Multiverse Computing
Multiverse Computing, S.L. is a Donostia-San Sebastian (Spain) quantum- and AI-software company whose commercial developer surface is the CompactifAI API — an OpenAI-compatible LLM inference service serving tensor-network-compressed versions of frontier open models (Hypernova 60B, Carina 60B, Mistral Small 3.1 Slim, Whisper Large V3 Turbo Slim) alongside uncompressed third-party models (GPT-OSS 120B, GLM 5.1/5.2, Quasar 438B, Qwen 3.6 27B, Nemotron 3 Nano Omni). The API is published at api.compactif.ai with regional EU and US endpoints, documented at docs.compactif.ai, billed pay-as-you-go per million tokens, and also sold through the AWS Marketplace. The company additionally sells Singularity, a quantum and quantum-inspired optimization product for finance, energy and manufacturing, which has no public developer documentation.
Multiverse Computing publishes 6 API contracts indexed on the APIs.io network, including Audio API, Batches API, Completions API, and 3 more. Tagged areas include Artificial Intelligence, Machine Learning, Inference, Model Compression, and Quantum Computing.
The Multiverse Computing catalog on APIs.io includes 1 Spectral governance ruleset.
Multiverse Computing’s developer surface includes authentication, documentation, API reference, getting-started guide, support, engineering blog, pricing, and 25 more developer resources.
What this lets a business do 1
Business capabilities this provider's published APIs can perform, derived from its own contracts. Browse all capabilities →
Kin Score
Markets this provider is in provisional
The Kin Score Market layer reads a provider inside its market: its position, and how deep its integrations go. Depth is only comparable within a position. Provisional and unweighted: not part of the Kin Score or agent readiness.
| Market | Position | Depth | Registered MCP server | Declares compatibility |
|---|---|---|---|---|
| Quantum Computing (hardware, cloud and software) | builds-on | 26.8 (thin) | - | 1 |
Registered MCP server and declares compatibility are report only — not weighted. Undeclared means we found nothing we can read, so there is no number: we never infer integrations.
Standards implemented 2
Standards this provider implements or carries. De facto ones are profiled and measured by the API Commons; formal ones come from the standards directory and are linked by the provider's own tags. The evidence column says how each claim was established — not that it was made.
APIs 6
Individual APIs this provider publishes, each with its own machine-readable definition.
Multiverse Computing Audio API
The audio API from Multiverse Computing — 1 operation(s) for audio.
Multiverse Computing Batches API
The batches API from Multiverse Computing — 3 operation(s) for batches.
Multiverse Computing Completions API
The completions API from Multiverse Computing — 2 operation(s) for completions.
Multiverse Computing Files API
The files API from Multiverse Computing — 2 operation(s) for files.
Multiverse Computing Model info API
The Model info API from Multiverse Computing — 2 operation(s) for model info.
Multiverse Computing Responses API
The responses API from Multiverse Computing — 2 operation(s) for responses.
Agent Skills 3
Packaged agent skills for driving this provider's APIs from an AI assistant.
compactifai-audio-transcription
AGENT SKILLcompactifai-batch-inference
AGENT SKILLcompactifai-chat-completion
AGENT SKILLMultiverse Computing API pricing
Prices published by Multiverse Computing, read 2026-10-28 from docs.compactif.ai/pricing/.
| Plan | Price |
|---|---|
| carina-60b | $0.022 per 1M input tokens |
| qwen-3-8-27b | $0.09 per 1M input tokens |
| glm-5-2 | $0.17 per 1M input tokens |
| glm-5-3 | $0.20 per 1M input tokens |
| quasar-1-2-358b | $0.11 per 1M input tokens |
| quasar-438b | $0.11 per 1M input tokens |
| cai-whisper-large-v3-turbo-slim | $0,000134 per audio minute |
Plan details, limits and sources →
Billed by: 1m input tokens · FinOps profile →
Pricing Plans 2
Published pricing tiers and plan structures.
Rate Limits 1
Documented rate limits and quota policies.
Multiverse Computing Rate Limits
RATE LIMITSService Levels 1
Uptime the provider promises or reports, as SLA4OAI. Read from its own pages; APIs.io runs no monitors.
FinOps 1
Cost, billing, and metering signals for API financial operations.
Spectral Rules 1
Spectral governance rulesets for linting and validating these APIs.
Multiverse Computing API Rules
SPECTRALOpenAPI Overlays 1
Overlays applied on top of this provider's contracts. Each card says who wrote it: a document the provider publishes, or one API Evangelist derived or generated.
Multiverse Computing Compactifai Overlay
GENERATEDSecurity Posture 2
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Resources
Get Started 4
Portal, sign-up, and the first successful call
Documentation 3
Reference material describing how the API behaves
Agent Surfaces 2
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 5
Pagination, idempotency, versioning, errors, and events
Build 2
SDKs, sample code, and the tooling you integrate with
Access & Security 2
Authentication, authorization, and security posture
Operate 6
Status, limits, changes, and where to get help
Commercial 4
Pricing, plans, and the legal terms of use
Company 2
The organization behind the API
Other 2
Properties that don't map to a standard resource type
Source (apis.yml)
Multiverse Computing API — frequently asked questions
Does Multiverse Computing have an API?
Yes. APIs.io lists 6 APIs from Multiverse Computing, including Multiverse Computing Audio API, Multiverse Computing Batches API and Multiverse Computing Completions API, and 3 more.
Is there an OpenAPI specification for the Multiverse Computing API?
Yes. APIs.io indexes 6 OpenAPI specifications for Multiverse Computing, each linked for download from this page.
How do I authenticate with the Multiverse Computing API?
Multiverse Computing uses bearer-token authentication (http · 1 scheme). The details are profiled on APIs.io as Multiverse Computing Authentication.
How much does the Multiverse Computing API cost?
Multiverse Computing publishes its prices; its carina-60b plan is $0.022 per 1M input tokens as of 2026-10-28. APIs.io lists 7 pricing plans for Multiverse Computing, with each plan's price, limits and inclusions under Pricing on this page.
Is the Multiverse Computing API ready for AI agents?
Multiverse Computing has a Kin Score of 53.3 out of 100 (developing) and an Agent Readiness score of 31.6 (agent-ready), scored by API Evangelist on 2026-11-06.
Work with this as data
Every provider here is available over the APIs.io API and to AI agents over MCP.