Bytez | liteLLM (original) (raw)
LiteLLM supports all chat models on Bytez!
That also means multi-modal models are supported 🔥
Tasks supported: chat, image-text-to-text, audio-text-to-text, video-text-to-text
Usage​
- SDK
- PROXY
API KEYS​
import os
os.environ["BYTEZ_API_KEY"] = "YOUR_BYTEZ_KEY_GOES_HERE"
Example Call​
from litellm import completion
import os
## set ENV variables
os.environ["BYTEZ_API_KEY"] = "YOUR_BYTEZ_KEY_GOES_HERE"
response = completion(
model="bytez/google/gemma-3-4b-it",
messages = [{ "content": "Hello, how are you?","role": "user"}]
)
Automatic Prompt Template Handling​
All prompt formatting is handled automatically by our API when you send a messages list to it!
If you wish to use custom formatting, please let us know via either help@bytez.com or on our Discord and we will work to provide it!
Passing additional params - max_tokens, temperature​
See all litellm.completion supported params here
# !uv add litellm
from litellm import completion
import os
## set ENV variables
os.environ["BYTEZ_API_KEY"] = "YOUR_BYTEZ_KEY_HERE"
# bytez gemma-3 call
response = completion(
model="bytez/google/gemma-3-4b-it",
messages = [{ "content": "Hello, how are you?","role": "user"}],
max_tokens=20,
temperature=0.5
)
proxy
model_list:
- model_name: gemma-3
litellm_params:
model: bytez/google/gemma-3-4b-it
api_key: os.environ/BYTEZ_API_KEY
max_tokens: 20
temperature: 0.5
Passing Bytez-specific params​
Any kwarg supported by huggingface we also support! (Provided the model supports it.)
Example repetition_penalty
# !uv add litellm
from litellm import completion
import os
## set ENV variables
os.environ["BYTEZ_API_KEY"] = "YOUR_BYTEZ_KEY_HERE"
# bytez llama3 call with additional params
response = completion(
model="bytez/google/gemma-3-4b-it",
messages = [{ "content": "Hello, how are you?","role": "user"}],
repetition_penalty=1.2,
)
proxy
model_list:
- model_name: gemma-3
litellm_params:
model: bytez/google/gemma-3-4b-it
api_key: os.environ/BYTEZ_API_KEY
repetition_penalty: 1.2