routstr/v0.2.1

v0.2.1

cursor-problems/REPRODUCE.md

@@ -1,44 +0,0 @@
-# Reproducing Cursor Problems
-
-Each subdirectory contains a `request.json` (the request body) and `response.json` (the error response received).
-
-## Using curl to reproduce
-
-From the `routstr-core/` directory:
-
-```bash
-# OpenAI model error
-curl -X POST https://staging.routstr.com/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -H "Authorization: Bearer $API_KEY" \
-  -d @cursor-problems/openai-model-error/request.json
-
-# Anthropic internal error
-curl -X POST https://staging.routstr.com/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -H "Authorization: Bearer $API_KEY" \
-  -d @cursor-problems/anthropic-internal-error/request.json
-
-# Model not found error
-curl -X POST https://staging.routstr.com/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -H "Authorization: Bearer $API_KEY" \
-  -d @cursor-problems/model-not-found-error/request.json
-
-# Upstream rate limit error
-curl -X POST https://staging.routstr.com/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -H "Authorization: Bearer $API_KEY" \
-  -d @cursor-problems/upstream-rate-limit-error/request.json
-```
-
-## Generic pattern
-
-```bash
-curl -X POST <API_ENDPOINT> \
-  -H "Content-Type: application/json" \
-  -H "Authorization: Bearer $API_KEY" \
-  -d @cursor-problems/<directory>/request.json
-```
-
-The `-d @filename` syntax tells curl to read the request body from a file.

cursor-problems/anthropic-internal-error/response.json

@@ -1,8 +0,0 @@
-{
-    "error": {
-        "message": "Internal Server Error",
-        "type": "upstream_error",
-        "code": 502
-    },
-    "request_id": "4a04e4f8-4a31-45f1-8189-455c86fc4e89"
-}

cursor-problems/model-not-found-error/response.json

@@ -1,8 +0,0 @@
-{
-    "error": {
-        "message": "Model 'claude-4.5-sonnet-thinking' not found",
-        "type": "invalid_model",
-        "code": 400
-    },
-    "request_id": "d410f512-3221-4047-a4ee-9be6e3fabe38"
-}

cursor-problems/openai-model-error/response.json

@@ -1,8 +0,0 @@
-{
-    "error": {
-        "message": "Input required: specify \"prompt\" or \"messages\"",
-        "type": "invalid_request_error",
-        "code": 400
-    },
-    "request_id": "586e0aec-351f-413a-8641-ddda4a0cbadf"
-}

cursor-problems/upstream-rate-limit-error/response.json

@@ -1,8 +0,0 @@
-{
-    "error": {
-        "message": "Upstream request failed",
-        "type": "rate_limit_exceeded",
-        "code": 429
-    },
-    "request_id": "80657fc6-4bca-4cb1-945d-ea65ec8a53c4"
-}

example.py

@@ -1,37 +0,0 @@
-import os
-
-import openai
-
-client = openai.OpenAI(
-    api_key=os.environ["CASHU_TOKEN"],
-    base_url=os.environ.get("ROUTSTR_API_URL", "https://api.routstr.com/v1"),
-    # base_url="http://roustrjfsdgfiueghsklchg.onion/v1",
-    # client=httpx.AsyncClient(
-    #     proxies={"http": "socks5://localhost:9050"},
-    # ),  # to use onion proxy (tor)
-)
-history: list = []
-
-
-def chat() -> None:
-    while True:
-        user_msg = {"role": "user", "content": input("\nYou: ")}
-        history.append(user_msg)
-        ai_msg = {"role": "assistant", "content": ""}
-
-        for chunk in client.chat.completions.create(
-            model=os.environ.get("MODEL", "openai/gpt-4o-mini"),
-            messages=history,
-            stream=True,
-        ):
-            if len(chunk.choices) > 0:
-                content = chunk.choices[0].delta.content
-                if content is not None:
-                    ai_msg["content"] += content
-                    print(content, end="", flush=True)
-        print()
-        history.append(ai_msg)
-
-
-if __name__ == "__main__":
-    chat()

examples/balance/check_balance.py

@@ -0,0 +1,11 @@
+import os
+
+import httpx
+
+# Use your Cashu token or API key as the Bearer token,
+# cashu token is hashed on the server and acts as an Temporary API key
+headers = {"Authorization": f"Bearer {os.environ.get('TOKEN')}"}
+base_url = os.environ.get("API_URL", "https://api.routstr.com/v1")
+
+resp = httpx.get(f"{base_url}/balance/info", headers=headers)
+print(resp.json())

examples/balance/create_balance.py

@@ -0,0 +1,15 @@
+import os
+
+import httpx
+
+# Send a Cashu token to the /create endpoint to get a persistent API key
+token = os.environ.get("TOKEN")
+if not token:
+    print("Please set TOKEN environment variable with a Cashu token")
+    exit(1)
+
+base_url = os.environ.get("API_URL", "https://api.routstr.com/v1")
+
+resp = httpx.get(f"{base_url}/balance/create", params={"initial_balance_token": token})
+
+print(resp.json())

examples/balance/refund_balance.py

@@ -0,0 +1,12 @@
+import os
+
+import httpx
+
+# Use your Cashu token or API key as the Bearer token
+headers = {"Authorization": f"Bearer {os.environ.get('TOKEN')}"}
+base_url = os.environ.get("API_URL", "https://api.routstr.com/v1")
+
+resp = httpx.post(f"{base_url}/balance/refund", headers=headers)
+
+print("Refund successful!")
+print(resp.json())

examples/balance/topup_balance.py

@@ -0,0 +1,16 @@
+import os
+
+import httpx
+
+# Use your Cashu token or API key as the Bearer token
+headers = {"Authorization": f"Bearer {os.environ.get('TOKEN')}"}
+base_url = os.environ.get("API_URL", "https://api.routstr.com/v1")
+
+# The Cashu token to top up with
+cashu_token = input("Enter Cashu token to top up: ")
+
+resp = httpx.post(
+    f"{base_url}/balance/topup", headers=headers, json={"cashu_token": cashu_token}
+)
+
+print(resp.json())

examples/chat_completions.py

@@ -0,0 +1,15 @@
+import os
+
+from openai import OpenAI
+
+client = OpenAI(
+    api_key=os.environ.get("TOKEN"),
+    base_url=os.environ.get("API_URL", "https://api.routstr.com/v1"),
+)
+
+response = client.chat.completions.create(
+    model=os.environ.get("MODEL", "gpt-5-nano"),
+    messages=[{"role": "user", "content": "Hello!"}],
+)
+
+print(response.choices[0].message.content)

examples/list_models.py

@@ -0,0 +1,19 @@
+import os
+
+import httpx
+from openai import OpenAI
+
+client = OpenAI(
+    api_key=os.environ.get("TOKEN", ""),
+    base_url=os.environ.get("API_URL", "https://api.routstr.com/v1"),
+)
+
+for model in client.models.list():
+    print(model.id)
+
+# OR
+
+models = httpx.get(
+    f"{client.base_url}/v1/models",
+    headers={"Authorization": f"Bearer {client.api_key}"},
+).json()

examples/responses/conversation.py

@@ -0,0 +1,31 @@
+import os
+
+from openai import OpenAI
+
+client = OpenAI(
+    api_key=os.environ.get("TOKEN"),
+    base_url=os.environ.get("API_URL", "https://api.routstr.com/v1"),
+)
+
+conversation = []  # type: ignore
+
+# First turn
+response1 = client.responses.create(  # type: ignore
+    model="o4-mini",
+    input="Hi, my name is Alice.",
+    conversation=conversation,
+)
+print("Response 1:", response1.output)
+
+# Note: The 'conversation' parameter might need to be constructed differently
+# depending on exact SDK/API spec. Typically, you pass back the previous turn's data.
+# Assuming the SDK manages or returns a conversation object/ID:
+# conversation.append(response1)
+
+# Second turn - demonstrating intent, actual implementation depends on strict API spec
+# response2 = client.responses.create(
+#     model="openai/gpt-4o-mini",
+#     input="What is my name?",
+#     conversation=conversation,
+# )
+# print("Response 2:", response2.output)

examples/responses/create.py

@@ -0,0 +1,17 @@
+import os
+
+from openai import OpenAI
+
+# The OpenAI SDK handles the 'responses' endpoint if it's updated to the latest version
+# and the base_url points to a compatible proxy like Routstr.
+client = OpenAI(
+    api_key=os.environ.get("TOKEN"),
+    base_url=os.environ.get("API_URL", "https://api.routstr.com/v1"),
+)
+
+response = client.responses.create(
+    model="gpt-5-mini",
+    input="Tell me a three sentence bedtime story about a unicorn.",
+)
+
+print(response.output)

examples/responses/streaming_response.py

@@ -0,0 +1,20 @@
+import os
+
+from openai import OpenAI
+
+client = OpenAI(
+    api_key=os.environ.get("TOKEN"),
+    base_url=os.environ.get("API_URL", "https://api.routstr.com/v1"),
+)
+
+stream = client.responses.create(
+    model="claude-4.5-sonnet",
+    input="Write a short poem about rust.",
+    stream=True,
+)
+
+for event in stream:
+    # Note: Depending on the SDK version and response structure,
+    # you might access event.output_delta or similar fields
+    print(event, end="", flush=True)
+print()

examples/responses/web_search.py

@@ -0,0 +1,16 @@
+import os
+
+from openai import OpenAI
+
+client = OpenAI(
+    api_key=os.environ.get("TOKEN"),
+    base_url=os.environ.get("API_URL", "https://api.routstr.com/v1"),
+)
+
+response = client.responses.create(
+    model="gpt-5-mini",
+    input="What is the latest news about AI?",
+    tools=[{"type": "web_search"}],  # type: ignore
+)
+
+print(response.output)

examples/streaming.py

@@ -0,0 +1,28 @@
+import os
+
+from openai import OpenAI
+
+client = OpenAI(
+    api_key=os.environ.get("TOKEN"),
+    base_url=os.environ.get("API_URL", "https://api.routstr.com/v1"),
+)
+
+messages = []
+while True:
+    messages.append({"role": "user", "content": input("\nYou: ")})
+
+    stream = client.chat.completions.create(
+        model=os.environ.get("MODEL", "gpt-5.1-mini"),
+        messages=messages,  # type: ignore
+        stream=True,
+    )
+
+    print("AI: ", end="")
+    response_content = ""
+    for chunk in stream:
+        if content := chunk.choices[0].delta.content:  # type: ignore
+            print(content, end="", flush=True)
+            response_content += content
+    print()
+
+    messages.append({"role": "assistant", "content": response_content})

examples/tor.py

@@ -0,0 +1,20 @@
+import os
+
+import httpx
+from openai import OpenAI
+
+# Requires `pip install "httpx[socks]"` and a running Tor proxy on port 9050
+client = OpenAI(
+    api_key=os.environ.get("TOKEN"),
+    base_url=os.environ.get("ONION_URL", "http://roustrjfsdgfiueghsklchg.onion/v1"),
+    http_client=httpx.Client(proxies="socks5://localhost:9050"),
+)
+
+print(
+    client.chat.completions.create(
+        model="openai/gpt-4o-mini",
+        messages=[{"role": "user", "content": "Hello from Tor!"}],
+    )
+    .choices[0]
+    .message.content
+)

pyproject.toml

@@ -73,6 +73,7 @@ packages = ["routstr"]
 [tool.ruff.lint]
 select = ["E", "F", "I"]
 ignore = ["E501"]
+exclude = ["examples"]
 
 [tool.mypy]
 python_version = "3.11"

routstr/payment/cost_calculation.py

@@ -191,6 +191,10 @@ async def calculate_cost(  # todo: can be sync
         output_tokens if output_tokens != 0 else usage_data.get("output_tokens", 0)
     )
 
+    # added for response api
+    input_tokens = input_tokens if input_tokens != 0 else  response_data.get("usage", {}).get("input_tokens", 0)
+    output_tokens = output_tokens if output_tokens != 0 else  response_data.get("usage", {}).get("output_tokens", 0)
+
     input_msats = round(input_tokens / 1000 * MSATS_PER_1K_INPUT_TOKENS, 3)
 
     output_msats = round(output_tokens / 1000 * MSATS_PER_1K_OUTPUT_TOKENS, 3)

routstr/proxy.py

@@ -137,20 +137,14 @@ async def proxy(
             "unauthorized", "Unauthorized", 401, request=request
         )
 
-    logger.info(  # TODO: move to middleware, async
-        "Received proxy request",
-        extra={
-            "method": request.method,
-            "path": path,
-            "client_host": request.client.host if request.client else "unknown",
-            "user_agent": request.headers.get("user-agent", "unknown")[:100],
-        },
-    )
-
+    is_responses_api = path.startswith("v1/responses") or path.startswith("responses")
     request_body = await request.body()
     request_body_dict = parse_request_body_json(request_body, path)
 
-    model_id = request_body_dict.get("model", "unknown")
+    if is_responses_api:
+        model_id = extract_model_from_responses_request(request_body_dict)
+    else:
+        model_id = request_body_dict.get("model", "unknown")
 
     model_obj = get_model_instance(model_id)
     if not model_obj:
@@ -176,9 +170,14 @@ async def proxy(
     check_token_balance(headers, request_body_dict, max_cost_for_model)
 
     if x_cashu := headers.get("x-cashu", None):
-        return await upstream.handle_x_cashu(
-            request, x_cashu, path, max_cost_for_model, model_obj
-        )
+        if is_responses_api:
+            return await upstream.handle_x_cashu_responses(
+                request, x_cashu, path, max_cost_for_model, model_obj
+            )
+        else:
+            return await upstream.handle_x_cashu(
+                request, x_cashu, path, max_cost_for_model, model_obj
+            )
 
     elif auth := headers.get("authorization", None):
         key = await get_bearer_token_key(headers, path, session, auth)
@@ -193,28 +192,36 @@ async def proxy(
             )
 
         logger.debug("Processing unauthenticated GET request", extra={"path": path})
-        # TODO: why is this needed? can we remove it?
         headers = upstream.prepare_headers(dict(request.headers))
         return await upstream.forward_get_request(request, path, headers)
 
-    # Only pay for request if we have request body data (for completions endpoints)
     if request_body_dict:
         await pay_for_request(key, max_cost_for_model, session)
 
-    # Prepare headers for upstream
     headers = upstream.prepare_headers(dict(request.headers))
 
-    # Forward to upstream and handle response
-    response = await upstream.forward_request(
-        request,
-        path,
-        headers,
-        request_body,
-        key,
-        max_cost_for_model,
-        session,
-        model_obj,
-    )
+    if is_responses_api:
+        response = await upstream.forward_responses_request(
+            request,
+            path,
+            headers,
+            request_body,
+            key,
+            max_cost_for_model,
+            session,
+            model_obj,
+        )
+    else:
+        response = await upstream.forward_request(
+            request,
+            path,
+            headers,
+            request_body,
+            key,
+            max_cost_for_model,
+            session,
+            model_obj,
+        )
 
     if response.status_code != 200:
         await revert_pay_for_request(key, session, max_cost_for_model)
@@ -317,6 +324,24 @@ async def get_bearer_token_key(
         raise
 
 
+def extract_model_from_responses_request(request_body_dict: dict[str, Any]) -> str:
+    if model := request_body_dict.get("model"):
+        return model
+
+    if input_data := request_body_dict.get("input"):
+        if isinstance(input_data, dict) and (model := input_data.get("model")):
+            return model
+
+    if request_body_dict.get("messages"):
+        return "unknown"
+
+    logger.warning(
+        "No model found in Responses API request",
+        extra={"body_keys": list(request_body_dict.keys())}
+    )
+    return "unknown"
+
+
 def parse_request_body_json(request_body: bytes, path: str) -> dict[str, Any]:
     request_body_dict = {}
     if request_body: