Boundless
Per-token API for open and frontier models, with engineers who tune the serving setup to your traffic
Boundless is an inference provider run by Boundless Networks, Inc. It serves around 20 models through an OpenAI-compatible API: open models from DeepSeek, Z.ai, Moonshot, MiniMax, Qwen and Xiaomi, plus Claude and GPT. It also hosts the Laya decision model on a /v1/systemone endpoint, which is the route Vercel AI Gateway uses for Laya.
Billing is prepaid credits at per-token rates, from $0.04/1M input on DeepSeek V4 Flash, with cached-input prices on most models. Its platform terms say prompts and outputs are not retained. A forward-deployed option has Boundless engineers choose the model and tune serving for a team's workload.
Pricing: Per token usage
Boundless prices by model
Per 1M tokens, read off Boundless's own pricing page on the date shown.
| Model | Input / 1M | Cached / 1M | Output / 1M | Checked | Notes |
|---|---|---|---|---|---|
| DeepSeek V4 Pro | $1.04 | $0.0352 | $2.08 | 3 Oct 2026 | Listed as the 0813 snapshot of DeepSeek V4 Pro. |
| DeepSeek V4.1 Flash | $0.20 | $0.01 | $1.00 | 3 Oct 2026 | |
| GLM 5.3 | $1.12 | $0.14 | $3.52 | 3 Oct 2026 | |
| GLM 5.3 Flash | $0.12 | $0.024 | $0.40 | 3 Oct 2026 | |
| Kimi K3 | $2.30 | $0.23 | $11.40 | 3 Oct 2026 | |
| MiniMax M3 | $0.28 | $0.056 | $1.10 | 3 Oct 2026 |
Boundless Alternatives
Explore 119 products in the Inference APIs category. View all Boundless alternatives.
CheapestInference
Flat-rate unlimited inference on open-weight models, sold in daily 8-hour windows
DeepInfra
Run the top AI models using a simple API, pay per use. Low cost, scalable and production ready infrastructure.
Perplexity API
Web search, agent, embeddings and decision APIs from Perplexity, billed per request or per token
Perplexity pplx-decider
Perplexity's open decision model: typed yes/no, choice and score answers with probabilities, by API or open weights
Work on Boundless? Feature it at the top of Inference APIs.
Is your product missing?