Large Language Models
Large Language Modelslarge-language-models
Providers using this tag (67)
Ranked by API Evangelist rating — Exemplar and Strong are expanded by default.
Exemplar 1 Complete, well-documented, and agent-ready
Strong 7 Solid coverage with minor gaps
Developing 24 Usable, with meaningful gaps to close
Thin 11 Limited public surface area
Emerging 14 Early or largely undocumented
Minimal 10 Almost no public developer surface
APIs with this tag (18)
Ranked by the provider's API Evangelist rating — the Kin Score is scored per provider, not per API, so every API of a provider shares its band. How the rating works →
Strong 8 Solid coverage with minor gaps
Developing 4 Usable, with meaningful gaps to close
Thin 4 Limited public surface area
Emerging 2 Early or largely undocumented
Score breakdown
Related tags
Where this tag comes from
Cohort brief
Auto-generatedThe 67 providers in the APIs.io catalog tagged Large Language Models, scored on the Kin Score. Every figure below is computed from the catalog — nothing here is written.
| Facet | This cohort | Catalog | Difference | Scored |
|---|---|---|---|---|
| Developer Ergonomics | 40 | 17.9 | +22.1 | 67 |
| Contract Quality | 35.5 | 17.5 | +18 | 67 |
| Operational Transparency | 21.8 | 11.3 | +10.5 | 67 |
| Access Clarity | 32.2 | 22.3 | +9.9 | 67 |
| Discoverability | 67.3 | 60.4 | +6.9 | 67 |
| Contract Governance | 9.9 | 6.4 | +3.5 | 67 |
A facet is averaged over the members that carry it, not over the whole cohort — the “Scored” column is that count. Averaging an absent facet as zero would score our own coverage gaps as the providers’ posture.
| Artifact | This cohort | Catalog | Difference |
|---|---|---|---|
| MCP server (any) | 33% | 16% | +17 |
| MCP server (first-party) | 10% | 7% | +3 |
| Agent Skills | 0% | 0% | 0 |
| OAuth scopes | 9% | 9% | 0 |
| Security | 100% | 88% | +12 |
| Arazzo workflows | 10% | 2% | +8 |
| Governance rules | 24% | 13% | +11 |
mcp_pct counts any mcp/ artifact including ones API Evangelist derived from the provider OpenAPI; mcp_first_party_pct counts only servers the provider publishes. Prefer the latter.
- 1 Anthropic 68.6
- 2 OpenAI 64.2
- 3 Cerebras Systems 63.8
- 4 IBM 62.6
- 5 Meta 60.9
- 6 Amazon Web Services (AWS) 60.6
- 7 Perplexity 56.3
- 8 Claude 54.4
- 9 Unify 52.1
- 10 H2O.ai 51.9
- 1 H2O.ai 46.9
- 2 IBM 39.4
- 3 Anthropic 38.1
- 4 Meta 37.8
- 5 OpenAI 37.7
- 6 Textcortex 37.2
- 7 Uniphore 34.9
- 8 LangChain 31.7
- 9 Smithery 31.5
- 10 Aleph Alpha 29.9
Work with this as data
Every tag 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 tags
7 MCP tools reach this
find_tagsBrowse and filter every tag in the catalog.get_cohortThis tag as a scored cohort — every provider carrying it, with scores.cohort_statsPRO — the distribution across this tag: mean, median, band split, adoption rates.cohort_rankingsPRO — the leaderboard, on composite AND agent-readiness axes.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.
Call it yourself
curl for this page
curl "https://apis.io/api/v1/tags/large-language-models"
curl "https://apis.io/api/v1/tags?limit=25"
curl "https://apis.io/api/v1/cohorts/tag/large-language-models"
curl "https://apis.io/api/v1/cohorts/tag/large-language-models/stats" \
-H "X-API-Key: $APIS_IO_KEY"
Discovery needs no key. Ratings and market analysis are Pro.