Other providers

This page covers the remaining providers that follow the same setup pattern. Use the table of contents on the right to jump to a provider.

Shared setup flow

1. Click the Settings button in the Dline panel title bar.

2. Choose the provider under Provider.

3. Paste your API key or token into the matching credential field.

4. Select a model under Model.

See Model configuration for the full flow.

AIHubMix

An OpenAI-compatible model aggregator that gives you one API for multiple model backends.

Website: aihubmix.com

1. Sign up for or sign in to an AIHubMix account.
2. Generate an API key in the dashboard.
3. In Dline, choose AIHubMix and paste the key.

AskSage

An AI access platform for enterprise and government users, with compliance-oriented controls.

Website: asksage.ai

1. Sign in to AskSage and create API credentials.
2. Confirm that your workspace or organization has model access enabled.
3. In Dline, choose AskSage and enter the key.

Baseten

Hosted model APIs and deployment infrastructure for production inference.

Website: baseten.co

1. Create a Baseten account and open the API keys page.
2. Generate an API key with the required permissions.
3. In Dline, choose Baseten and paste the key.

Cerebras

Very fast hosted inference for supported model families.

Website: cloud.cerebras.ai

1. Sign in to Cerebras Cloud.
2. Create or retrieve an API key.
3. In Dline, choose Cerebras and enter the key.

Dify.ai

A workflow-centric AI platform with app and pipeline orchestration.

Website: dify.ai

1. Create a Dify workspace and an API credential.
2. Confirm that your Dify endpoint and provider settings are active.
3. In Dline, choose Dify.ai and paste the key.

Doubao

ByteDance’s Doubao model family, usually accessed through Volcengine. It appears as ByteDance Doubao under Provider.

Website: volcengine.com

1. Sign in to Volcengine and enable model access.
2. Generate API credentials for the Doubao endpoints.
3. In Dline, choose ByteDance Doubao and paste the credentials.

Fireworks AI

Performance-focused hosted inference for open models.

Website: fireworks.ai

1. Create a Fireworks account.
2. Generate an API key in your project or account settings.
3. In Dline, choose Fireworks AI and enter the key.

GCP Vertex AI

Google Cloud’s enterprise model platform, with IAM and project-level governance.

Website: cloud.google.com/vertex-ai

1. Prepare a GCP project with Vertex AI enabled.
2. Configure authentication (a service account or application default credentials).
3. In Dline, choose GCP Vertex AI, fill in Google Cloud Project ID, and pick a region under Google Cloud Region.

Groq

Low-latency inference for supported model families.

Website: groq.com

1. Sign in to the Groq Console.
2. Create an API key.
3. In Dline, choose Groq and paste the key.

HiCap

An OpenAI-compatible model service with multimodal support.

Website: hicap.ai

1. Create a HiCap account.
2. Generate an API key or token.
3. In Dline, choose HiCap and enter the credential.

Huawei Cloud MaaS

Model-as-a-service access within Huawei Cloud.

Website: huaweicloud.com

1. Sign in to Huawei Cloud and open the MaaS service.
2. Create API credentials for model access.
3. In Dline, choose Huawei Cloud MaaS and add the credentials.

Hugging Face

Hosted inference for open-source models.

Website: huggingface.co

1. Sign in to Hugging Face.
2. Create an access token with inference permissions.
3. In Dline, choose Hugging Face and paste the token.

LiteLLM

A proxy gateway that gives you one interface to many model providers.

Docs: docs.litellm.ai

1. Start a LiteLLM proxy and note its address and API key.
2. In Dline, choose LiteLLM, enter the proxy address under Base URL (optional) (default http://localhost:4000), and enter the key under API Key.
3. Search for, select, or type a model ID under Model.

Mistral

Direct API access to Mistral’s model lineup.

Website: mistral.ai

1. Sign up for or sign in to a Mistral platform account.
2. Generate an API key.
3. In Dline, choose Mistral and paste the key.

Nebius AI Studio

Managed hosted model APIs.

Website: studio.nebius.com

1. Sign up for or sign in to Nebius AI Studio.
2. Generate API credentials.
3. In Dline, choose Nebius AI Studio and provide the credentials.

Nous Research

Access to the Hermes model family.

Website: nousresearch.com

1. Get access credentials for the Nous-hosted endpoints.
2. Confirm which model IDs your account can use.
3. In Dline, choose Nous Research and add the credentials.

Oracle Code Assist

AI coding assistance through the Oracle Cloud Infrastructure (OCI) Generative AI service.

Website: oracle.com

1. Prepare an OCI account.
2. Enable the OCI Generative AI service in your tenancy.
3. In Dline, choose Oracle Code Assist and fill in OCA Base URL and OCA API Key.

Qwen Code

Coding-oriented access to Qwen models.

Website: chat.qwen.ai

1. Sign in to the Qwen platform.
2. Obtain API access credentials.
3. In Dline, choose Qwen Code and enter the credential.

Requesty

Multi-provider routing behind a single API.

Website: requesty.ai

1. Sign up for or sign in to Requesty.
2. Generate an API key.
3. In Dline, choose Requesty and paste the key.

SambaNova

Hosted inference and enterprise AI platform capabilities.

Website: sambanova.ai

1. Sign up for or sign in to a SambaNova account.
2. Create an API key or token.
3. In Dline, choose SambaNova and enter the credentials.

SAP AI Core

SAP’s enterprise AI platform for model integration and governance.

Website: SAP AI Core

1. Set up SAP AI Core / Generative AI Hub access.
2. Prepare your service key and endpoint credentials.
3. In Dline, choose SAP AI Core and provide the required values.

Together

Hosted inference for many popular open models.

Website: together.ai

1. Sign up for or sign in to a Together account.
2. Generate an API key.
3. In Dline, choose Together and paste the key.

Vercel AI Gateway

One API for multiple upstream model providers.

Website: vercel.com

1. Sign in to Vercel and open AI Gateway.
2. Create a Gateway API key.
3. In Dline, choose Vercel AI Gateway and add the key.

VS Code Language Model API

Lets Dline use the built-in language models available in your VS Code installation. It appears as GitHub Copilot under Provider.

Docs: VS Code Language Model API

1. Make sure language models are available in your VS Code installation.
2. In Dline, choose GitHub Copilot. No API key or other configuration is needed.

W&B Inference

Hosted inference from Weights & Biases.

Website: wandb.ai

1. Sign in to W&B and create an API key on the settings page.
2. In Dline, choose W&B Inference and paste the key into the W&B API Key field.
3. Select a model under Model.