Requesty
Independent gateway · 5% on tokens · BYOK · checked Sep 23, 2026
What it costs on real workloads
| Model | Direct | Through Requesty |
|---|---|---|
 Claude Sonnet 5 | $400.00 | $420.00vs $400.00 direct |
 GPT-6 Sol | $400.00 | $420.00vs $400.00 direct |
 Gemini 3.8 Flash | $150.00 | $157.50vs $150.00 direct |
 DeepSeek V4.1 Flash | $27.00 | $28.35vs $27.00 direct |
100M input and 20M output tokens a month, paying with gateway credits.
About Requesty
Hosted LLM router with fallbacks, load balancing, spend limits and analytics, charging 5% on top of model costs.
- Fee on tokens
- 5%
- Pricing model
- 5% on top of model costs, pay as you go
- Bring your own key
- Yes, fee not stated
- Entry plan
- Pay-As-You-Go
- Hosting
- Hosted
Features stated: Fallbacks, Load balancing, Caching, Guardrails, Observability, Budgets, Bring your own key. Not stated: Rate limits, Prompts, OpenAI-compatible, Data residency, Private networking.
The terms, in their words
- Markup
- 5% markup on model costs on Pay-As-You-Go.
- Free tier
- $0, 200 requests per day, access to all free models
- Providers
- 600+ models, 20+ providers
- A model that costs $10 per 1M tokens from OpenAI costs $10.50 through Requesty
- 200 requests per day
Source: www.requesty.ai/pricing
Requesty vsHeliconeKong AI GatewayLiteLLMVercel AI GatewayCloudflare AI GatewayEden AI
Sources: each gateway's own pricing page and docs, read by hand and fetched again every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.