Last refreshed 2026-09-30. Next refresh: weekly.
Why use Nous Capybara 34B on Fireworks AI?
Fireworks AI offers Nous Capybara 34B with pay-as-you-go pricing at $0.90/1M input tokens. Fireworks AI offers a generative AI platform as a service, focusing on rapid product iteration and cost-efficient AI deployment.
Setup recipe
Python + curlpip install openaiexport FIREWORKS_API_KEY=...import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["FIREWORKS_API_KEY"],nous-capybara-34bRequest example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["FIREWORKS_API_KEY"],
base_url="https://api.fireworks.ai/inference/v1"
)
response = client.chat.completions.create(
model="nous-capybara-34b",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Fireworks model IDs use "accounts/fireworks/models/{model-name}" format, e.g. "accounts/fireworks/models/llama4-scout-instruct-basic" or "accounts/fireworks/models/deepseek-r1".
- The examples expect FIREWORKS_API_KEY; rename it only if your application config maps the new variable.
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.90 |
| Output tokens | $0.90 |
Capabilities
No model capability flags are currently sourced.
About Nous Capybara 34B
The Nous Capybara 34B, developed by NousResearch, is a cutting-edge large language model built on the Yi-34B architecture. It stands out with its remarkable 200K context length, enabling effective handling of vast input data. Excelling in tasks such as text generation, conversational AI, complex summarization, and information recall, the model is trained on a concise dataset of 20,000 examples, enhanced by the Amplify-Instruct synthesis technique. This transformer-based model provides multiple quantization formats for varied hardware capacities, though it faces challenges like small dataset size and potential accuracy trade-offs.