Skip to content
NewTry RouterPlus with free creditsTry playground →
RouterPlus
Book a demo

Wafer API

Open in consoleI need inference
  • 8Models
  • 4Labs
  • 1.05MMax context
  • $0.05/ $0.20From, per 1M in / out

Pricing

ModelLabContextInput / 1MCached / 1MOutput / 1MProviders
Kimi K3.1 Promoonshotai/kimi-k3.1-proMoonshot AI1.05M$2.00$0.20$10.005
DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017DeepSeek1.05M$0.13$0.008$0.506
DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flashDeepSeek1.05M$0.19$0.012$0.659
GLM 5.3 Flashz-ai/glm-5.3-flashZ.ai1.05M$0.05$0.03$0.2012
GLM 5.3z-ai/glm-5.3Z.ai1.05M$0.20$0.18$1.8012
Qwen3.8 27Bqwen/qwen3.8-27bQwen262K$0.06$0.05$2.308
Kimi K3moonshotai/kimi-k3Moonshot AI1.05M$0.60$0.20$15.0010
GLM 5.2z-ai/glm-5.2Z.ai1.05M$0.19$0.18$4.408

Wafer's price, USD, as of November 5, 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": ["wafer"] }
  }'

FAQ

How do I send a request to Wafer?

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

How much does Wafer cost on RouterPlus?

You pay Wafer's own price for the model. Wafer's lowest input price is $0.05 per million tokens (GLM 5.3 Flash) and its lowest output price is $0.20 per million tokens (GLM 5.3 Flash). Prices as of November 5, 2026.

Which models does Wafer serve?

Kimi K3.1 Pro, DeepSeek V4.1 Flash 1017, DeepSeek V4.1 Flash, GLM 5.3 Flash, GLM 5.3, Qwen3.8 27B, Kimi K3 and GLM 5.2.

Does Wafer keep my prompts?

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

Route to Wafer with one key

Open in consoleI need inference