Phind

Phind was an AI answer engine and coding assistant built for developers, offering conversational, multi-step technical search on the web and through a VS Code extension. Founded in 2022 by Michael Royzen and Justin Wei (Y Combinator S22), Phind trained its own code models and briefly held the top-ranked open-source coding model on Hugging Face. The phind.com product was a consumer/subscription service and never shipped an official public or partner developer API - the only genuinely public developer artifacts were its open-weight models on Hugging Face (Phind-CodeLlama-34B v1/v2, Python-v1, and later Phind-70B). Community "Phind API" projects on GitHub and RapidAPI are unofficial reverse-engineered wrappers, not an official interface. Phind shut down on January 16, 2026; Pro subscribers received prorated refunds and could export chat history through January 30, 2026 before servers were wiped. This entry is a historical record; API surfaces are modeled, not officially documented.

Phind is listed with 1 API on the APIs.io network. Tagged areas include AI Coding Assistant, AI Search, Developer Tools, LLM, and Answer Engine.

0.0/100 minimal ▬ flat Agent 0/100 human only saas Full breakdown ↓
scored 2026-10-09 · rubric v0.23.0
AccessFreemium
1 API1 Not an API
AI Coding AssistantAI SearchDeveloper ToolsLLMAnswer EngineOpen WeightsDiscontinuedDefunctFoundation Models

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-10-09 · rubric v0.23.0
Regulatory Posture applies to this provider. Its tags matched the Horizontal (data, software, accessibility, platform) regime, so Regulatory Posture carries 15 points of the composite. If this regime is wrong for your business, say so on your provider repo — the applicability map is public and we will correct it.
Create-or-Update Ergonomics could not be measured. We hold no machine-readable contract for this provider to read, so there is nothing to measure a write surface against. Excluded rather than scored zero: never-measured and measured-empty are different facts. Publishing an OpenAPI is what makes this facet — and several others — scorable at all.
The six quality facets above are damped to 85 points between them, because the conditional facet above carries the other 15. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 85% of its nominal weight, not 100%. The full arithmetic is at apis.io/rating/.
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from github.com/api-evangelist/phind: open an issue to ask a question, or submit a pull request to add artifacts. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

APIs 2

Individual APIs this provider publishes. MODELED: a real API behind a partner or contract gate; there is no public reference, so API Evangelist drew its shape. NOT AN API: a product area with no API behind it, not counted.

Phind AI Answer Engine

Conceptual (modeled) surface for Phind's AI answer engine - the developer-focused conversational search that powered phind.com and the VS Code extension. Phind never published a...

NOT AN API

Phind Open-Weight Models

Phind's genuinely public developer artifacts - open-weight models published to the Phind organization on Hugging Face. These include the code models Phind-CodeLlama-34B-v1, Phin...

MODELED, NO PUBLIC REFERENCE

Pricing Plans 1

Published pricing tiers and plan structures.

Phind Plans Pricing

5 plans

PLANS

Resources

Commercial 1

Pricing, plans, and the legal terms of use

Company 3

The organization behind the API

Other 1

Properties that don't map to a standard resource type

Source (apis.yml)

apis.yml Raw ↑
aid: phind
url: https://raw.githubusercontent.com/api-evangelist/phind/refs/heads/main/apis.yml
name: Phind
kind: company
description: Phind was an AI answer engine and coding assistant built for developers, offering conversational, multi-step
  technical search on the web and through a VS Code extension. Founded in 2022 by Michael Royzen and Justin Wei (Y Combinator
  S22), Phind trained its own code models and briefly held the top-ranked open-source coding model on Hugging Face. The phind.com
  product was a consumer/subscription service and never shipped an official public or partner developer API - the only genuinely
  public developer artifacts were its open-weight models on Hugging Face (Phind-CodeLlama-34B v1/v2, Python-v1, and later
  Phind-70B). Community "Phind API" projects on GitHub and RapidAPI are unofficial reverse-engineered wrappers, not an official
  interface. Phind shut down on January 16, 2026; Pro subscribers received prorated refunds and could export chat history
  through January 30, 2026 before servers were wiped. This entry is a historical record; API surfaces are modeled, not officially
  documented.
deliveryModel:
  model: saas
  open_source: false
  commercial: true
  callable_host: false
  label: Hosted service · you call their endpoint
  confidence: medium
  source:
  - pricing
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: freemium
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Freemium
  confidence: medium
  source:
  - plans
  generated: '2026-07-22'
  method: derived
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/phind.png
tags:
- AI Coding Assistant
- AI Search
- Developer Tools
- LLM
- Answer Engine
- Open Weights
- Discontinued
- Defunct
- Foundation Models
created: '2026-07-11'
modified: '2026-07-11'
specificationVersion: '0.23'
apis:
- aid: phind:phind-ai-answer-engine
  x-published: false
  name: Phind AI Answer Engine
  tags:
  - AI Coding Assistant
  - AI Search
  - Answer Engine
  - LLM
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://www.phind.com
  endpointsModeled: true
  properties:
  - url: https://www.phind.com
    type: Website
  description: Conceptual (modeled) surface for Phind's AI answer engine - the developer-focused conversational search that
    powered phind.com and the VS Code extension. Phind never published an official public or partner developer API for this
    service; it was consumed only through the Phind web UI and editor extension. No official base URL, authentication, OpenAPI,
    or endpoint reference was ever documented. Any third-party "Phind API" on GitHub or RapidAPI is an unofficial reverse-engineered
    wrapper of the website's internal endpoints and is not represented here as official. This API is listed for discovery
    only and is marked endpointsModeled.
- aid: phind:phind-open-weight-models
  name: Phind Open-Weight Models
  tags:
  - Open Weights
  - Models
  - Code Models
  - LLM
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://huggingface.co/Phind
  endpointsModeled: true
  properties:
  - url: https://huggingface.co/Phind
    type: Documentation
  - url: https://huggingface.co/Phind/Phind-CodeLlama-34B-v2
    type: SourceCode
  description: Phind's genuinely public developer artifacts - open-weight models published to the Phind organization on Hugging
    Face. These include the code models Phind-CodeLlama-34B-v1, Phind-CodeLlama-34B-v2, and Phind-CodeLlama-34B-Python-v1
    (fine-tunes of Meta's Code Llama 34B, released August 2023 and briefly the top-ranked open-source coding models on HumanEval),
    plus the later Phind-70B, Phind-SVG, and Magic-Edit. These are downloadable model weights hosted on Hugging Face, not
    a hosted HTTP inference API operated by Phind; they can be self-hosted or run through third-party inference stacks. Listed
    as endpointsModeled because Phind exposed no official hosted inference endpoint for them.
common:
- type: Plans
  url: plans/phind-plans-pricing.yml
- type: LinkedIn
  url: https://www.linkedin.com/company/phind
- type: Website
  url: https://www.phind.com
- type: HuggingFace
  url: https://huggingface.co/Phind
- type: CrunchBase
  url: https://www.crunchbase.com/organization/phind
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
x-status: defunct

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this
  • find_providersBrowse and filter every provider in the catalog.
  • get_provider_artifactsEvery artifact this provider publishes, grouped by type.
  • get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
  • get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
  • get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
  • get_provider_ratingPRO — composite, band, trend and facet scores.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This provider
curl "https://apis.io/api/v1/providers/phind"
All providers
curl "https://apis.io/api/v1/providers?limit=25"
Every operation they expose
curl "https://apis.io/api/v1/providers/phind/operations?limit=25"
How their score was established
curl "https://apis.io/api/v1/providers/phind/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.