Helicone
"Open-source LLM observability and monitoring platform for developers" - routes, debugs, and analyzes AI applications with access to 100+ models through one API with built-in observability, automatic fallbacks, and zero markup pricing. [1]
Helicone is an open-source LLM observability and gateway platform that routes requests across 100+ models through a single OpenAI-compatible API, with built-in monitoring, semantic caching, automatic failover, and spend controls. It targets developers and teams building AI applications who need multi-provider flexibility without markup on model costs. Paid plans start at $79 per month, with a free tier capped at 10,000 requests per month and an Apache 2.0 self-hosted option. Helicone holds SOC 2 Type II certification and is HIPAA and GDPR compliant, with SDKs for Python and Node.js and an MCP server available.
Best for / Avoid if
Best for: Prototypes and side projects - free to start, no sales call; Regulated or enterprise workloads - compliance attestations and an enterprise plan; AI agents and automation - an agent-ready surface (MCP / llms.txt)
Pricing & procurement
- Pricing model
- Hybrid (base + usage) [2]
- Published pricing
- ✓ Yes [3]
- Free tier
- ✓ Yes [4]
- Free tier details
- Hobby plan at $0/month: 10,000 free requests/month, 1 GB storage, 1 seat, 1 organization, 7-day data retention, 10 logs/min ingestion. Open-source self-hosting also available (Apache 2.0) with zero gateway markup - pay exactly what providers charge. [5]
- Self-serve signup
- ✓ Yes [6]
- Requires sales call
- ✗ No
- Enterprise plan
- ✓ Yes [7]
| Plan | Item | Per | Amount | Source |
|---|---|---|---|---|
| Hobby | Gateway / observability platform | month | $0 | source |
| Hobby | Free request allowance | 10,000 requests/month | $0 | source |
| Pro | Platform subscription | month | $79 | source |
| Pro | Storage overage (usage-based) | 0.30 GB (approx $3.23/GB) | $0.97 | source |
| Team | Platform subscription | month | $799 | source |
| Enterprise | Platform subscription | month | - | source |
| LLM gateway markup | % of LLM spend | 0% + $0 | source | |
| Self-hosted (open source) | $0 | source | ||
| Startup discount | first year (under 2 yrs old, <$5M funding) | 50% | source | |
| Open-source project credit | first year | $100 | source |
Capabilities
- Supported actions
- unified_chat_completions, openai_compatible_api, model_routing, automatic_fallback, load_balancing, semantic_caching, prompt_caching, spend_limits, rate_limiting, observability_logging, tracing, guardrails, prompt_management, virtual_keys, byo_provider_keys, webhooks, alerts, session_tracking, custom_properties, user_feedback_scoring, datasets, experiments, reports, pii_redaction [8]
- Regions
- US, EU [9]
- Input types
- chat completions, text completions, embeddings, image generation, audio (Realtime API / WebSocket), moderation
- Output types
- streaming (SSE), JSON, OpenAI-compatible response
- Webhooks
- ✓ Yes [10]
- Sandbox / test mode
- ✗ No [11]
- SDK languages
- Node.js, Python, Node.js (OpenAI-compatible drop-in) [12]
- MCP server
- ✓ Yes [13]
Trust & compliance
- SOC 2
- SOC 2 Type II [14]
- HIPAA
- ✓ Yes [15]
- GDPR
- ✓ Yes [16]
- ISO 27001
- – Unknown [17]
- PCI DSS
- – Unknown
- Published SLA
- ✗ No [18]
- Rate limits
- Unapproved domains: 10,000 requests per day and 1 request per second (gateway docs). Ingestion limits by plan: Hobby 10 logs/min, Pro 1,000 logs/min, Team 15,000 logs/min, Enterprise 30,000 logs/min. [19]
- Known restrictions
- LLM Security (guardrails) currently works with OpenAI models only (gpt-4, gpt-3.5-turbo, etc.); support for other providers coming soon, SOC 2 Type II report available upon request only, not publicly downloadable, Webhook payload body truncated at 10KB limit (full data via S3 URL, accessible 30 minutes), Cache-Control max duration is 7 days, Free Hobby plan limited to 1 seat and 1 organization, 7-day data retention on free Hobby plan; Enterprise only has configurable/unlimited retention, SLAs listed as an Enterprise-only feature - no public SLA terms published [20]
Developer surface
Integration
- API style
- rest
- Base URL
- https://ai-gateway.helicone.ai
- Version
- v1
- Versioning
- url
- Stability
- ga
- Auth methods
- api_key
- Error format
- vendor-specific
- Webhook signing
- hmac_sha256
- Rate limit
- 10000 / day
Adoption & maturity
- Launched
- 2023-01-01
- GA
- 2023-01-01
Other AI Gateway & LLM Routing APIs
Vercel AI Gateway
"AI Gateway provides a unified API to access hundreds of AI models through a single endpoint, with built-in budgets, usage monitoring, and fallbacks."
Portkey
"Production Stack for Gen AI Builders"
Bifrost (Maxim AI)
"The fastest, most resilient, enterprise-grade LLM, MCP, and agent gateway."
Cloudflare AI Gateway
"Connect to any model, dynamically route requests, and manage usage, billing, and logs from one unified gateway."
TrueFoundry AI Gateway
"A unified AI gateway to securely manage and govern AI across 1600+ models with policy control, real-time monitoring, and up to 30% cost reduction."
OpenRouter
"The Unified Interface For LLMs" - OpenRouter scouts for the best prices, the lowest latencies, and the highest throughput across dozens of providers, offering a single OpenAI-compatible API with automatic fallback, model routing, and unified billing.
References
- ↑Description: helicone.ai · helicone.ai
- ↑Pricing model: helicone.ai
- ↑Published pricing: helicone.ai
- ↑Free tier: helicone.ai
- ↑Free tier details: helicone.ai · helicone.ai
- ↑Self-serve signup: helicone.ai
- ↑Enterprise plan: helicone.ai
- ↑Supported actions: helicone.ai · docs.helicone.ai
- ↑Regions: docs.helicone.ai
- ↑Webhooks: docs.helicone.ai
- ↑Sandbox: docs.helicone.ai
- ↑SDK languages: docs.helicone.ai
- ↑MCP server: docs.helicone.ai
- ↑SOC 2: helicone.ai · docs.helicone.ai
- ↑HIPAA: helicone.ai
- ↑GDPR: docs.helicone.ai · docs.helicone.ai
- ↑ISO 27001: docs.helicone.ai
- ↑Published SLA: helicone.ai · helicone.ai
- ↑Rate limits: helicone.ai · docs.helicone.ai
- ↑Known restrictions: docs.helicone.ai · docs.helicone.ai
Change history
- 2026-06-21 Capabilities: {} → {"guardrails":true,"self_hosted":true,"observability":true,"spend_controls":tru…
- 2026-06-21 Summary Md: (none) → Helicone is an open-source LLM observability and gateway platform that routes r…
- 2026-06-21 Score Pricing Transparency: (none) → 100
- 2026-06-21 Score Setup Speed: (none) → 85
- 2026-06-21 Score Docs Quality: (none) → 35
- 2026-06-21 Score Procurement Friction: (none) → 100
- 2026-06-21 Score Trust Readiness: (none) → 55
- 2026-06-21 Best For: (none) → Prototypes and side projects - free to start, no sales call, Regulated or enter…
- 2026-06-21 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
- 2026-06-21 Score Agent Friendliness: (none) → 55
- 2026-06-21 Llms Txt Present: (none) → Yes
- 2026-06-21 Rendering: (none) → static
- 2026-06-21 Has Structured Data: (none) → No
- 2026-06-21 Robots Allows Agents: (none) → Yes
- 2026-06-21 Status Page URL: (none) → https://status.helicone.ai
- 2026-06-21 Changelog URL: (none) → https://www.helicone.ai/changelog
- 2026-06-21 Docs URL: (none) → https://docs.helicone.ai/getting-started/quick-start
- 2026-06-21 Llms Txt URL: (none) → https://www.helicone.ai/llms.txt
- 2026-06-21 Free Tier Available: set to Yes
- 2026-06-21 Free Tier Details: set to Hobby plan at $0/month: 10,000 free requests/month, 1 GB storage, 1 seat, 1 org…
- 2026-06-21 Self Serve Signup: set to Yes
- 2026-06-21 Requires Sales Call: set to No
- 2026-06-21 Enterprise Plan Available: set to Yes
- 2026-06-21 SOC 2: set to type_2
- 2026-06-21 HIPAA: set to Yes
- 2026-06-21 GDPR: set to Yes
- 2026-06-21 SLA Published: set to No
- 2026-06-21 Data Retention Policy URL: set to https://www.helicone.ai/privacy
- 2026-06-21 Documented Rate Limits: set to Unapproved domains: 10,000 requests per day and 1 request per second (gateway d…
- 2026-06-21 Rate Limit Requests: set to 10000
- 2026-06-21 Rate Limit Window: set to day
- 2026-06-21 Known Restrictions: set to LLM Security (guardrails) currently works with OpenAI models only (gpt-4, gpt-3…
- 2026-06-21 Auth Methods: set to api_key
- 2026-06-21 Auth Docs URL: set to https://docs.helicone.ai/helicone-headers/helicone-auth
- 2026-06-21 API Style: set to rest
- 2026-06-21 Base URL: set to https://ai-gateway.helicone.ai
- 2026-06-21 API Version: set to v1
- 2026-06-21 Versioning Scheme: set to url
- 2026-06-21 Stability: set to ga
- 2026-06-21 MCP URL: set to https://docs.helicone.ai/integrations/tools/mcp
- 2026-06-21 Quickstart URL: set to https://docs.helicone.ai/getting-started/quick-start
- 2026-06-21 Error Format: set to vendor-specific
- 2026-06-21 Webhook Signing: set to hmac_sha256
- 2026-06-21 Webhook Events URL: set to https://docs.helicone.ai/features/webhooks
- 2026-06-21 Requires Verification: set to No
- 2026-06-21 Starting Price Usd: set to 79
- 2026-06-21 Slug: set to helicone
- 2026-06-21 Free Tier Limit: set to 10,000 requests/month; open-source self-host available (Apache 2.0)
- 2026-06-21 Launched At: set to 2023-01-01
- 2026-06-21 GA Date: set to 2023-01-01
Suggest an edit / leave a review
Leave a review or comment
curl -X POST https://apio.sh/api/feedback/helicone \
-H 'Content-Type: application/json' \
-d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'Suggest a correction to a field (cite a source)
curl -X POST https://apio.sh/api/suggest/helicone/FIELD \
-H 'Content-Type: application/json' \
-d '{"value":"corrected value","citations":[{"url":"https://source.example/page","excerpt":"supporting quote"}],"note":"what changed and why"}'