Any OpenTelemetry Provider — Universal Integration

Spanora accepts standard OTLP HTTP traces from any OpenTelemetry-compatible source. If your framework, language, or service can export OTEL traces, it works with Spanora out of the box.

This means you can use LangChain, CrewAI, AutoGen, LlamaIndex, Spring AI, or any other framework in any language — as long as it exports OTEL data, Spanora will ingest and visualize it.

Endpoint

Point your OTEL exporter to:

https://spanora.ai/api/v1/traces

Authentication

Include your API key as a Bearer token in the Authorization header:

Authorization: Bearer <your-spanora-api-key>

Get your API key from the dashboard.

Protocol

Both OTLP JSON and OTLP Protobuf content types are supported. Most OTEL exporters default to Protobuf, which works out of the box.

Python Example

Any Python application using the OpenTelemetry SDK can send traces to Spanora:

from opentelemetry import trace
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk.resources import Resource

resource = Resource.create({
    "service.name": "my-ai-app",
})

provider = TracerProvider(resource=resource)
provider.add_span_processor(BatchSpanProcessor(OTLPSpanExporter(
    endpoint="https://spanora.ai/api/v1/traces",
    headers={"Authorization": "Bearer <your-spanora-api-key>"},
)))
trace.set_tracer_provider(provider)

Node.js / TypeScript Example

Use the standard @opentelemetry/exporter-trace-otlp-http package:

import { NodeSDK } from "@opentelemetry/sdk-node";
import { OTLPTraceExporter } from "@opentelemetry/exporter-trace-otlp-http";
import { BatchSpanProcessor } from "@opentelemetry/sdk-trace-base";

const exporter = new OTLPTraceExporter({
  url: "https://spanora.ai/api/v1/traces",
  headers: {
    Authorization: "Bearer <your-spanora-api-key>",
  },
});

const sdk = new NodeSDK({
  spanProcessors: [new BatchSpanProcessor(exporter)],
});

sdk.start();

Environment Variables

Most OTEL SDKs support configuration via environment variables:

OTEL_EXPORTER_OTLP_ENDPOINT=https://spanora.ai
OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=https://spanora.ai/api/v1/traces
OTEL_EXPORTER_OTLP_HEADERS="Authorization=Bearer <your-spanora-api-key>"
OTEL_EXPORTER_OTLP_PROTOCOL=http/protobuf  # or http/json — both are supported

Recommended Resource Attributes

Set these resource attributes so Spanora can group and filter your traces:

What Gets Captured

Spanora automatically recognizes spans following these attribute conventions:

• GenAI Semantic Conventions (gen_ai.*) — the OTEL standard for AI/LLM observability
• OpenInference — used by LlamaIndex, Phoenix, and others
• Vercel AI SDK attributes
• Spanora attributes (spanora.*) for cost and outcome metadata

If your framework emits gen_ai.* attributes on its spans, Spanora will extract model, provider, tokens, prompts, and outputs automatically.

Compatible Frameworks

Any framework that exports OTEL traces works with Spanora. Some popular options:

Troubleshooting

Traces not appearing?

• Verify your API key is correct and prefixed with Bearer in the Authorization header
• Ensure the endpoint URL is exactly https://spanora.ai/api/v1/traces
• Both OTLP HTTP JSON and Protobuf are supported, but gRPC is not — make sure your exporter uses HTTP
• Make sure BatchSpanProcessor is flushed before your process exits

Missing cost data?

• Cost is calculated by Spanora from model name + token counts
• Ensure your spans include gen_ai.request.model and token usage attributes
• If the model is not in Spanora's pricing database, cost will show as null

Next Steps

• LangChain (Python) — Auto-instrumentation for LangChain and LangGraph
• Vercel AI SDK — Native OTEL integration for Vercel AI
• OTEL Attributes — Full list of attributes recognized by Spanora