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

Boundless API

Open in consoleI need inference
  • 14Models

Pricing

ModelLabContextInput / 1MCached / 1MOutput / 1MProviders
Kimi K3.1 Promoonshotai/kimi-k3.1-proMoonshot AI1.05M$1.70$0.20$8.506
DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017DeepSeek1.05M$0.24$0.0048$0.968
MiMo V2.6 Flashxiaomi/mimo-v2.6-flashXiaomi1.05M$0.14$0.0028$0.283
MiMo V2.6 Proxiaomi/mimo-v2.6-proXiaomi1.05M$0.435$0.0036$0.873
DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flashDeepSeek1.05M$0.20$0.01$1.0010
GLM 5.3 Flashz-ai/glm-5.3-flashZ.ai1.05M$0.12$0.024$0.4013
GLM 5.3z-ai/glm-5.3Z.ai1.05M$1.12$0.14$3.5213
DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813DeepSeek1.05M$1.04$0.0352$2.087
DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731DeepSeek1.05M$0.04$0.02$0.2110
Kimi K3moonshotai/kimi-k3Moonshot AI1.05M$2.30$0.23$11.4011
GLM 5.2z-ai/glm-5.2Z.ai1.05M$0.34$0.17$2.309
MiniMax M3minimax/minimax-m3MiniMax524K$0.28$0.056$1.104
Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3bQwen262K$0.04$0.02$0.355
Gemma 4 31Bgoogle/gemma-4-31b-itGoogle262K$0.42$0.21$0.845

Boundless's price, USD, as of November 8, 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": ["boundless"] }
  }'

FAQ

How do I send a request to Boundless?

Name Boundless in provider.only or provider.order, as "boundless" or "boundless-chat". Boundless serves requests that name it. Where Boundless is the last provider still serving a model, it also serves requests that do not name it.

How much does Boundless cost on RouterPlus?

You pay Boundless's own price for the model. Boundless's lowest input price is $0.04 per million tokens (DeepSeek V4 Flash 0731) and its lowest output price is $0.21 per million tokens (DeepSeek V4 Flash 0731). Prices as of November 8, 2026.

Which models does Boundless serve?

Kimi K3.1 Pro, DeepSeek V4.1 Flash 1017, MiMo V2.6 Flash, MiMo V2.6 Pro, DeepSeek V4.1 Flash, GLM 5.3 Flash, GLM 5.3, DeepSeek V4 Pro 0813, DeepSeek V4 Flash 0731, Kimi K3, GLM 5.2, MiniMax M3, Qwen3.6 35B A3B and Gemma 4 31B.

Does Boundless keep my prompts?

Boundless declares no prompt retention, and zero data retention is Boundless's commitment, not something RouterPlus measures. Boundless keeps a record of each request for 90 days, with account identifiers and no prompt or answer content.

Which backend serves my call?

Boundless is itself a router: it sends each call to one of its own backends. RouterPlus neither chooses nor sees which one serves a call. Your prompt passes through the RouterPlus gateway before it reaches Boundless.

Why did Boundless return a 429?

Boundless's capacity is smaller than other providers'. A long prompt, or one without max_tokens, can be refused with a 429 that waiting will not fix. Shorten the prompt, set max_tokens, or allow another provider.

Route to Boundless with one key

Open in consoleI need inference