Cross-provider insight
Capability adoption by provider
What share of each provider's current lineup supports each capability. Greener cells mean broader adoption; gray means sparse or none.
| Provider | Active models | Vision | Function calling | Structured output | Prompt caching | Batch API | Fine-tuning |
|---|---|---|---|---|---|---|---|
| OpenAI | 69 | 32% | 32% | 30% | 25% | 0% | 10% |
| Google Gemini | 58 | 19% | 14% | 14% | 19% | 9% | 0% |
| Mistral AI | 42 | 14% | 2% | 0% | 0% | 0% | 0% |
| Cohere | 27 | 15% | 19% | 0% | 0% | 0% | 0% |
| Anthropic | 15 | 73% | 80% | 0% | 67% | 0% | 0% |
| AWS Bedrock | 14 | 36% | 36% | 0% | 0% | 7% | 14% |
| Meta | 13 | 23% | 15% | 0% | 0% | 0% | 0% |
| xAI | 9 | 33% | 44% | 33% | 33% | 0% | 0% |
| Azure OpenAI Service | 2 | 50% | 0% | 0% | 0% | 0% | 0% |
| Black Forest Labs | 2 | 50% | 0% | 0% | 0% | 0% | 0% |
| ElevenLabs | 2 | 0% | 0% | 0% | 0% | 0% | 0% |
| Runway | 2 | 50% | 0% | 0% | 0% | 0% | 0% |
| Stability AI | 1 | 100% | 0% | 0% | 0% | 0% | 0% |
How this is built
Each cell is the percentage of a provider's currently available models that support that capability — based on the most recent record we have for each model. Preview and deprecated models still count (you can still use them); retired models don't. Hubs and aggregators that don't run their own model lineup aren't included.
Updated Jun 15, 2026 17:30 UTC · Full methodology →