Helicone
Independent gateway · no token markup · BYOK 0% · hosted or self-host · open source · checked Sep 23, 2026
What it costs on real workloads
| Model | Direct | Through Helicone |
|---|---|---|
 Claude Sonnet 5 | $400.00 | $400.00vs $400.00 direct |
 GPT-6 Sol | $400.00 | $400.00vs $400.00 direct |
 Gemini 3.8 Flash | $150.00 | $150.00vs $150.00 direct |
 DeepSeek V4.1 Flash | $27.00 | $27.00vs $27.00 direct |
100M input and 20M output tokens a month, paying with gateway credits.
About Helicone
Open source LLM observability platform with an OpenAI-compatible AI gateway that logs, caches and fails over requests across providers.
- Fee on tokens
- None
- Pricing model
- 0% markup on credits; plans by requests and seats (Pro $79 a month)
- Bring your own key
- 0% fee
- Entry plan
- Pro, $79/mo
- Hosting
- Hosted or self-host
- License
- Apache 2.0
Features stated: Fallbacks, Caching, Guardrails, Observability, Rate limits, Prompts, OpenAI-compatible, Bring your own key. Not stated: Load balancing, Budgets, Data residency, Private networking.
The terms, in their words
- Markup
- Gateway docs state 0% markup on credits.
- Free tier
- Hobby: 10,000 free requests, 1 GB storage
- Providers
- 100+ LLM providers
- 0% markup
- Pro: $79 per month; Team: $799 per month
- 10,000 free requests
Source: www.helicone.ai/pricing
Helicone vsKong AI GatewayLiteLLMVercel AI GatewayCloudflare AI GatewayRequestyEden AI
Pricing as read from the gateway's own pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.