ProductsPlatform · Endpoints · Splash

Open-weight models,
wherever you run them

Call them per token on Inco Platform, run them on your own compute with Inco Splash,
or on capacity dedicated to your team with Inco Endpoints.

Zero data retention is available whichever product you choose. On Platform and Endpoints, you decide how your data is handled, all the way to prompts and outputs not being kept once the request is served. With Splash, they never leave your machine.

01 · Inco PlatformBeta

Serverless

Serverless open-weight models, at the speed your workload needs

The leading open-weight models, per token, through the OpenAI- and Anthropic-compatible APIs you already use. Run each model at the tier that fits the job.

An illustration of the Inco Platform console for GLM 5.3 Flash, with a tier switch and the code to call it.

from openai import OpenAI​client = OpenAI(    base_url="https://api.inco.ai/v1",    api_key="INCO_API_KEY",)​resp = client.chat.completions.create(    model="glm-5.3-flash:fast",    messages=[{"role": "user", "content": task}],)

Every model, at the speed you need

Multiples vs. Standard
The Batch, Standard, and Fast tiers, measured against Standard
Speed
PriceHalf the list priceList price per token2× the list price
How to callmodel-id:batchmodel-idmodel-id:fast
Best forEvaluations, dataset processing, and other offline jobsMost applications, where cost matters more than peak speedAgents and real-time products, where each step waits on the last answer

Each model's prices are on the live catalog. For your own speed and price, see custom models on Inco Endpoints.

02 · Inco SplashPreview

Local AI · Open source

Local AI, built around the model

Splash is our open-source inference engine for local compute. Its kernels, draft model, and memory plan are specialized for each model it serves. It runs on Apple silicon today, with more hardware coming soon.

Decode speed vs. the next-fastest engine on Qwen3.6-35B-A3B
1.7×
On Qwen3.8-27B, on the same Mac
2.0×
Single-request decode on short prompts
210tok/s

Qwen3.6-35B-A3B on a 48 GB M5 Pro, with coding prompts from NVIDIA's SPEED-Bench, as published in the Splash post

splash — zsh

brew install incoai/tap/splash splash serve --model unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M

Splash needs an M3 or newer Mac on macOS 26.4 or later, and Homebrew. This model needs at least 36 GB of unified memory.

03 · Inco Endpoints

By agreement

Dedicated throughput for your team's workload

Throughput
A committed rate of tokens per minute, sized to your workload
Service levels
Set out in an enterprise agreement
Where it runs
Dedicated capacity on our infrastructure, or on-prem
Custom models
Optional: your fine-tuned weights, at the speed and price your workload needs

An illustration of a dedicated endpoint's dashboard: a committed token throughput reserved for your team, with your traffic running under it, above 1B tokens per minute.