduce uncertainties related to scalability and biases.

Get Started

Model Specs

Released2024-10-31
Parameters7B
ArchitectureDecoder Only