no advanced testing for now

Add cost usage to messages endpoint

routstr/payment/models.py

@@ -7,7 +7,7 @@ from fastapi import APIRouter, Depends
 from pydantic.v1 import BaseModel
 from sqlmodel.ext.asyncio.session import AsyncSession
 
-from ..core.db import ModelRow, get_session
+from ..core.db import ModelRow, UpstreamProviderRow, get_session
 from ..core.logging import get_logger
 from ..core.settings import settings
 from .price import sats_usd_price
@@ -405,6 +405,76 @@ async def update_sats_pricing() -> None:
             logger.error(f"Error updating sats pricing: {e}")
 
 
+class ModelTestRequest(BaseModel):
+    model_id: str
+    endpoint_type: str
+    request_data: dict
+
+
+@models_router.post("/api/models/test")
+async def test_model(
+    payload: ModelTestRequest,
+    session: AsyncSession = Depends(get_session),
+) -> dict:
+    """Test a model by sending a request through its configured upstream provider."""
+    from sqlmodel import select
+
+    result = await session.execute(
+        select(ModelRow).where(ModelRow.id == payload.model_id)
+    )
+    model_row = result.scalars().first()
+
+    if not model_row:
+        return {
+            "success": False,
+            "error": f"Model '{payload.model_id}' not found in database",
+            "status_code": 404,
+        }
+
+    provider = await session.get(UpstreamProviderRow, model_row.upstream_provider_id)
+    if not provider:
+        return {
+            "success": False,
+            "error": "Upstream provider not found",
+            "status_code": 404,
+        }
+
+    base_url = provider.base_url.rstrip("/")
+    if payload.endpoint_type == "chat-completions":
+        url = f"{base_url}/chat/completions"
+    else:
+        url = f"{base_url}/{payload.endpoint_type}"
+
+    actual_model_id = model_row.forwarded_model_id or model_row.id
+    request_data = dict(payload.request_data)
+    request_data["model"] = actual_model_id
+
+    headers = {
+        "Content-Type": "application/json",
+        "Authorization": f"Bearer {provider.api_key}",
+    }
+
+    try:
+        async with httpx.AsyncClient(timeout=30.0) as client:
+            response = await client.post(url, json=request_data, headers=headers)
+            try:
+                response_data = response.json()
+            except Exception:
+                response_data = {"raw": response.text}
+
+            return {
+                "success": response.status_code < 400,
+                "data": response_data,
+                "status_code": response.status_code,
+            }
+    except Exception as e:
+        return {
+            "success": False,
+            "error": str(e),
+            "status_code": 500,
+        }
+
+
 @models_router.get("/v1/models")
 @models_router.get("/v1/models/", include_in_schema=False)
 @models_router.get("/models")

routstr/proxy.py

@@ -69,7 +69,25 @@ def get_upstreams() -> list[BaseUpstreamProvider]:
 
 def get_model_instance(model_id: str) -> Model | None:
     """Get Model instance by ID from global cache."""
-    return _model_instances.get(model_id.lower())
+    if not model_id:
+        return None
+
+    model_id_lower = model_id.lower()
+    # Try exact match first
+    if model := _model_instances.get(model_id_lower):
+        return model
+
+    # Try stripping common version suffixes (e.g., -20251222)
+    # This handles cases where upstream returns a specific version
+    # but we only track the base model name.
+    import re
+
+    base_model_id = re.sub(r"-\d{8}$", "", model_id_lower)
+    if base_model_id != model_id_lower:
+        if model := _model_instances.get(base_model_id):
+            return model
+
+    return None
 
 
 def get_provider_for_model(model_id: str) -> list[BaseUpstreamProvider] | None:

routstr/upstream/base.py

@@ -119,6 +119,51 @@ class BaseUpstreamProvider:
             "can_show_balance": False,
         }
 
+    def inject_cost_metadata(
+        self,
+        response_json: dict,
+        cost_data: CostData | MaxCostData | dict,
+        key: ApiKey,
+    ) -> None:
+        """Unifies the injection of cost and usage metadata across all completion types."""
+        if isinstance(cost_data, dict):
+            total_msats = cost_data.get("total_msats", 0)
+            total_usd = cost_data.get("total_usd", 0.0)
+            cost_dict = cost_data
+        else:
+            total_msats = cost_data.total_msats
+            total_usd = cost_data.total_usd
+            cost_dict = cost_data.dict()
+
+        sats_cost = total_msats // 1000
+
+        # Inject into top-level usage block (OpenAI/Anthropic style)
+        if "usage" in response_json:
+            response_json["usage"]["cost"] = total_usd
+            response_json["usage"]["cost_sats"] = sats_cost
+            response_json["usage"]["remaining_balance_msats"] = key.balance
+
+        # Inject into Anthropic nested usage block if present
+        if (
+            "message" in response_json
+            and isinstance(response_json["message"], dict)
+            and "usage" in response_json["message"]
+        ):
+            response_json["message"]["usage"]["sats_cost"] = sats_cost
+
+        # Unified Routstr metadata
+        response_json["metadata"] = response_json.get("metadata", {})
+        response_json["metadata"]["routstr"] = {
+            "cost": cost_dict,
+            "sats_cost": sats_cost,
+            "remaining_balance_msats": key.balance,
+        }
+
+        # Legacy/Compatibility fields
+        response_json["cost"] = cost_dict.copy()
+        response_json["cost"]["sats_cost"] = sats_cost
+        response_json["cost"]["remaining_balance_msats"] = key.balance
+
     def prepare_headers(self, request_headers: dict) -> dict:
         """Prepare headers for upstream request by removing proxy-specific headers and adding authentication.
 
@@ -1139,7 +1184,11 @@ class BaseUpstreamProvider:
                 )
 
     async def handle_streaming_messages_completion(
-        self, response: httpx.Response, key: ApiKey, max_cost_for_model: int
+        self,
+        response: httpx.Response,
+        key: ApiKey,
+        max_cost_for_model: int,
+        requested_model: str | None = None,
     ) -> StreamingResponse:
         async def stream_with_cost(
             max_cost_for_model: int,
@@ -1178,6 +1227,8 @@ class BaseUpstreamProvider:
                     stored_chunks.append(chunk)
                     try:
                         decoded_chunk = chunk.decode("utf-8", errors="ignore")
+                        modified_lines = []
+                        changed = False
                         for line in decoded_chunk.split("\n"):
                             if line.startswith("data: "):
                                 try:
@@ -1187,6 +1238,20 @@ class BaseUpstreamProvider:
                                         if msg and msg.get("model"):
                                             last_model_seen = str(msg.get("model"))
 
+                                        if requested_model:
+                                            # Apply requested_model override
+                                            model_updated = False
+                                            if msg:
+                                                msg["model"] = requested_model
+                                                model_updated = True
+                                            if data.get("model"):
+                                                data["model"] = requested_model
+                                                model_updated = True
+
+                                            if model_updated:
+                                                line = "data: " + json.dumps(data)
+                                                changed = True
+
                                         if usage := msg.get("usage"):
                                             input_tokens += usage.get("input_tokens", 0)
                                             output_tokens += usage.get(
@@ -1200,10 +1265,14 @@ class BaseUpstreamProvider:
                                             )
                                 except json.JSONDecodeError:
                                     pass
-                    except Exception:
-                        pass
+                            modified_lines.append(line)
 
-                    yield chunk
+                        if changed:
+                            yield "\n".join(modified_lines).encode("utf-8")
+                        else:
+                            yield chunk
+                    except Exception:
+                        yield chunk
 
                 usage_data = {
                     "input_tokens": input_tokens,
@@ -1225,6 +1294,11 @@ class BaseUpstreamProvider:
                                     new_session,
                                     max_cost_for_model,
                                 )
+
+                                self.inject_cost_metadata(
+                                    combined_data, cost_data, fresh_key
+                                )
+
                                 usage_finalized = True
                                 yield f"event: cost\ndata: {json.dumps({'cost': cost_data})}\n\n".encode()
                             except Exception:
@@ -1264,11 +1338,22 @@ class BaseUpstreamProvider:
         session: AsyncSession,
         deducted_max_cost: int,
         path: str,
+        requested_model: str | None = None,
     ) -> Response:
         try:
             content = await response.aread()
             response_json = json.loads(content)
 
+            if requested_model:
+                if "model" in response_json:
+                    response_json["model"] = requested_model
+                if (
+                    "message" in response_json
+                    and isinstance(response_json["message"], dict)
+                    and "model" in response_json["message"]
+                ):
+                    response_json["message"]["model"] = requested_model
+
             if path.endswith("count_tokens") and "usage" not in response_json:
                 input_tokens = response_json.get("input_tokens", 0)
                 response_json["usage"] = {"input_tokens": input_tokens}
@@ -1276,7 +1361,8 @@ class BaseUpstreamProvider:
             cost_data = await adjust_payment_for_tokens(
                 key, response_json, session, deducted_max_cost
             )
-            response_json["cost"] = cost_data
+
+            self.inject_cost_metadata(response_json, cost_data, key)
 
             allowed_headers = {
                 "content-type",
@@ -1430,7 +1516,10 @@ class BaseUpstreamProvider:
 
                     if is_streaming and response.status_code == 200:
                         result = await self.handle_streaming_messages_completion(
-                            response, key, max_cost_for_model
+                            response,
+                            key,
+                            max_cost_for_model,
+                            requested_model=original_model_id,
                         )
                         background_tasks = BackgroundTasks()
                         background_tasks.add_task(response.aclose)
@@ -1441,7 +1530,12 @@ class BaseUpstreamProvider:
                     if response.status_code == 200:
                         try:
                             return await self.handle_non_streaming_messages_completion(
-                                response, key, session, max_cost_for_model, path
+                                response,
+                                key,
+                                session,
+                                max_cost_for_model,
+                                path,
+                                requested_model=original_model_id,
                             )
                         finally:
                             await response.aclose()
@@ -1451,7 +1545,12 @@ class BaseUpstreamProvider:
                     if response.status_code == 200:
                         try:
                             return await self.handle_non_streaming_messages_completion(
-                                response, key, session, max_cost_for_model, path
+                                response,
+                                key,
+                                session,
+                                max_cost_for_model,
+                                path,
+                                requested_model=original_model_id,
                             )
                         finally:
                             await response.aclose()

routstr/upstream/ppqai.py

@@ -1,9 +1,9 @@
 from __future__ import annotations
 
-from typing import TYPE_CHECKING
+from typing import TYPE_CHECKING, Optional
 
 import httpx
-from pydantic import BaseModel
+from pydantic import BaseModel, Field
 
 from ..core.logging import get_logger
 from ..payment.models import Architecture, Model, Pricing, async_fetch_openrouter_models
@@ -16,18 +16,20 @@ logger = get_logger(__name__)
 
 
 class PPQAIModelPricing(BaseModel):
-    ui: dict[str, float]
-    api: dict[str, float]
+    ui: Optional[dict[str, float]] = None
+    api: Optional[dict[str, float]] = None
+    input_per_1M_tokens: Optional[float] = Field(None, alias="input_per_1M_tokens")
+    output_per_1M_tokens: Optional[float] = Field(None, alias="output_per_1M_tokens")
 
 
 class PPQAIModel(BaseModel):
     id: str
-    provider: str
+    provider: Optional[str] = None
     name: str
     created_at: int
     context_length: int
     pricing: PPQAIModelPricing
-    popular: bool
+    popular: bool = False
 
 
 class PPQAIUpstreamProvider(BaseUpstreamProvider):
@@ -134,31 +136,54 @@ class PPQAIUpstreamProvider(BaseUpstreamProvider):
                         )
 
                         if or_model:
-                            if input_price := ppqai_model.pricing.api.get(
-                                "input_per_1M"
-                            ):
+                            input_price = None
+                            if ppqai_model.pricing.api:
+                                input_price = ppqai_model.pricing.api.get(
+                                    "input_per_1M"
+                                )
+                            elif ppqai_model.pricing.input_per_1M_tokens:
+                                input_price = ppqai_model.pricing.input_per_1M_tokens
+
+                            if input_price is not None:
                                 or_model.pricing.prompt = input_price / 1_000_000
-                            if output_price := ppqai_model.pricing.api.get(
-                                "output_per_1M"
-                            ):
+
+                            output_price = None
+                            if ppqai_model.pricing.api:
+                                output_price = ppqai_model.pricing.api.get(
+                                    "output_per_1M"
+                                )
+                            elif ppqai_model.pricing.output_per_1M_tokens:
+                                output_price = ppqai_model.pricing.output_per_1M_tokens
+
+                            if output_price is not None:
                                 or_model.pricing.completion = output_price / 1_000_000
+
                             if cl := ppqai_model.context_length:
                                 or_model.context_length = cl
                             models.append(or_model)
                         else:
-                            input_price = ppqai_model.pricing.api.get(
-                                "input_per_1M", 0.0
-                            )
-                            output_price = ppqai_model.pricing.api.get(
-                                "output_per_1M", 0.0
-                            )
+                            input_price = 0.0
+                            if ppqai_model.pricing.api:
+                                input_price = ppqai_model.pricing.api.get(
+                                    "input_per_1M", 0.0
+                                )
+                            elif ppqai_model.pricing.input_per_1M_tokens:
+                                input_price = ppqai_model.pricing.input_per_1M_tokens
+
+                            output_price = 0.0
+                            if ppqai_model.pricing.api:
+                                output_price = ppqai_model.pricing.api.get(
+                                    "output_per_1M", 0.0
+                                )
+                            elif ppqai_model.pricing.output_per_1M_tokens:
+                                output_price = ppqai_model.pricing.output_per_1M_tokens
 
                             models.append(
                                 Model(
                                     id=ppqai_model.id,
                                     name=ppqai_model.name,
                                     created=ppqai_model.created_at // 1000,
-                                    description=f"{ppqai_model.provider} model",
+                                    description=f"{ppqai_model.provider or 'PPQ.AI'} model",
                                     context_length=ppqai_model.context_length,
                                     architecture=Architecture(
                                         modality="text->text",

ui/components/api-endpoint-tester.tsx

@@ -471,7 +471,11 @@ export function ApiEndpointTester({ models }: ApiEndpointTesterProps) {
     testEndpointMutation.mutate(requestData);
   };
 
-  const enabledModels = models.filter((model) => model.isEnabled);
+  const enabledModels = Array.from(
+    new Map(
+      models.filter((model) => model.isEnabled).map((m) => [m.id, m])
+    ).values()
+  );
   const credentials = selectedModel ? getModelCredentials(selectedModel) : null;
   const endpointUrl = credentials
     ? buildEndpointUrl(

ui/components/model-tester.tsx

@@ -197,7 +197,11 @@ export function ModelTester({ models }: ModelTesterProps) {
     testModelMutation.mutate(request);
   };
 
-  const enabledModels = models.filter((model) => model.isEnabled);
+  const enabledModels = Array.from(
+    new Map(
+      models.filter((model) => model.isEnabled).map((m) => [m.id, m])
+    ).values()
+  );
   const credentials = selectedModel ? getModelCredentials(selectedModel) : null;
 
   return (

ui/components/models-page.tsx

@@ -124,12 +124,14 @@ export function ModelsPage() {
             >
               Basic Testing
             </TabsTrigger>
+            {/*
             <TabsTrigger
               value='test-api'
               className='h-9 snap-start px-2 text-[13px] sm:h-10 sm:px-2.5 sm:text-sm'
             >
               API Endpoints
             </TabsTrigger>
+            */}
           </TabsList>
 
           <TabsContent value='manage' className='mt-0'>