Japanese StableLM 70B on Fireworks AI

Name: Japanese StableLM 70B on Fireworks AI
Brand: Stability AI
Price: 0.90 USD

Provisioned

Last refreshed 2026-04-19. Next refresh: weekly.

Why use Japanese StableLM 70B on Fireworks AI?

Fireworks AI offers Japanese StableLM 70B 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.

Input / 1M

$0.90

Output / 1M

$0.90

Cache

Not sourced

Batch

Not sourced

Setup recipe

Python + curl

Install

pip install openai

Auth

export FIREWORKS_API_KEY=...

Call

import os
from openai import OpenAI
client = OpenAI(
    api_key=os.environ["FIREWORKS_API_KEY"],

Model ID

japanese-stablelm-70b

Request 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="japanese-stablelm-70b",
    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 Japanese StableLM 70B

The Japanese StableLM 70B is a highly advanced large language model developed by Stability AI Japan, drawing from the Llama 2 architecture. It is purpose-built for tasks in the Japanese language, featuring an impressive 70 billion parameters, making it one of the largest open-source Japanese language models as of November 2023. This model excels in generating human-like Japanese text, effective question answering, and adeptly following instructions in Japanese. Its training encompassed approximately 100 billion tokens from wide-ranging Japanese and English sources, ensuring a robust linguistic capability. However, users should be mindful of its limitations, such as potential biases and contextual challenges due to its dependence on the quality of training data. Notably, the model is complemented by smaller, faster versions and a special "JA-Vocab Beta" version for enhanced performance.