Modality
Speech-to-Text providers
Every model provider on LLMAPI tagged “Speech-to-Text” — 7 of 50 providers. All of them run through one API key and one OpenAI-compatible endpoint.
Providers listed7
Models reachable56
Filters available84
IntegrationOne OpenAI-compatible endpoint
7 providers matching this filter.
| Provider | Models | Regions | Best for | |
|---|---|---|---|---|
OpenAI GPT series, o-series reasoning models, and multimodal APIs. |
15 | US, EU | General-purpose chat, multimodal apps, and the widest tooling ecosystem | View → |
Baseten High-performance inference for open models. |
8 | US | Production inference for open models with autoscaling | View → |
Modal Serverless GPUs for custom model code. |
1 | US, EU | Running custom inference code on serverless GPUs | View → |
Fireworks Fast generative AI inference platform. |
10 | US, EU | High-speed OpenAI-compatible inference for open models | View → |
Replicate Run thousands of community models via API. |
5 | US | Prototyping with thousands of community models | View → |
DeepInfra Low-cost inference for popular open models. |
8 | US | Popular open models at the lowest per-token cost | View → |
Groq LPU hardware for ultra-low-latency inference. |
9 | US, EU | Ultra-low-latency inference for real-time apps | View → |
One key, every provider on this page
Consolidated billing, spend limits and instant fallback between providers.