1endpoint
One API for leading AI models, transparent token pricing
Last verified:
What is 1endpoint?
1endpoint is an API gateway that provides access to 16+ AI models (Claude, GPT, DeepSeek, Gemini, GLM, and others) through a single unified endpoint with transparent token-based pricing. Designed for high-volume workloads, it emphasizes cost efficiency through prompt caching and independent pricing for input, cached, and output tokens.
1endpoint pricing
Pricing model: Freemium
Usage-based pricing at $1 per 1,000 credits. Input tokens from $0.0420–$1.50 per 1M depending on model; cached tokens at 1/5 input rate; output pricing varies by model.
1endpoint pros
- Unified API gateway supporting 16+ models with a single base URL change
- Highly competitive token pricing starting at $0.0420 per 1M input tokens
- Prompt caching reduces costs up to 5x for cached tokens, with transparent cache-hit pricing
- Independent pricing for input, cached input, and output tokens with no hidden platform fees
1endpoint cons
- Limited to the fixed model catalog provided; no custom model deployment
- No mention of SLA/uptime guarantees or tiered support options
- Cache ratio and pricing benefits vary significantly by model
- Early-stage service with limited documentation visible on homepage
Frequently asked questions about 1endpoint
How much cheaper is caching?
Cached input tokens are billed at 5× less than uncached input. For example, message 12 in a conversation costs $1.41 instead of $5.17 without caching.
Do I need to rewrite my code?
No. The API is compatible by design—only change the base URL to https://1endpoint.dev/api/v1 and specify the model ID.
Which models are supported?
16+ models including GLM 5.2/5.3, GPT 5.6 variants, DeepSeek V4, Gemini 3.7 Flash, Claude Sonnet/Opus/Fable, and others.
Are there hidden fees?
No. Input, cached input, and output are priced independently with no blended platform fee.