Selection
Match models to tasks
Choose models by task, context needs, and budget.
Light · Limitless · Forward
Explore language and video models by family.
Explore modelsReceive model output as it streams.
Explore streamingExplore models for image and video tasks.
Explore video modelsConnect a model to the tools you use.
Choose a toolEasy API access.
View an API exampleRead about concurrency and request limits.
Read request limitsPlan your integration from setup through delivery.
Explore integrationCompare context windows in the model directory.
View specifications01 Services
End-to-end integration support
Integration
Configure tools & systems
Connect existing coding tools or integrate your systems through APIs.
Handover
Test & deliver
Test with real business samples and receive configuration files and operating instructions.
02 Applications
Common use cases
Documents & office work
Typical tasks
- Summarize meeting notes
- Draft emails and replies
- Extract key points
Document workflowWorkflow overview
Coding & troubleshooting
Typical tasks
- Read and explain code
- Add unit tests and technical documentation
- Draft changes and run checks
Code repair workflowWorkflow overview
Knowledge retrieval & analysis
Typical tasks
- Search internal policies and manuals
- Compare information across documents
- Summarize research findings
Knowledge workflowWorkflow overview
Video generation & storyboarding
Typical tasks
- Generate product demo clips
- Edit visuals using references
- Create storyboard drafts
Video generation workflowWorkflow overview
Prepare a case for a support agent
Typical tasks
- Categorise incoming tickets
- Extract steps to reproduce a fault
- Draft a reply using the returns policy
Customer supportWorkflow overview
Turn unstructured records into importable data
Typical tasks
- Extract quantities from purchase orders
- Normalise field names and dates
- Flag duplicates and missing values
Data preparationWorkflow overview
Keep terminology consistent across languages
Typical tasks
- Translate a manual against a glossary
- Preserve UI placeholders and variables
- Flag ambiguous terms for the translator
LocalisationWorkflow overview
Build practice materials from lesson notes
Typical tasks
- Generate revision cards by chapter
- Draft exercises at several levels
- Prepare presenter notes for training
LearningWorkflow overview
03 Models
Supported model families
Language & multimodal models
DeepSeekReasoning and codeFeatured modelDeepSeek-v4.1-Flash GLMSoftware developmentFeatured modelGLM-5.3 QwenDocuments and visionFeatured modelQwen3.8-Max KimiLong documents and researchFeatured modelKimi K3.1 ProVideo generation models
SeedanceReference-guided videoModelSeedance 2.5 WanText and image to videoModelWan 3.0 MiniMaxFirst and last frame controlModelMiniMax H304 Tool setup
Connect your development tools
Choose a tool for configuration examples. Confirm your provisioned endpoint, API key, and supported protocol first.
Third-party tool configuration reference.
BAC
WORLDNITE
AFrom model makersBOpen-source agentsCAgent platforms
DeepSeek Harness
DeepSeek
- Where it runs
- Web UI, desktop app
- Models it uses
- DeepSeek models built in. Other models and tools are added as plugins
- How to connect
- Configure a compatible endpoint, key, and model for your tool version. Confirm protocol and permissions before using plugins.
# Developer preview: starts the web UI
npx @deepseek-ai/dsh web
# Then open http://127.0.0.1:3080
Codex
OpenAI
- Where it runs
- Terminal, IDE, app
- Models it uses
- OpenAI models, or other providers you add in config.toml
- How to connect
- Add WORLDNITE as a provider in config.toml using your assigned API endpoint and key.
model = "<model-id>"
model_provider = "worldnite"
[model_providers.worldnite]
name = "WORLDNITE"
base_url = "https://api.example.com/v1"
env_key = "WORLDNITE_API_KEY"
wire_api = "responses"
Grok Build
xAI
- Where it runs
- Terminal
- Models it uses
- xAI's Grok models. Sign in with xAI or use XAI_API_KEY
- How to connect
- Before connecting WORLDNITE, confirm that your tool version supports a custom endpoint and the required protocol. xAI sign-in and WORLDNITE keys are separate credentials.
# Windows PowerShell: irm https://x.ai/cli/install.ps1 | iex
cd your-project
grok
Claude Code
Anthropic
- Where it runs
- Terminal, IDE, desktop, web
- Models it uses
- Anthropic models, or any service that uses the Anthropic API format
- How to connect
- Set ANTHROPIC_BASE_URL to your provisioned Anthropic-compatible endpoint.
{
"env": {
"ANTHROPIC_BASE_URL": "https://api.example.com",
"ANTHROPIC_AUTH_TOKEN": "<WORLDNITE_API_KEY>",
"ANTHROPIC_MODEL": "<model-id>"
}
}
Kimi Code
Moonshot AI
- Where it runs
- Terminal, desktop, IDE
- Models it uses
- Kimi models. Sign in to Kimi Code or use a Moonshot AI Open Platform API key
- How to connect
- For WORLDNITE access, confirm that your tool version supports the endpoint and protocol required by the selected model.
kimi
/login
# Choose Kimi Code sign-in or an Open Platform API key
Gemini CLI
- Where it runs
- Terminal
- Models it uses
- Google Gemini models. Sign in with Google, a Gemini API key, or Vertex AI
- How to connect
- For WORLDNITE access, configure a compatible Gemini endpoint, key, and model. Google account sign-in is a separate access method.
export GEMINI_API_KEY="<WORLDNITE_API_KEY>"
export GOOGLE_GEMINI_BASE_URL="https://api.example.com"
export GEMINI_MODEL="<model-id>"
gemini
OpenCode
Open source
- Where it runs
- Terminal, desktop, IDE
- Models it uses
- Many providers, including any OpenAI-style service
- How to connect
- Add WORLDNITE as an OpenAI-style provider in opencode.jsonc. Keep the key in an environment variable.
{
"providers": {
"worldnite": {
"name": "WORLDNITE",
"env": ["WORLDNITE_API_KEY"],
"package": "@opencode/ai/providers/openai-compatible",
"settings": { "baseURL": "https://api.example.com/v1" },
"models": { "<model-id>": { "name": "<model name>" } }
}
}
}
pi
Open source
- Where it runs
- Terminal
- Models it uses
- Many providers and models. Switch with /model
- How to connect
- Select your configured WORLDNITE provider and a provisioned model ID in pi.
pi
/login # sign in to a provider
/model # pick an available model
Hermes Agent
Nous Research
- Where it runs
- Terminal
- Models it uses
- Many providers, including your own OpenAI-style service
- How to connect
- Run hermes model, choose Custom endpoint, and enter your API address, key, and model.
hermes model
# Choose "Custom endpoint", then enter:
# API base URL https://api.example.com/v1
# API key <WORLDNITE_API_KEY>
# Model name <model-id>
OpenClaw
Open source
- Where it runs
- Your machine, as a background service
- Models it uses
- Many providers, including your own
- How to connect
- Choose Custom provider during setup and enter your assigned endpoint and model ID.
openclaw onboard --install-daemon
# Choose "Custom provider", then enter
# https://api.example.com/v1 and <model-id>
AstrBot
Open source
- Where it runs
- Messaging apps, web dashboard
- Models it uses
- Many providers, added in the web dashboard
- How to connect
- In the AstrBot dashboard, add a provider with your assigned API endpoint, key, and model ID.
astrbot
# Open the web dashboard and add a model provider
# with the values from your console
