SambaCloud Dashboard

Start building AI powered applications in minutes with our OpenAI compatible API.

1curl -H "Authorization: Bearer $API_KEY" \
2     -H "Content-Type: application/json" \
3     -d '{
4	"stream": true,
5	"model": "ALLaM-7B-Instruct-preview",
6	"messages": [
7		{
8			"role": "system",
9			"content": "You are a helpful assistant"
10		},
11		{
12			"role": "user",
13			"content": "Hello"
14		}
15	]
16	}' \
17     -X POST https://api.sambanova.ai/v1/chat/completions

1from sambanova import SambaNova
2
3client = SambaNova(
4    api_key="<YOUR API KEY>",
5    base_url="https://api.sambanova.ai/v1",
6)
7
8response = client.chat.completions.create(
9    model="ALLaM-7B-Instruct-preview",
10    messages=[{"role":"system","content":"You are a helpful assistant"},{"role":"user","content":"Hello"}],
11    temperature=0.1,
12    top_p=0.1
13)
14
15print(response.choices[0].message.content)

1import gradio as gr
2    import sambanova_gradio
3    gr.load("ALLaM-7B-Instruct-preview", src=sambanova_gradio.registry, accept_token=True).launch()
4    

Experience the best open-source models powered by SambaNova RDUs. Learn more about each of them in our documentation.

Humain Models

ALLaM-7B-Instruct-preview

Text

DeepSeek Models

DeepSeek-R1-0528

TextReasoning

DeepSeek-R1-Distill-Llama-70B

TextReasoning

DeepSeek-V3-0324

Text

DeepSeek-V3.1

TextReasoning

DeepSeek-V3.1-Terminus

TextReasoning

Mistral Models

E5-Mistral-7B-Instruct

Embeddings

Meta Models

Llama-3.3-Swallow-70B-Instruct-v0.4

Text

Llama-4-Maverick-17B-128E-Instruct

TextVision

Meta-Llama-3.1-8B-Instruct

Text

Meta-Llama-3.3-70B-Instruct

Text

Qwen Models

Qwen3-235B

Text

Qwen3-32B

TextReasoning

OpenAI Models

Whisper-Large-v3

Audio

gpt-oss-120b

TextReasoning

* Preview models in SambaNova Cloud are available as early-access offerings intended primarily for evaluation purposes. During the preview phase, these models have limited capacity and being optimized for production. Please provide feedback in the SambaNova Community to help our teams optimize these models for your production applications.