Inference
AI InferenceLLM InferenceInference APIInference
Providers using this tag (157)
Ranked by API Evangelist rating — Exemplar and Strong are expanded by default.
Exemplar 6 Complete, well-documented, and agent-ready
Strong 12 Solid coverage with minor gaps
Developing 41 Usable, with meaningful gaps to close
Thin 51 Limited public surface area
Emerging 21 Early or largely undocumented
Minimal 25 Almost no public developer surface
Unrated 1 Not yet scored
APIs with this tag (100)
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 →
Exemplar 9 Complete, well-documented, and agent-ready
Strong 18 Solid coverage with minor gaps
Developing 27 Usable, with meaningful gaps to close
Thin 34 Limited public surface area
Emerging 10 Early or largely undocumented
Companies reaching this through an API (37)
These companies publish an API, specification or operation carrying “Inference” but do not classify their business under it. Listed unranked and kept out of the count above, because one tagged operation is not a statement about what a company does.
Score breakdown
Where this tag sits
157 providers carry this tag directly, and 163 counting the 1 narrower tag below — 6 more to reach.
Related tags
Where this tag comes from
Cohort brief
Auto-generatedThe 154 providers in the APIs.io catalog tagged Inference, 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 | 42.6 | 23.2 | +19.4 | 154 |
| Contract Quality | 31.8 | 17.6 | +14.2 | 154 |
| Operational Transparency | 22.8 | 13.7 | +9.1 | 154 |
| Access Clarity | 34.8 | 26.5 | +8.3 | 154 |
| Discoverability | 66.3 | 58.1 | +8.2 | 154 |
| Contract Governance | 7.3 | 6.3 | +1 | 154 |
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) | 23% | 14% | +9 |
| MCP server (first-party) | 21% | 12% | +9 |
| Agent Skills | 0% | 0% | 0 |
| OAuth scopes | 3% | 11% | -8 |
| Security | 97% | 98% | -1 |
| Arazzo workflows | 5% | 2% | +3 |
| Governance rules | 19% | 14% | +5 |
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 Hive Civilization 74.1
- 2 Segmind 68.8
- 3 fal 68.6
- 4 Hugging Face 68
- 5 NVIDIA NIM 68
- 6 Amazon SageMaker 67.3
- 7 NexGen Cloud 65.9
- 8 Seekr 63
- 9 Cerebras Systems 59.1
- 10 Hyperbolic 57.7
- 1 brick.blue 56.6
- 2 Roboflow 54
- 3 Fastino Labs 52
- 4 fal 50.6
- 5 Replicate 50.6
- 6 Inference 47.1
- 7 NexGen Cloud 44.7
- 8 Hive Civilization 44.3
- 9 Sail 43.2
- 10 Superb AI 42.2
Work with this as data
Every tag here is available over the APIs.io API and to AI agents over MCP.