Roster for OpenRouter

Route Roster through a unified model gateway.

Use OpenRouter — or another validated OpenAI-compatible gateway — to centralize model access, routing, budgets, provider selection, and policy controls for Roster's resolver.

Roster treats OpenRouter as a gateway configuration, not as a separate direct model-provider family.

Configure OpenRouterReview validated gateway models

Last verified 07/13/2026

Centralize model access without changing Roster's participant model

Roster continues to govern:

Who should review this contract exception for the Atlas project in Europe?

OpenRouter sits between Roster and the selected underlying model provider. This adds flexibility, but also introduces another layer of API behavior, routing, privacy policy, limits, and failure handling that must be validated.

  • Projects
  • Participants
  • Directory context
  • Memberships
  • Metadata
  • Delegations
  • Access boundaries
  • Resolution history

Roster remains the participant-resolution and governance layer regardless of which model or provider the gateway routes to.

How the integration works

Roster reaches OpenRouter through an OpenAI-compatible interface, which routes to the selected underlying model.

Agent, workflow, or application
   ↓
Roster Resolve
   ↓
Authorized participant context
   ↓
OpenRouter
   ↓
Selected OpenAI, Anthropic, Mistral,
or other gateway-hosted model
   ↓
Structured participant selection
   ↓
Roster validation and expansion

Why use a model gateway?

Centralized model access
Use one gateway credential and endpoint to reach multiple approved model families.
Model and provider controls
Gateways can centralize which models or underlying inference providers are available to a deployment.
Budgeting and usage management
Organizations may use gateway-level budgets, spend controls, usage reporting, or key policies.
Routing and availability
A gateway may route across multiple endpoints or providers for the selected model.
Faster model evaluation
Teams can test multiple provider/model combinations without rebuilding Roster's integration layer.
Validation still required
These benefits do not remove the requirement to test each exact gateway, model, API, and policy combination.

Configure OpenRouter

Keep ROSTER_MODEL_PROVIDER=openai because Roster reaches OpenRouter through an OpenAI-compatible interface.

For a supported OpenAI model through the Responses API:

OPENAI_API_KEY=<openrouter-api-key>
OPENAI_BASE_URL=https://openrouter.ai/api/v1
ROSTER_MODEL_PROVIDER=openai
ROSTER_MODEL_NAME=openai/gpt-5.4-mini
ROSTER_MODEL_EFFORT=low

When ROSTER_MODEL_API is omitted for the openai provider family, Roster defaults to responses.

For many non-OpenAI models, Chat Completions is the more appropriate starting point because gateway support for the Responses API varies by model:

OPENAI_API_KEY=<openrouter-api-key>
OPENAI_BASE_URL=https://openrouter.ai/api/v1
ROSTER_MODEL_PROVIDER=openai
ROSTER_MODEL_API=chat-completions
ROSTER_MODEL_NAME=anthropic/claude-opus-4.8

The use of ROSTER_MODEL_PROVIDER=openai describes the compatible API family used by Roster. It does not mean that the underlying model is necessarily operated by OpenAI.

Responses API output limit — when OPENAI_BASE_URL is configured, Roster defaults the OpenAI Responses output cap to:

ROSTER_MODEL_OPENAI_RESPONSES_MAX_OUTPUT_TOKENS=2048

Override this only when required by the selected gateway, model, or account limits. Test the complete Resolve response rather than checking only for HTTP success.

Currently validated OpenRouter model/API combinations:

openai/gpt-5.5                    Responses           low
openai/gpt-5.4                    Responses           low
openai/gpt-5.4-mini               Responses           low
anthropic/claude-opus-4.8         Chat Completions    n/a
mistralai/mistral-large-2512      Chat Completions    n/a

Treat these as validated candidates, not a permanent guarantee. Model slugs, availability, routing providers, APIs, and underlying behavior can change. Revalidate before publishing a production recommendation.

Example gateway resolution

A legal-operations workflow asks:

Who should review this contract exception for the Atlas project in Europe?
  1. Roster builds the authorized participant context.
  2. Roster calls the configured OpenRouter endpoint.
  3. OpenRouter routes the request to the selected model/provider combination.
  4. The model returns a structured participant selection.
  5. Roster validates the selection and resolves current users or delegates.
  6. Roster records its model run and Resolve request.

Gateway activity and Roster activity may have separate request IDs and observability systems. Preserve both when investigating a production issue.

Compatibility has several layers

A gateway model can pass a simple API test and still fail as a Roster resolver. Validate endpoint compatibility, API compatibility (Responses vs Chat Completions), structured-output compatibility, reasoning-control compatibility (does the gateway pass, translate, ignore, or reject Roster's effort setting), output-limit compatibility, Resolve quality on representative organizational data, and operational compatibility (latency, limits, availability, cost, errors).

Provider routing matters. OpenRouter may have multiple inference providers available for a model and can route between them according to its configuration and availability logic. Two requests using the same model slug may involve different underlying providers unless routing is constrained. Evaluate whether you need a preferred provider, allowlists or exclusions, fallback routing, regional routing, Zero Data Retention-only endpoints, fixed model versions, model-access guardrails, or key-specific spending limits.

Data handling requires two reviews — the gateway and the underlying inference provider. Review gateway metadata logging, optional prompt and completion logging, provider retention, provider training policies, ZDR routing, regional processing, fallback-provider policies, and error logging. OpenRouter documents account and request controls for restricting routing to providers that meet specified retention or training policies. Configure and verify those policies independently from Roster.

Production checklist

Select the exact model slug
Pin the gateway's model identifier and choose Responses or Chat Completions deliberately.
Confirm structured-output compatibility
Validate schema-conformant responses across representative queries.
Validate effort and output-token limits
Confirm the gateway's handling of ROSTER_MODEL_EFFORT and Responses output caps.
Run the full Resolve evaluation suite
Include ambiguous, delegated, and no-match cases before promoting to production.
Review underlying provider routing
Restrict routing when provider consistency, data policy, or region is important.
Configure privacy and retention policies
Set gateway account and request controls for ZDR and training-policy requirements.
Set budgets and access restrictions
Use gateway-level spend controls, key policies, and model allowlists.
Compare gateway and Roster usage
Reconcile gateway-reported and Roster-reported cost and latency; canary before broad rollout.

Frequently asked questions

Roster treats it as an OpenAI-compatible gateway. Set ROSTER_MODEL_PROVIDER=openai and configure the OpenRouter base URL.

Centralize model access without weakening resolution governance

Use OpenRouter or an approved compatible gateway for model access and routing while Roster remains the system for participant context, authorization, delegation, validation, and observability.

Configure OpenRouterReview validated gateway modelsExplore all integrations