airoboros L2 70B 2.2.1 on DeepInfra

airoboros · Jon Durbin

ServerlessOpen Weights

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

Why use airoboros L2 70B 2.2.1 on DeepInfra?

DeepInfra offers airoboros L2 70B 2.2.1 with pay-as-you-go pricing at $0.45/1M input tokens. DeepInfra is a cloud inference platform offering cost-effective access to open-source AI models.

Input / 1M
$0.45
Output / 1M
$0.65
Cache
Not sourced
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install openai
Auth
export DEEPINFRA_API_KEY=...
Call
import os
from openai import OpenAI
client = OpenAI(
    api_key=os.environ["DEEPINFRA_API_KEY"],
Model ID
airoboros-l2-70b-2.2.1

Request example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["DEEPINFRA_API_KEY"],
    base_url="https://api.deepinfra.com/v1/openai"
)
response = client.chat.completions.create(
    model="airoboros-l2-70b-2.2.1",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Gotchas

  • DeepInfra uses "organization/model-name" format, e.g. "meta-llama/Meta-Llama-3-8B-Instruct" or "mistralai/Mistral-7B-Instruct-v0.3". See the DeepInfra model catalog for exact IDs.
  • The examples expect DEEPINFRA_API_KEY; rename it only if your application config maps the new variable.

Pricing

TypePrice (per 1M)
Input tokens$0.45
Output tokens$0.65

Capabilities

Structured Outputs

About airoboros L2 70B 2.2.1

The Airoboros L2 70B 2.2.1, built on the Llama 2 architecture, is a large language model optimized for instruction following rather than casual conversation. With 70 billion parameters, it excels in tasks like instruction following, question answering, summarization, and coding. The model employs a unique prompting format, A chat.\nUSER: {prompt}\nASSISTANT:, and benefits from using explicit delimiters to reduce hallucinations in closed-context instructions. A limitation is that Q4_0 quantization yields unusable outputs.

Get Started

Model Specs

Released2023-07-15
Parameters70B
ArchitectureDecoder Only