Migrate from Helicone

Helicone was acquired by Mintlify in March 2026. The platform is now in maintenance mode — security patches, new model support, and bug fixes, but no new governance features. If you need an actively developed gateway with PII scanning, HITL approvals, and managed runners, this guide covers the move.

Migration time: 10–20 minutes. Helicone and Curate-Me use the same “swap the base URL” pattern, so the change is almost identical.

Environment variable mapping

Helicone env var	Curate-Me equivalent	Notes
`HELICONE_API_KEY`	`CM_API_KEY` (`cm_sk_...`)	Same role; different format
Helicone base URL (`https://oai.helicone.ai/v1`)	`https://api.curate-me.ai/v1/openai`	Per-provider path
Helicone-Auth header	`X-CM-API-Key` header	Same position; different header name
`Helicone-User-Id`	`X-CM-User-Id`	Optional per-request user attribution
`Helicone-Property-*` headers	`X-CM-Tag-*` custom tags	Roadmap; not available yet
`Helicone-Cache-Enabled`	—	Response caching is on the CM roadmap

Before / after code diff

Python


 from openai import OpenAI
 
 client = OpenAI(
-    base_url="https://oai.helicone.ai/v1",
-    default_headers={
-        "Helicone-Auth": f"Bearer {HELICONE_API_KEY}",
-    },
+    base_url="https://api.curate-me.ai/v1/openai",
+    api_key="cm_sk_your_gateway_key",
 )
 response = client.chat.completions.create(
     model="gpt-4o",
     messages=[{"role": "user", "content": "Hello"}],
 )
 print(response.choices[0].message.content)

For Anthropic (Helicone’s https://anthropic.helicone.ai → CM):


 import anthropic
 
 client = anthropic.Anthropic(
-    base_url="https://anthropic.helicone.ai",
-    default_headers={
-        "Helicone-Auth": f"Bearer {HELICONE_API_KEY}",
-    },
+    base_url="https://api.curate-me.ai/v1/anthropic",
+    api_key="cm_sk_your_gateway_key",
 )

TypeScript


 import OpenAI from 'openai';
 
 const client = new OpenAI({
-  baseURL: 'https://oai.helicone.ai/v1',
-  defaultHeaders: {
-    'Helicone-Auth': `Bearer ${process.env.HELICONE_API_KEY}`,
-  },
+  baseURL: 'https://api.curate-me.ai/v1/openai',
+  apiKey: process.env.CM_API_KEY,
 });
 const response = await client.chat.completions.create({
   model: 'gpt-4o',
   messages: [{ role: 'user', content: 'Hello' }],
 });
 console.log(response.choices[0].message.content);

curl


-curl https://oai.helicone.ai/v1/chat/completions \
-  -H "Authorization: Bearer $OPENAI_API_KEY" \
-  -H "Helicone-Auth: Bearer $HELICONE_API_KEY" \
-  -H "Content-Type: application/json" \
-  -d '{"model":"gpt-4o","messages":[{"role":"user","content":"Hello"}]}'
+curl https://api.curate-me.ai/v1/openai/chat/completions \
+  -H "X-CM-API-Key: $CM_API_KEY" \
+  -H "Content-Type: application/json" \
+  -d '{"model":"gpt-4o","messages":[{"role":"user","content":"Hello"}]}'

Step-by-step migration

Create a Curate-Me account and get your gateway key

Store your provider secrets

Curate-Me injects your upstream API keys automatically once they’re stored:


# OpenAI
curl -X POST https://api.curate-me.ai/v1/admin/secrets \
  -H "X-CM-API-Key: cm_sk_your_gateway_key" \
  -H "Content-Type: application/json" \
  -d '{"provider": "openai", "secret": "sk-your-openai-key"}'
 
# Anthropic
curl -X POST https://api.curate-me.ai/v1/admin/secrets \
  -H "X-CM-API-Key: cm_sk_your_gateway_key" \
  -H "Content-Type: application/json" \
  -d '{"provider": "anthropic", "secret": "sk-ant-your-key"}'

Set a daily budget


curl -X POST https://api.curate-me.ai/v1/admin/budgets \
  -H "X-CM-API-Key: cm_sk_your_gateway_key" \
  -H "Content-Type: application/json" \
  -d '{"daily_limit_usd": 30.0, "scope": "org"}'

Update your environment variables


unset HELICONE_API_KEY
 
export CM_API_KEY=cm_sk_your_gateway_key
# OpenAI SDK
export OPENAI_BASE_URL=https://api.curate-me.ai/v1/openai
export OPENAI_API_KEY=cm_sk_your_gateway_key
# Anthropic SDK
export ANTHROPIC_BASE_URL=https://api.curate-me.ai/v1/anthropic

Verify your first request


curl https://api.curate-me.ai/v1/openai/chat/completions \
  -H "X-CM-API-Key: $CM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-4o","messages":[{"role":"user","content":"Migration test"}]}'

Confirm the trace appears in Dashboard → Traces within a few seconds.

Helicone feature equivalents

Helicone feature	Curate-Me equivalent
Request logging	Traces dashboard (full request/response with cost)
User tracking (`Helicone-User-Id`)	`X-CM-User-Id` header (partial — dashboard grouping roadmap)
Custom properties (`Helicone-Property-*`)	Tag system (roadmap)
Prompt management	Not available
Experiments / A/B testing	Not available
Rate limiting	IETF-standard `RateLimit-*` headers per key/org
Moderation / safety	PII scanning + content safety built-in (no add-on needed)
Semantic caching	Roadmap
Cost tracking	Per-request, per-key, per-org hierarchies
Webhook on request	Roadmap
Datasets	Not available

Helicone data export before migration

If you want to preserve historical data from Helicone, export it before cancelling:

Helicone Dashboard → Requests → Export
Choose CSV or JSON format
Store in your own data warehouse (Helicone exports in OpenAI request format)

Curate-Me’s traces API does not currently import external data — this is archive-only.

Rollback


export HELICONE_API_KEY=your-old-key
export OPENAI_BASE_URL=https://oai.helicone.ai/v1
# Restore default headers in code:
#   "Helicone-Auth": f"Bearer {HELICONE_API_KEY}"
unset CM_API_KEY