Zephyr 7B Beta API Pricing
As of October 10, 2026, Zephyr 7B Beta costs $0.15 per 1M input tokens and $0.15 per 1M output tokens from Anyscale, the lowest of 2 providers. It has a 16,384-token context window and returns up to 16,384 tokens per response.
- Input
- $0.15 / 1M tokens
- Output
- $0.15 / 1M tokens
- Context window
- 16,384 tokens
- Max output
- 16,384 tokens
- Providers
- 2
- Added to LiteLLM
- November 2023
Zephyr 7B Beta pricing by provider
2 listings across 2 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Context |
|---|---|---|---|---|
| Anyscale | anyscale/HuggingFaceH4/zephyr-7b-beta | $0.15 | $0.15 | 16K |
| Fireworks AI | fireworks_ai/accounts/fireworks/models/zephyr-7b-beta | $0.20 | $0.20 | 32K |
What Zephyr 7B Beta costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Anyscale | $0.375 |
| Fireworks AI | $0.50 |
Use Zephyr 7B Beta with LiteLLM
Call Zephyr 7B Beta through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="anyscale/HuggingFaceH4/zephyr-7b-beta",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: zephyr-7b-beta
litellm_params:
model: anyscale/HuggingFaceH4/zephyr-7b-beta
# credentials: see the provider's LiteLLM docs pagecurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "zephyr-7b-beta",
"messages": [{"role": "user", "content": "Hello!"}]
}'Zephyr 7B Beta FAQ
How much does Zephyr 7B Beta cost?
Zephyr 7B Beta costs $0.15 per 1M input tokens and $0.15 per 1M output tokens from Anyscale, the lowest of 2 providers.
What is the context window of Zephyr 7B Beta?
Zephyr 7B Beta has a 16,384-token context window and returns up to 16,384 tokens per response.
Which providers offer Zephyr 7B Beta?
Zephyr 7B Beta is available from 2 providers through LiteLLM: Anyscale and Fireworks AI. The lowest price is on Anyscale.
How do I call Zephyr 7B Beta with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="anyscale/HuggingFaceH4/zephyr-7b-beta", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
When did LiteLLM add Zephyr 7B Beta?
Zephyr 7B Beta was added to LiteLLM's model price file in November 2023.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request.
LiteLLM docs: Fireworks AI.
Provider pages: Anyscale, Fireworks AI.