Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.brightnode.cloud/llms.txt

Use this file to discover all available pages before exploring further.

The Models catalog shows what you can call through Brightnode Router. Each model entry includes the model ID, modality, context length, pricing, and provider or hosting details you need before sending traffic.

​
Find model IDs

Use the Models page in the console, or query the API directly: 
curl https://api.brightnode.cloud/v1/models \
  -H "Authorization: Bearer $BRIGHTNODE_API_KEY"
Model IDs are passed directly in the model field of your request. They may include slashes, for example:
  • meta-llama/Llama-3.3-70B-Instruct
  • mistralai/Devstral-Small-2507
  • Qwen/Qwen3-Embedding-8B

​
Inspect a single model

Use the model detail endpoint when you want richer metadata for one model: 
curl https://api.brightnode.cloud/v1/models/meta-llama/Llama-3.3-70B-Instruct \
  -H "Authorization: Bearer $BRIGHTNODE_API_KEY"
The detail response includes fields such as:
  • modality for the workload type, such as text or embedding.
  • context_length for the maximum supported context window.
  • pricing_input and pricing_output for token-based pricing.
  • providers for the backing provider or hosting source.
  • license_class, self_hostable, and residency metadata where available.

​
Choose the right model

When comparing models, start with these questions:
  • Do you need chat generation, embeddings, or another modality?
  • What context length does your workload require?
  • Do latency or provider availability matter for this use case?
  • Do compliance or residency constraints limit your options?
The console model detail pages surface this metadata directly and include copy-paste quickstarts for curl, Python, and TypeScript.

​
Use a model with Router

from openai import OpenAI
import os

client = OpenAI(
    base_url="https://api.brightnode.cloud/v1",
    api_key=os.environ["BRIGHTNODE_API_KEY"],
)

response = client.chat.completions.create(
    model="meta-llama/Llama-3.3-70B-Instruct",
    messages=[{"role": "user", "content": "Summarize the latest deployment notes."}],
)

print(response.choices[0].message.content)
For the full request flow, see Router.