# Model providers - Obss

Set up
Model providers
Connect the API keys, gateways, and personal subscriptions that give agents and Obss AI features their models.
You bring your own models. The providers you connect give models to the agents that do your tasks and to the Obss AI features: the Evals model, Insights model, Experiment insights model, and Ask Obss model. Connecting a provider is step 2 of the
setup checklist
.
How providers work
Shared with organization
: an API key or gateway added under
Organization settings → Model providers
. Every member uses it.
Private to you
: a personal subscription connected under
Profile → Integrations
. Only your runs use it.
Every project lists the same providers. Each connection lists only the models its provider reports, and you can’t add other model IDs. An agent also lists only models that serve a model API it supports (OpenAI Responses, OpenAI Chat Completions, or Anthropic Messages), so one gateway can show a model to one agent and not to another (
Which providers each agent uses
).
Obss runs
pay for the platform. Your providers bill model use separately, and Obss doesn’t track that spend.
Connect a provider
Open
Organization settings → Model providers
.
Find the provider and select
Connect
on its row. For your own gateway or a self-hosted API, select
Add any OpenAI-compatible provider
, or open the menu beside it and select
Add any Anthropic-compatible provider
.
Enter its API key, and a base URL if the provider needs one.
Select
Save changes
. Obss reads the provider’s model list right away.
Turn on the agents that use it under
Manage → Agents
.
For a personal subscription, select
Connect
on its row under
Profile → Integrations
.
Provider list
The list shows each provider’s access tag and connection state. A connected
Shared with organization
row shows
API key
, and a connected
Private to you
row shows your account, such as your email and plan.
Rows that need attention come first, then connected rows.
Filters
narrows the list:
Status
:
Connected
,
Needs attention
(the connection is saved but needs a fix, such as
Sign in again
), or
Not connected
.
Access
:
Shared with organization
or
Private to you
.
Organization providers
Add these under
Organization settings → Model providers
.
Provider
What you enter
Notes
OpenAI
API key
OpenAI models for Codex, other agents, and Obss AI features
Anthropic
API key
Claude models for Claude Code, other agents, and Obss AI features
Cursor
API key
Runs the Cursor agent only. Needs a paid plan key (Pro, Pro+, Ultra, Teams, or Enterprise); a free Hobby key doesn’t work.
xAI
API key
Grok models. Grok Build can search the web only through an xAI API key.
Google Gemini API
API key
Gemini models. The only provider for Antigravity.
Alibaba Cloud Model Studio
API key and regional base URL
Use a pay-as-you-go key. Alibaba prohibits automated use of Coding Plan and Token Plan keys.
DeepSeek API
API key
Kimi API
API key
Use a global key from
platform.kimi.ai
. Kimi Membership, Kimi Code, and mainland China keys don’t work.
Meta Model API
API key
MiniMax API
API key and base URL
Use the international or mainland China base URL that matches the key. Use pay-as-you-go: Token Plan can throttle automated traffic.
OpenRouter
API key
Many models through one key. Claude Code uses only its
anthropic/claude…
models.
Vercel AI Gateway
API key
Many models through one key
Cloudflare AI Gateway
API token and account AI API root
The token needs
Account → Workers AI → Read
. Accepts Cloudflare’s
cf-aig-*
request headers. Cloudflare logs prompts and responses by default.
GMI Cloud
API key
Many models through one key. Accepts the optional
X-Organization-ID
header.
OpenCode Zen
OpenCode API key
OpenCode’s pay-as-you-go gateway
OpenCode Go
OpenCode API key
OpenCode’s subscription gateway
Any OpenAI-compatible provider
Base URL and API key
Your own gateway or a self-hosted OpenAI-compatible API. You can add more than one.
Any Anthropic-compatible provider
Base URL and API key
Your own gateway or an Anthropic-compatible API. You can add more than one.
Personal integrations
Each member connects their own under
Profile → Integrations
, and Obss uses the account of the person who starts the work.
Profile and API keys
lists the plan each needs.
Integration
Powers
GitHub
GitHub Copilot
OpenAI (ChatGPT Subscription)
Codex, and Obss AI features
Anthropic (Claude Subscription)
Claude Code, Evals, and Insights
Nous Portal
Hermes, and Obss AI features
Turn off or refresh models
Open a provider to see its model table. Turn a model off to hide it from agents and Obss AI features.
Obss reads the model list when you connect or save a provider, and again once it’s a day old. To read it now, select
Refresh models
on the provider or
Refresh all models
on the list. A model the provider stops listing drops off until the provider lists it again.
A refresh has two parts. First, Obss reads the provider’s list, and the models show in the table in a few seconds. Then it checks which of those models your key can use, which can take longer for a long list. During the checks, the provider shows
Refreshing models
and the table is dimmed. A new model shows in the table but can’t be selected until its check finishes. A model you could already select stays selectable.
If the checks fail, the table keeps the list that the refresh read, and the provider shows what to fix.
When a refresh adds or removes models, or a list stops refreshing, the other people who use it get an in-app
notice
.
Set the context window for a model
A model’s context window is how many tokens it can read at once. Obss uses it to size what Evals and Insights read and to set up agents such as Pi and OpenClaw. Custom gateways, such as a self-hosted proxy, often don’t state it. Without a window, Evals and Insights read up to 128K tokens, and Ask Obss can’t use the model.
Open the provider under
Organization settings → Model providers
.
In the model table, select the pencil button in the
Context
column.
Enter the window in tokens and select
Save
.
Clear
removes your value.
A window you set shows
Set by your organization
, and applies only while the provider states none. You can set windows only on organization providers, and personal integrations always use their provider’s windows.
Suggested windows from public catalogs
When OpenRouter or Models.dev lists exactly one window for the same model ID, the table shows
Suggested
under
Not available
. The editor fills it in and names the catalog. Check it against your endpoint, which can allow less, then select
Save
. Obss never uses a suggestion until you save it.
From the CLI or the plugin, send
set_model_context_windows
to
obss project ai apply
or
manage_project_ai
. A
null
value clears a window:
obss
project
ai
apply
--operation
'{"action":"set_model_context_windows","connectionId":"aic_51be0c9a3f2d4e6b8a7c1d20","models":[{"modelId":"aim_3a91c7e2b4d6f8a0c2e4f6a8","contextWindowTokens":500000}]}'
obss project ai inspect --view models
shows each model’s
contextWindowTokens
,
contextWindowSource
, and any
suggestedContextWindow
.
Fix a provider that needs attention
A row shows
Needs attention
when its connection is saved but can’t run models, for example after a personal sign-in expires. Open the row and follow its fix, such as
Sign in again
. Until a provider works, every dashboard page shows a
banner with the fix
.
From the CLI and the plugin
The CLI and the plugin read providers and models, refresh lists, turn models on or off, and set context windows. You enter keys and sign in only in the dashboard, so for those steps the CLI and the plugin return a dashboard link.
Task
CLI
Plugin (MCP)
List providers, with
access
and
connectionState
obss project ai inspect --view providers
inspect_project_ai
List a provider’s models
obss project ai inspect --view models
inspect_project_ai
Refresh model lists
obss project ai apply
with
refresh_models
manage_project_ai
Turn models on or off
obss project ai apply
with
set_model_enabled
or
set_models_enabled
manage_project_ai
Set context windows
obss project ai apply
with
set_model_context_windows
manage_project_ai
Delete or reset an organization provider, or disconnect your account
obss project ai delete
delete_project_ai
Get the dashboard link to enter a key or sign in
obss setup links
get_setup_links
For example, list the providers that need attention:
obss
project
ai
inspect
--view
providers
--connection-state
needs_attention
Next steps
Agents
Step 3: turn on the agents you want to evaluate.
Obss AI features
Step 5: choose models for Evals, Insights, and Ask Obss.
Profile and API keys
Step 7: connect your personal subscriptions.
obss project ai and setup
Look up every provider and model command.
Projects
Agents
Powered by
This documentation is built and hosted on Mintlify, a developer documentation platform