Skip to content
NewTry RouterPlus with free creditsTry playground →
  • 2Models

Pricing

ModelLabContextInput / 1MCached / 1MOutput / 1MProviders
DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017DeepSeek1.05M$0.15$0.003$0.6010
GLM 5.3z-ai/glm-5.3Z.ai1.05M$1.40$0.26$4.4014

Alpha.sh's price, USD, as of November 16, 2026. Live prices

Quickstart

OpenAI-compatible
curl https://api.routerplus.com/v1/chat/completions \
  -H "Authorization: Bearer $ROUTERPLUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-5.3",
    "messages": [{ "role": "user", "content": "Hello" }],
    "max_tokens": 1024,
    "provider": { "only": ["alphash-chat"] }
  }'

FAQ

How do I send a request to Alpha.sh?

Routing tries providers cheapest first, by input plus output price, so Alpha.sh serves a model where it is the cheapest and otherwise as a fallback. To send a request to Alpha.sh first, name it in provider.only or provider.order as "alphash-chat".

How much does Alpha.sh cost on RouterPlus?

You pay Alpha.sh's own price for the model. Alpha.sh's lowest input price is $0.15 per million tokens (DeepSeek V4.1 Flash 1017) and its lowest output price is $0.60 per million tokens (DeepSeek V4.1 Flash 1017). Prices as of November 16, 2026.

Which models does Alpha.sh serve?

DeepSeek V4.1 Flash 1017 and GLM 5.3.

Does Alpha.sh keep my prompts?

Alpha.sh declares no prompt retention in its RouterPlus listing, per its published policy.

Route to Alpha.sh with one key