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 modelsVisionFunction callingStructured outputPrompt cachingBatch APIFine-tuning
OpenAI 6932%32%30%25%0%10%
Google Gemini 5819%14%14%19%9%0%
Mistral AI 4214%2%0%0%0%0%
Cohere 2715%19%0%0%0%0%
Anthropic 1573%80%0%67%0%0%
AWS Bedrock 1436%36%0%0%7%14%
Meta 1323%15%0%0%0%0%
xAI 933%44%33%33%0%0%
Azure OpenAI Service 250%0%0%0%0%0%
Black Forest Labs 250%0%0%0%0%0%
ElevenLabs 20%0%0%0%0%0%
Runway 250%0%0%0%0%0%
Stability AI 1100%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 →