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

StreamLake API

Open in consoleI need inference
  • 16Models
  • 5Labs
  • 1.05MMax context
  • $0.14/ $0.28From, per 1M in / out

Pricing

ModelLabContextInput / 1MCached / 1MOutput / 1MProviders
MiniMax M3.1 Flashminimax/minimax-m3.1-flashMiniMax1M$0.15$0.015$0.601
DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flashDeepSeek1.05M$0.30$0.006$1.209
GLM 5.3 Flashz-ai/glm-5.3-flashZ.ai1.05M$0.15$0.03$0.5012
GLM 5.3z-ai/glm-5.3Z.ai1.05M$1.40$0.26$4.4012
DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813DeepSeek1.05M$1.32$0.044$3.966
Qwen3.8 27Bqwen/qwen3.8-27bQwen262K$0.50$0.10$3.008
DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731DeepSeek1.05M$0.44$0.014$1.329
GLM 5.2z-ai/glm-5.2Z.ai1.05M$1.40$0.26$4.408
MiniMax M3minimax/minimax-m3MiniMax524K$0.60$0.12$2.403
Qwen3.6 27Bqwen/qwen3.6-27bQwen262K$0.60–$3.604
Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3bQwen262K$0.375–$2.254
DeepSeek V4 Flashdeepseek/deepseek-v4-flashDeepSeek1M$0.14$0.028$0.282
DeepSeek V4 Prodeepseek/deepseek-v4-proDeepSeek1.05M$1.74$0.145$3.484
Kimi K2.6moonshotai/kimi-k2.6Moonshot AI262K$0.95$0.16$4.005
Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17bQwen262K$0.60$0.12$3.603
GLM 5z-ai/glm-5Z.ai205K$1.00$0.20$3.202

StreamLake'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": ["streamlake"] }
  }'

FAQ

How do I send a request to StreamLake?

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

How much does StreamLake cost on RouterPlus?

You pay StreamLake's own price for the model. StreamLake's lowest input price is $0.14 per million tokens (DeepSeek V4 Flash) and its lowest output price is $0.28 per million tokens (DeepSeek V4 Flash). Prices as of November 5, 2026.

Which models does StreamLake serve?

MiniMax M3.1 Flash, DeepSeek V4.1 Flash, GLM 5.3 Flash, GLM 5.3, DeepSeek V4 Pro 0813, Qwen3.8 27B, DeepSeek V4 Flash 0731, GLM 5.2, MiniMax M3, Qwen3.6 27B, Qwen3.6 35B A3B, DeepSeek V4 Flash, DeepSeek V4 Pro, Kimi K2.6, Qwen3.5 397B A17B and GLM 5.

Does StreamLake keep my prompts?

StreamLake declares that it retains prompts, per its published policy.

Route to StreamLake with one key

Open in consoleI need inference