$worker
provider-openrouter
v0.1.5OpenRouter Chat Completions provider worker; one API key in front of every major vendor. Implements provider::openrouter::stream and provider::openrouter::refresh_models behind llm-router.
iiiverifiedinstall
$iii trigger compose::add worker=provider-openrouter@0.1.5
- macOS: arm64
- Linux: arm64 · armv7 · x64
- Windows: arm64 · x64
repoiii-hq/workers
exact versions are immutable; binary and bundle artifacts are digest-pinned.
agent-ready brief for v0.1.5
install + config + dependencies + readme + api reference, all in one place. fetch as agent-context.md for an llm to consume.
full markdown
the same content rendered as discrete blocks below is exposed as a single markdown document at
/workers/provider-openrouter.md?version=0.1.5. paste it into an llm prompt or pipe it through curl from a worker.install
install
$iii trigger compose::add worker=provider-openrouter@0.1.5
dependencies
readme
README.md
provider-openrouter
OpenRouter Chat Completions provider worker behind
llm-router: one API key in front of every major
vendor's models. OpenRouter's API is OpenAI Chat Completions-compatible, so
this worker forks the shared provider scaffolding; what makes it different
from the single-vendor providers is the catalog — OpenRouter's
GET /api/v1/models listing is self-describing (context windows, output
ceilings, per-token pricing, modalities, supported parameters, reasoning
efforts), so live discovery owns the entire record and there is no local
metadata table to maintain when upstream ships new models.
Implements the provider protocol from
tech-specs/2026-06-agentic/llm-router.md: provider::openrouter::stream
(SSE chunks → AssistantMessageEvent frames into a router-owned channel) and
provider::openrouter::refresh_models (live GET /api/v1/models, admitted
rows mapped to full catalog records → router::models::reconcile).
Behavior
- Catalog ids are prefixed: OpenRouter's own model ids are
vendor/model(anthropic/claude-sonnet-4.5), which unprefixed would read as belonging to the sibling single-vendor providers. Catalog ids are thereforeopenrouter/vendor/model; the prefix is stripped on every upstream call. - Admission: a model must support function
tools, emittext, and be reachable over Chat Completions to be reconciled. The agent loop is unusable without tool calling; image or audio generators and batch-endpoint-only:batchvariants (chat calls to them 404) would be dead rows in the picker. Everything else in the listing (several hundred models) lands in the catalog with live metadata. - Registration: self-declares via
router::provider::registerwith backoff until acked, and re-declares on therouter::readytrigger type. The declaration carries no staticmodelsslice — the live listing is the source of truth and a refresh fires right after registration. Defaults:api_url: https://openrouter.ai/api/v1/chat/completions,credential_env_var: OPENROUTER_API_KEY. - Identity binding: the router returns a
registration_tokenon first registration; it is persisted in iii-state (scopeprovider-openrouter, keyregistration_token) and presented on every laterregister/resolve/reconcile. If that state is lost the router rejects re-registration — the operator must clear the binding on the router side. - Credentials: resolved per request via
router::provider::resolve(config slice →OPENROUTER_API_KEYenv on the router → none). Bothapi_keyandoauthcredential shapes are sent asAuthorization: Bearer; v1 performs no OAuth refresh. - Reasoning:
thinking_levelmaps to OpenRouter's unifiedreasoning: {effort}parameter, resolved against the model's advertisedsupported_effortsfrom the listing. Ladders step down, never up (a request can only get less reasoning than asked); a model that does not support the parameter gets noreasoningfield and the caller is told via a report-and-continue warning. Reasoning deltas stream back as thinking blocks — OpenRouter's normalizedreasoningfield, with the olderreasoning_contenthonored for compatible gateways pointed at viaapi_url. - Structured output: strict
json_schemamode on models whose listing declaresstructured_outputs; a schema requested for any other model degrades tojson_objectwith a warning. - Usage accounting: requests carry
usage: {include: true}, so the final usage chunk reports native token counts, cache reads/writes, reasoning tokens, and the actual billed cost (cache discounts included). The billed cost lands onusage.cost_usdverbatim — the router's catalog-pricing fill keeps a provider-supplied value. - Token counting: none. OpenRouter exposes no pre-request tokenizer
endpoint, and one local tokenizer cannot honestly meter models spanning
every vendor's vocabulary —
router::count_tokensreportsno_token_counterfor this provider and the harness falls back to its own estimate. - Liveness:
pingat least every 30s of upstream silence; a failed channel write (caller gone /router::abort) drops the SSE receiver and aborts the in-flight HTTP request. - Errors: OpenRouter's gateway-level status semantics map to the shared
taxonomy: 401 →
auth_expired; 402 (insufficient credits) and 403 (moderation flagged the input) →permanent; 408 →transient; 429 →rate_limited; 502/503 (upstream down / no provider available) and network failures →transient; context-length errors →context_overflow. The numericerror.codeenvelope wins over the transport status; OpenAI-style string codes from compatibility proxies are honored too. No transport retries here — the router owns retry policy. - Attribution: requests carry OpenRouter's optional app-attribution
headers (
HTTP-Referer: https://iii.dev,X-OpenRouter-Title: iii), identifying the harness stack, never the end user.
Tests
cargo test # unit (pure modules + TCP stubs)
III_ENGINE_BIN=$(which iii) cargo test --test integration -- --test-threads=1The integration suite spawns a real engine, the real router (path dep), this provider, and a local stub upstream — no external API calls anywhere.
Running
The binary takes the standard worker CLI flags: --url (engine WebSocket,
default ws://127.0.0.1:49134, falls back to the III_WS_URL environment
variable), --manifest (print the registry manifest and exit), and
--config (accepted but ignored with a warning — provider config comes
from the llm-router configuration entry).
api reference (json)
agent-api-reference.json
{
"functions": [
{
"description": "Cancel the in-flight upstream stream for a request_id (router::abort fan-out), stopping billed generation immediately.",
"metadata": {
"internal": true
},
"name": "provider::openrouter::abort",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"description": "Input of a provider's `provider::<id>::abort`: actively cancel the in-flight upstream stream for `request_id` (the router's `request_id`, delivered to the provider as `resolution_key`) so billed generation stops immediately instead of waiting for the provider to notice the closed channel on its next write.",
"properties": {
"request_id": {
"type": "string"
}
},
"required": [
"request_id"
],
"title": "ProviderAbortRequest",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"description": "Output of `provider::<id>::abort`. `aborted: false` means the request was unknown — already finished, never started, or aborted before (idempotent).",
"properties": {
"aborted": {
"type": "boolean"
}
},
"required": [
"aborted"
],
"title": "ProviderAbortResponse",
"type": "object"
}
},
{
"description": "Internal: router::ready subscriber that re-declares this provider and refreshes its catalog.",
"metadata": {
"internal": true
},
"name": "provider::openrouter::on_router_ready",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"description": "Event delivered to a provider's `provider::<id>::on_router_ready` (the `router::ready` trigger payload, currently `{}`). Unknown fields are ignored.",
"title": "RouterReadyEvent",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"description": "Ack returned by a provider's `provider::<id>::on_router_ready`.",
"properties": {
"ok": {
"type": "boolean"
}
},
"required": [
"ok"
],
"title": "ProviderReadyAck",
"type": "object"
}
},
{
"description": "Refresh the OpenRouter catalog slice from GET /api/v1/models — ids, context windows, pricing, and capabilities all come from the live listing — and reconcile it through the router; returns the model count written.",
"metadata": {},
"name": "provider::openrouter::refresh_models",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"description": "Input of a provider's `provider::<id>::refresh_models` — takes no arguments. A struct (not `Value`) keeps the request schema concrete; unknown fields (e.g. the engine-injected `_caller_worker_id`) are ignored.",
"title": "RefreshModelsRequest",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"description": "Output of `provider::<id>::refresh_models`.",
"properties": {
"count": {
"format": "uint",
"minimum": 0,
"type": "integer"
},
"ok": {
"type": "boolean"
}
},
"required": [
"count",
"ok"
],
"title": "RefreshModelsResponse",
"type": "object"
}
},
{
"description": "Stream an OpenRouter chat completion: resolve credentials, call the upstream Chat Completions API, and relay AssistantMessageEvent frames to writer_ref.",
"metadata": {},
"name": "provider::openrouter::stream",
"request_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"definitions": {
"AgentFunction": {
"description": "Function invocation schema — what a provider sees as a `tools` array entry (README § Function invocation schema; adapter boundary). These describe iii functions exposed to the model, not provider-native tools.",
"properties": {
"description": {
"type": "string"
},
"execution_mode": {
"type": [
"string",
"null"
]
},
"label": {
"type": [
"string",
"null"
]
},
"name": {
"type": "string"
},
"parameters": true
},
"required": [
"description",
"name",
"parameters"
],
"type": "object"
},
"AgentMessage": {
"anyOf": [
{
"$ref": "#/definitions/AssistantMessage"
},
{
"$ref": "#/definitions/FunctionResultMessage"
},
{
"$ref": "#/definitions/CustomMessage"
},
{
"$ref": "#/definitions/UserMessage"
}
],
"description": "The canonical transcript message union. Untagged: the single-variant role tags disambiguate deserialization."
},
"AssistantMessage": {
"properties": {
"content": {
"items": {
"$ref": "#/definitions/ContentBlock"
},
"type": "array"
},
"error_kind": {
"anyOf": [
{
"$ref": "#/definitions/ErrorKind"
},
{
"type": "null"
}
]
},
"error_message": {
"type": [
"string",
"null"
]
},
"model": {
"type": "string"
},
"native_stop_reason": {
"type": [
"string",
"null"
]
},
"provider": {
"type": "string"
},
"role": {
"$ref": "#/definitions/AssistantRoleTag"
},
"stop_reason": {
"$ref": "#/definitions/StopReason"
},
"timestamp": {
"format": "int64",
"type": "integer"
},
"usage": {
"anyOf": [
{
"$ref": "#/definitions/Usage"
},
{
"type": "null"
}
]
},
"warnings": {
"items": {
"type": "string"
},
"type": [
"array",
"null"
]
}
},
"required": [
"content",
"model",
"provider",
"role",
"stop_reason",
"timestamp"
],
"type": "object"
},
"AssistantRoleTag": {
"enum": [
"assistant"
],
"type": "string"
},
"ChannelDirection": {
"enum": [
"read",
"write"
],
"type": "string"
},
"ContentBlock": {
"description": "Content blocks — the atomic units of message content (README § Content blocks).",
"oneOf": [
{
"properties": {
"text": {
"type": "string"
},
"type": {
"enum": [
"text"
],
"type": "string"
}
},
"required": [
"text",
"type"
],
"type": "object"
},
{
"properties": {
"data": {
"type": "string"
},
"mime": {
"type": "string"
},
"type": {
"enum": [
"image"
],
"type": "string"
}
},
"required": [
"data",
"mime",
"type"
],
"type": "object"
},
{
"properties": {
"signature": {
"type": [
"string",
"null"
]
},
"text": {
"type": "string"
},
"type": {
"enum": [
"thinking"
],
"type": "string"
}
},
"required": [
"text",
"type"
],
"type": "object"
},
{
"description": "Opaque redacted thinking payload — replayed verbatim on the Anthropic wire.",
"properties": {
"data": {
"type": "string"
},
"type": {
"enum": [
"redacted_thinking"
],
"type": "string"
}
},
"required": [
"data",
"type"
],
"type": "object"
},
{
"properties": {
"arguments": true,
"function_id": {
"type": "string"
},
"id": {
"type": "string"
},
"type": {
"enum": [
"function_call"
],
"type": "string"
}
},
"required": [
"arguments",
"function_id",
"id",
"type"
],
"type": "object"
},
{
"properties": {
"content": {
"items": {
"$ref": "#/definitions/ContentBlock"
},
"type": "array"
},
"function_call_id": {
"type": "string"
},
"is_error": {
"type": [
"boolean",
"null"
]
},
"type": {
"enum": [
"function_result"
],
"type": "string"
}
},
"required": [
"content",
"function_call_id",
"type"
],
"type": "object"
}
]
},
"CustomMessage": {
"properties": {
"content": {
"items": {
"$ref": "#/definitions/ContentBlock"
},
"type": "array"
},
"custom_type": {
"type": "string"
},
"details": true,
"display": {
"type": [
"string",
"null"
]
},
"role": {
"$ref": "#/definitions/CustomRoleTag"
},
"timestamp": {
"format": "int64",
"type": "integer"
}
},
"required": [
"content",
"custom_type",
"role",
"timestamp"
],
"type": "object"
},
"CustomRoleTag": {
"enum": [
"custom"
],
"type": "string"
},
"ErrorKind": {
"enum": [
"auth_expired",
"rate_limited",
"context_overflow",
"transient",
"permanent"
],
"type": "string"
},
"FunctionResultMessage": {
"properties": {
"content": {
"items": {
"$ref": "#/definitions/ContentBlock"
},
"type": "array"
},
"details": true,
"function_call_id": {
"type": "string"
},
"function_id": {
"type": "string"
},
"is_error": {
"type": "boolean"
},
"role": {
"$ref": "#/definitions/FunctionResultRoleTag"
},
"timestamp": {
"format": "int64",
"type": "integer"
}
},
"required": [
"content",
"details",
"function_call_id",
"function_id",
"is_error",
"role",
"timestamp"
],
"type": "object"
},
"FunctionResultRoleTag": {
"enum": [
"function_result"
],
"type": "string"
},
"Model": {
"description": "The capability record (README § Model descriptor).",
"properties": {
"context_window": {
"format": "uint64",
"minimum": 0,
"type": "integer"
},
"display_name": {
"type": [
"string",
"null"
]
},
"id": {
"type": "string"
},
"input_limit": {
"format": "uint64",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"max_output_tokens": {
"format": "uint64",
"minimum": 0,
"type": "integer"
},
"pricing": {
"anyOf": [
{
"$ref": "#/definitions/Pricing"
},
{
"type": "null"
}
]
},
"provider": {
"type": "string"
},
"reasoning_efforts": {
"items": {
"$ref": "#/definitions/ReasoningEffort"
},
"type": [
"array",
"null"
]
},
"supports_cache": {
"type": [
"boolean",
"null"
]
},
"supports_structured_output": {
"type": [
"boolean",
"null"
]
},
"supports_thinking": {
"type": [
"boolean",
"null"
]
},
"supports_tools": {
"type": [
"boolean",
"null"
]
},
"supports_vision": {
"type": [
"boolean",
"null"
]
},
"supports_xhigh": {
"type": [
"boolean",
"null"
]
},
"thinking_budgets": {
"additionalProperties": {
"format": "uint64",
"minimum": 0,
"type": "integer"
},
"type": [
"object",
"null"
]
}
},
"required": [
"context_window",
"id",
"max_output_tokens",
"provider"
],
"type": "object"
},
"Pricing": {
"properties": {
"cache_read": {
"format": "double",
"type": [
"number",
"null"
]
},
"cache_write": {
"format": "double",
"type": [
"number",
"null"
]
},
"input": {
"format": "double",
"type": [
"number",
"null"
]
},
"output": {
"format": "double",
"type": [
"number",
"null"
]
}
},
"type": "object"
},
"ReasoningEffort": {
"description": "One provider-native reasoning effort advertised for a specific model.\n\nValues intentionally remain strings: provider catalogs can add efforts without requiring a router-wide enum release first.",
"properties": {
"description": {
"type": [
"string",
"null"
]
},
"effort": {
"type": "string"
}
},
"required": [
"effort"
],
"type": "object"
},
"ResponseFormat": {
"properties": {
"schema": true,
"type": {
"type": "string"
}
},
"required": [
"type"
],
"type": "object"
},
"StopReason": {
"enum": [
"end",
"length",
"function_call",
"aborted",
"error"
],
"type": "string"
},
"StreamChannelRef": {
"properties": {
"access_key": {
"type": "string"
},
"channel_id": {
"type": "string"
},
"direction": {
"$ref": "#/definitions/ChannelDirection"
}
},
"required": [
"access_key",
"channel_id",
"direction"
],
"type": "object"
},
"ThinkingLevel": {
"description": "\"minimal\" requests the lowest reasoning effort and needs only `thinking` support; levels map to provider-native knobs via `Model::thinking_budgets`.",
"enum": [
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"type": "string"
},
"Usage": {
"properties": {
"cache_read": {
"format": "uint64",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"cache_write": {
"format": "uint64",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"cost_usd": {
"format": "double",
"type": [
"number",
"null"
]
},
"input": {
"format": "uint64",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"output": {
"format": "uint64",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"reasoning": {
"format": "uint64",
"minimum": 0,
"type": [
"integer",
"null"
]
}
},
"type": "object"
},
"UserMessage": {
"properties": {
"content": {
"items": {
"$ref": "#/definitions/ContentBlock"
},
"type": "array"
},
"role": {
"$ref": "#/definitions/UserRoleTag"
},
"timestamp": {
"format": "int64",
"type": "integer"
}
},
"required": [
"content",
"role",
"timestamp"
],
"type": "object"
},
"UserRoleTag": {
"description": "Single-variant role tags: exact-match on deserialize, correct wire string on serialize, and they let `AgentMessage` be an untagged union.",
"enum": [
"user"
],
"type": "string"
}
},
"description": "Input of a provider worker's `provider::<id>::stream` iii function — what the router forwards per attempt. (No `PartialEq`: `iii_sdk::StreamChannelRef` doesn't implement it.)",
"properties": {
"max_output_tokens": {
"format": "uint64",
"minimum": 0,
"type": [
"integer",
"null"
]
},
"messages": {
"items": {
"$ref": "#/definitions/AgentMessage"
},
"type": "array"
},
"model": {
"type": "string"
},
"model_meta": {
"anyOf": [
{
"$ref": "#/definitions/Model"
},
{
"type": "null"
}
]
},
"provider_options": true,
"resolution_key": {
"type": [
"string",
"null"
]
},
"response_format": {
"anyOf": [
{
"$ref": "#/definitions/ResponseFormat"
},
{
"type": "null"
}
]
},
"session_id": {
"description": "Stable conversation identity for provider cache affinity.",
"type": [
"string",
"null"
]
},
"system_prompt": {
"type": [
"string",
"null"
]
},
"thinking_level": {
"anyOf": [
{
"$ref": "#/definitions/ThinkingLevel"
},
{
"type": "null"
}
]
},
"tools": {
"items": {
"$ref": "#/definitions/AgentFunction"
},
"type": [
"array",
"null"
]
},
"writer_ref": {
"$ref": "#/definitions/StreamChannelRef"
}
},
"required": [
"messages",
"model",
"writer_ref"
],
"title": "ProviderStreamInput",
"type": "object"
},
"response_schema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"description": "Output of a provider's `provider::<id>::stream` (spec § stream contract): the function streams frames to `writer_ref` and returns this ack.",
"properties": {
"ok": {
"type": "boolean"
}
},
"required": [
"ok"
],
"title": "ProviderStreamOutput",
"type": "object"
}
}
],
"triggers": []
}