Milliseconds.ai vs Soup CLI: Features, Pricing & Which Is Better (2026)
A side-by-side comparison of Milliseconds.ai and Soup CLI — features, pricing, and ideal use cases — to help you decide which AI tool fits your workflow.
Milliseconds.ai
CloudRaker
A small decision model served over a REST API that returns typed labels, scores, spans, and JSON fields from text or images in milliseconds.
Key features
- Typed Decision Endpoints: Eight purpose-built routes — yes-no, classify, classify-tree, rate, answer, extract, entities, and verify — each returning structured JSON rather than free text, so application code can branch on the result immediately.
- Sub-Second Latency: A decision returns in about 90 milliseconds, answer calls in 0.3–0.9 seconds, and extraction in 2.5–3.5 seconds at medium detail, making the model usable inside request paths rather than background jobs.
- Calibrated Probabilities: Responses include per-label probabilities and a confidence value, so near-ties surface as uncertainty your application can route to a human instead of acting on silently.
- Schema-Driven Extraction: Send a JSON Schema and get back a filled object — up to five fields per extract call — ready for validation before writing to a record.
- Image Input: Send JPEG, PNG, or WebP images up to 5 MB as bytes, a data URL, or base64, billed as a fixed token count set by the detail level you request, with no image storage retained.
- Answer Spans with Offsets: The answer capability returns the exact text span plus start and end offsets, so an application can highlight where in the source the answer came from.
- SDKs and CLI: Hand-written TypeScript (@cloudraker/milliseconds) and Python (cloudraker-milliseconds) SDKs plus a dm1 CLI, where label names, scale levels, and schemas flow into the result type so a misspelled label is a compile error.
- Free Test Tier: Test keys carry 125 million free input tokens a month with no card required, at 30 requests and 500,000 input tokens per minute, shared across an organization.
Best for
- Support Ticket Routing: Classifying inbound messages into billing, shipping, or technical queues and flagging urgent ones for faster response.
- Invoice and Receipt Processing: Extracting invoice number, vendor, total, and currency from document text or images into validated fields before writing a record.
- Content Moderation and Policy Checks: Verifying whether a return request, listing, or submission satisfies a written policy before it reaches a human reviewer.
- Sentiment and Priority Scoring: Rating customer frustration on a defined scale to sort a support queue by how badly each thread needs attention.
- Entity Recognition in Records: Pulling people, organizations, claim IDs, and dates out of free-text notes for search and record matching.
- Agent Tool Calls: Giving an LLM agent a fast, cheap decision primitive for yes/no and classification steps that do not need a generative model.
S
Soup CLI
MePlay, Inc.
Open-source CLI that runs the whole LLM post-training stack — SFT, DPO, ORPO — on a 4GB laptop GPU.
Key features
- Whole Post-Training Stack: SFT, DPO, ORPO, SimPO, KTO, and more in one CLI.
- Low-VRAM Streaming: Fine-tune Llama-3.1-8B on a 4 GB GPU by streaming the base from RAM/NVMe.
- Auto-Configured Runs: Task, LR, epochs, and quantization derived from rules instead of grid search.
- Self-Healing Training: Detects and self-corrects reward hacking mid-run.
- One-Command Migration: `soup migrate` converts LLaMA-Factory, Axolotl, and Unsloth configs.
- Ship Gate: Every checkpoint is evaluated and either passes or is rejected before saving.
- Broad Ecosystem: Integrates with HuggingFace, Ollama, vLLM, DeepSpeed, Unsloth, ONNX, TensorRT, W&B.
- MLX + Apple Adapter: First-class Apple silicon support.
Best for
- Fine-tuning open-source LLMs on a consumer laptop GPU
- Post-training alignment (DPO/ORPO) without a rented A100
- Migrating existing LLaMA-Factory / Axolotl pipelines to a simpler workflow
- Producing evaluated, ship-gated checkpoints for internal deployment
- Researchers experimenting with 23 training methods without rewriting scripts