Get a specific model with provider info and profile
const url = 'https://app.everruns.com/api/v1/models/example';const options = {method: 'GET'};
try { const response = await fetch(url, options); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}curl --request GET \ --url https://app.everruns.com/api/v1/models/exampleParameters
Section titled “ Parameters ”Path Parameters
Section titled “Path Parameters ”Model ID (prefixed, e.g., mod_…)
Responses
Section titled “ Responses ”Model found
Wrapper that adds API and UI links to a serialized resource.
Uses self_url (not url) for the API link to avoid collision with
resources that already have a url field (e.g. McpServer). The
allowed_actions array carries state-aware hypermedia links — empty
(and omitted from the wire shape) until the underlying resource opts
into the convention by overriding ResourceUrlable::allowed_actions.
object
Capability tags supported by this model.
Timestamp when this model was created (RFC 3339).
Human-readable display name.
Whether this model is selectable. Controls UI visibility AND server-side resolution: ProviderResolverService requires enabled = true, and org default-model validation rejects disabled models.
Derived: model is configured and ready for use. Currently means the joined provider is active and has an API key set; over time this may also incorporate live reachability checks. Not persisted.
Prefixed public identifier. See ID Schema.
Whether this model is starred in the UI for quick access.
Provider-side model identifier as sent on the wire (e.g. gpt-4o).
Readonly profile with model capabilities (limits, pricing, modalities). Not persisted.
object
Whether the model supports file/image attachments
Cost per million tokens
object
Cached read cost per million tokens (USD), if supported
Tiered pricing that applies above certain context thresholds. When present, the base cost fields apply up to the tier threshold, and each tier’s costs apply for tokens beyond that threshold.
A pricing tier that activates above a context token threshold. For example, OpenAI charges higher rates for prompts exceeding 200K tokens.
object
Context token threshold above which this tier applies
Cached read cost per million tokens (USD) for this tier, if supported
Input cost per million tokens (USD) for this tier
Output cost per million tokens (USD) for this tier
Input cost per million tokens (USD)
Output cost per million tokens (USD)
Short human-readable description of the model’s strengths and intended use
Model family (e.g., “gpt-4o”, “claude-3-5-sonnet”)
Knowledge cutoff date (YYYY-MM-DD format)
Last updated date (YYYY-MM-DD format)
Token limits
object
Maximum context window size in tokens
Maximum input tokens (if different from context - output)
Maximum images or PDF pages per request
Maximum output tokens
Display name of the model
Whether the model has open weights
Whether the model has reasoning/chain-of-thought capabilities
Reasoning effort configuration (for reasoning models)
object
Default reasoning effort for this model
Available reasoning effort values for this model
Named reasoning effort value for UI display
object
Display name (e.g., “Low”, “Medium”)
The API value (e.g., “low”, “medium”)
Release date (YYYY-MM-DD format)
Whether the model supports structured output (JSON mode)
Provider-advertised request parameters supported by this model.
Whether the model supports native execution phases (“commentary” / “final_answer”).
When true, the driver sends the phase field on assistant messages in the wire format.
Currently supported by GPT-5.4 and newer via OpenAI Responses API.
Whether temperature control is supported
Whether the model supports tool/function calling
Whether the model supports tool_search (deferred tool loading). When true, the driver can use namespaces and defer_loading to reduce token usage for large tool sets. Currently supported by GPT-5.4 and newer.
Owning provider’s prefixed public identifier.
Joined provider display name.
Joined provider implementation type.
How this model entry was added (manually, discovered, or seeded as predefined).
Timestamp when this model was last updated (RFC 3339).
State-aware hypermedia actions the caller can take on this resource
next (e.g. cancel, events, update). Omitted from the wire
shape when empty so resources that haven’t opted into the
convention don’t grow their payloads.
Agent-actionable link describing a follow-up the caller can take. Used in two contexts:
- Error recovery —
ErrorResponse.allowed_actionscarriesrels likeretry,retry-later,unarchive,get-existingso the agent knows the right next call after a 4xx/429. - Entity hypermedia —
WithUrls<T>.allowed_actionscarries state-awarerels likecancel,events,self,updateon the entity itself so the agent can follow links instead of reconstructing routes from prose.
The shape is intentionally identical across both contexts; the closed
rel vocabulary documented in specs/api-conventions.md distinguishes
them.
object
Short, agent-readable hint (e.g. “Shorten ‘name’ to <= 200 chars.”, “Cancel the active turn for this session.”).
Absolute (preferred) or relative URL the caller may invoke
directly. Always present on entity hypermedia actions
(WithUrls<T>.allowed_actions); optional on error-recovery
actions (ErrorResponse.allowed_actions) where the matching
operation_id is enough and the URI is implicit from the failed
call.
HTTP method to use against href. Required for entity hypermedia
actions; usually omitted on error-recovery actions where the same
operation is retried with its original method.
OpenAPI operationId the caller should invoke. Lets an MCP client
resolve the call without parsing href.
Link relation describing the action. Closed vocabulary documented
in specs/api-conventions.md — examples: self, cancel, pause,
resume, events, retry, retry-later, unarchive,
get-existing, delete, update.
OpenAPI $ref to the request-body schema, when the action takes one
(e.g. #/components/schemas/UpdateSessionRequest). Lets a tool-calling
agent fetch the input shape without scanning the whole spec.
Full API endpoint URL for this resource.
Alias for view_url, used by command and MCP outputs.
Full UI URL for viewing this resource.
Example
{ "capabilities": [ "text", "tools", "vision", "thinking" ], "created_at": "2026-01-04T11:23:00Z", "display_name": "Claude Sonnet 4.5", "enabled": true, "healthy": true, "id": "model_01933b5a00007000800000000000001", "is_favorite": true, "model_id": "claude-sonnet-4-5", "model_vendor": "openai", "profile": { "modalities": { "input": [ "text" ], "output": [ "text" ] }, "reasoning_effort": { "default": "none", "values": [ { "value": "none" } ] } }, "provider_id": "provider_01933b5a00007000800000000000001", "provider_name": "Anthropic", "source": "manual", "updated_at": "2026-05-27T15:24:00Z", "allowed_actions": [ { "method": "POST" } ]}Invalid model ID
Model not found