aid: taalas
name: Taalas
description: >-
  Taalas is a Toronto-based semiconductor company building "Hardcore Models" — AI models etched
  directly into custom silicon rather than executed as software on general-purpose GPUs, under the
  tagline "The Model is The Computer." Its first product, the HC1 technology demonstrator, hard-wires
  Meta's Llama 3.1 8B into an 815mm2 / 53-billion-transistor die on TSMC's 6nm process and is publicly
  demonstrated through the ChatJimmy chatbot. Taalas exposes that silicon to developers through a
  hosted inference REST API at api.taalas.com, which publishes two OpenAPI 3.1.0 contracts: a root
  API with health, model-info and a Taalas-native /generate operation, and an OpenAI-compatible /v1
  surface with /v1/completions and /v1/chat/completions. Access is by bearer API key issued through
  an application form; applications are currently closed due to demand.
url: https://raw.githubusercontent.com/api-evangelist/taalas/refs/heads/main/apis.yml
image: https://taalas.com/h-content/uploads/2024/01/cropped-favicon-192x192.png
x-type: company
x-source: harvest:secondary-market
x-tier: profiled
x-tier-reason: enrichment
specificationVersion: '0.20'
created: '2026-08-02'
modified: '2026-08-02'
tags:
- Company
- artificial-intelligence
- ai-inference
- semiconductors
- ai-accelerator
- large-language-models
- llama
- inference-api
- openai-compatible
- hardware
- deep-tech
apis:
- name: Taalas API
  description: >-
    Taalas-native REST interface for running inference against the HC1 hardcore-model silicon. Three
    operations: a public /health probe reporting server status, queue depth and the currently loaded
    LoRA adapter; /models for model information; and /generate, the Taalas-native text-generation
    operation supporting streaming, tool calling, guided JSON/regex generation, logprobs and stop
    sequences. Authenticated with a bearer API key; only /health is reachable anonymously.
  humanURL: https://api.taalas.com/docs
  baseURL: https://api.taalas.com
  tags:
  - ai-inference
  - large-language-models
  - llama
  - inference-api
  properties:
  - type: OpenAPI
    url: openapi/taalas-inference-api-openapi.yml
  - type: Documentation
    url: https://api.taalas.com/docs
  - type: APIReference
    url: https://api.taalas.com/docs
  - type: Authentication
    url: authentication/taalas-authentication.yml
  - type: Conventions
    url: conventions/taalas-conventions.yml
  - type: ErrorCatalog
    url: errors/taalas-problem-types.yml
  - type: DataModel
    url: data-model/taalas-data-model.yml
  - type: Overlay
    url: overlays/taalas-inference-api-overlay.yaml
- name: Taalas API v1 (OpenAI-compatible)
  description: >-
    OpenAI-compatible inference surface served under /v1 on api.taalas.com, so existing OpenAI client
    libraries can be pointed at Taalas hardcore-model silicon by changing the base URL. Exposes
    /v1/models, /v1/completions and /v1/chat/completions with the familiar model, messages,
    temperature, top_p, stop, max_tokens, logit_bias, tools and stream_options parameters, plus
    multimodal text/image message content and function-calling tool definitions.
  humanURL: https://api.taalas.com/v1/docs
  baseURL: https://api.taalas.com/v1
  tags:
  - ai-inference
  - large-language-models
  - openai-compatible
  - inference-api
  properties:
  - type: OpenAPI
    url: openapi/taalas-inference-v1-api-openapi.yml
  - type: Documentation
    url: https://api.taalas.com/v1/docs
  - type: APIReference
    url: https://api.taalas.com/v1/docs
  - type: Authentication
    url: authentication/taalas-authentication.yml
  - type: Conventions
    url: conventions/taalas-conventions.yml
  - type: ErrorCatalog
    url: errors/taalas-problem-types.yml
  - type: DataModel
    url: data-model/taalas-data-model.yml
  - type: Overlay
    url: overlays/taalas-inference-v1-api-overlay.yaml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: Website
  url: https://taalas.com/
- type: DeveloperPortal
  url: https://api.taalas.com/
- type: Documentation
  url: https://api.taalas.com/docs
- type: APIReference
  url: https://api.taalas.com/v1/docs
- type: SignUp
  url: https://taalas.com/api-request-form/
- type: Support
  url: https://api.taalas.com/bug-report
- type: Blog
  url: https://taalas.com/mission-log/
- type: StatusPage
  url: https://status.taalas.com/
- type: TermsOfService
  url: https://taalas.com/terms-conditions/
- type: PrivacyPolicy
  url: https://taalas.com/privacy-policy/
- type: Products
  url: https://taalas.com/products/
- type: Careers
  url: https://taalas.com/position/
- type: Demo
  url: https://chatjimmy.ai/
- type: Authentication
  url: authentication/taalas-authentication.yml
- type: Conventions
  url: conventions/taalas-conventions.yml
- type: ErrorCatalog
  url: errors/taalas-problem-types.yml
- type: DataModel
  url: data-model/taalas-data-model.yml
- type: Lifecycle
  url: lifecycle/taalas-lifecycle.yml
- type: Conformance
  url: conformance/taalas-conformance.yml
- type: Packages
  url: packages/taalas-packages.yml
- type: WellKnown
  url: well-known/taalas-well-known.yml
- type: LLMsTxt
  url: llms/taalas-llms.txt
- type: MCPServer
  url: mcp/taalas-mcp.yml
- type: AgentSkill
  url: skills/_index.yml
- type: DomainSecurity
  url: security/taalas-domain-security.yml
- type: AgenticAccess
  url: agentic-access/taalas-agentic-access.yml
x-enrichment:
  date: '2026-08-02'
  status: enriched
  artifacts_added: 21
  pass: local-v1