--- title: Run the best open-source models. One Inference API. canonical: https://telnyx.com/products/inference --- # Run the best open-source models. One Inference API. English # Serverless inference. A curated library of leading open-weight models, hosted on GPUs we own. OpenAI-compatible, in-region compute, zero data retention, with no infrastructure to manage. Up to 75% less than proprietary alternatives. [Start Building](https://telnyx.com/sign-up)[CONTACT US](https://telnyx.com/contact-us) AGENT RUNTIME ## Frontier models hosted on in-region GPUs Hosted models are chosen deliberately. Each one is the best at something real: high-throughput reasoning, cost-efficient intelligence at scale, and real-time interactive workloads. For the current lineup, see telnyx.com/pricing/inference-api. Loading... **WHY TELNYX** ## The shift to open-weight Open-weight models have caught up with models from frontier labs. Same quality, fraction of the cost. Telnyx hosts models on GPU infrastructure we own, so there's no cloud provider markup in your per-token price. Switch workloads from the frontier and save up to 75%, no compromise on quality, no vendor lock-in. * ### Ultra-low latency Run state-of-the-art models on GPUs colocated with the network that serves your users. Inference happens in-region across the Americas, Europe, MENA, and APAC, so data stays where your users are with zero data retention. No inter-provider hops, no cross-border routing, no training on your data. * ### Cut costs, gain flexibility Save up to 75% vs proprietary models with OpenAI compatible endpoints that work with existing SDKs, so you can switch models easily without rewriting code. * ### Autoscaling by default Go from 0 to 1000s of requests per second without planning around available capacity. Pay only for what you use. **SERVICE TIERS** ## Route each request based on latency requirements A single parameter on each request controls serving capacity and price. Set service\_tier to flex, default, or priority on any chat completion call. Omit the field and you get Default. Same model IDs, same synchronous API, no new endpoints to integrate. * ### Default Standard serving capacity at standard rates. This is what every existing inference call already uses. All published pricing comparisons and benchmark results refer to Default tier. Omit service\_tier and this is what you get. * ### Priority Serving capacity optimized for low-latency interactive workloads, including voice orchestration. Priority does not change the model or the context window. It selects faster serving capacity at a different rate. Live on select models today, more models and regions coming soon. * ### Flex Lowest rates, optimized for throughput where minutes of end-to-end latency is acceptable. Flex is for background work: offline evaluation, document processing, background summarization. All requests remain synchronous. Available in US on select models. [See pricing](https://telnyx.com/pricing/inference-api) FEATURES ## Production-ready inference APIs OpenAI-compatible endpoints that work with your existing SDK and deploy globally. * In-region deployment Inference runs in the Americas, Europe, MENA and APAC with LATAM coming soon. Your data stays where your users are, and stays private. * OpenAI-compatible API Save up to 75% on your inference bills using your existing OpenAI SDK by changing the base URL to access open-source models. * Priority tiers Tiers run on Telnyx-hosted models, so you change one field in the request body rather than adding a second inference provider. * Autoscaling Owned GPU infrastructure handles concurrent requests and scales automatically with your workload. No capacity planning, no cold starts. * Vendor flexibility Access leading open-weight models from z.ai, DeepSeek, Minimax and more as they launch. * Structured output JSON mode and regex constraints ensure inference output conforms to your schema for production-grade reliability. HOW IT WORKS ## Migrate in minutes OpenAI-compatible. Change your base URL, that's it. [EXPLORE DEV DOCS](https://developers.telnyx.com) cURL ``` curl -i -X POST "https://api.telnyx.com/v2/ai/chat/completions" \ -H "Authorization: Bearer $TELNYX_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "moonshotai/Kimi-K3", "messages": [{"role": "user", "content": "Hello, World!"}] }' ``` **PRICING** ## Structural pricing, not stacked margins Up to 75% less than proprietary alternatives. Cached input at up to 88% off. No GPU rental fees, no compute surcharges, no minimums. Per-token rates vary by model and service tier. 75% savings vs frontier labs [See pricing](https://telnyx.com/pricing/inference-api) PRODUCTS ## Building AI that reaches beyond the chat? Your AI doesn't have to stop at text. Telnyx runs text-to-speech, voice AI, and telephony on the same infrastructure. Same API key, same network, same bill. [See all products](https://telnyx.com/products) * ### Cloud Storage Discover low-latency, cost-effective storage for your AI applications. Store data and embeddings in one place. [Learn more](https://telnyx.com/products/cloud-storage) * ### Voice AI Agents Build and deploy low-latency Voice AI agents in minutes on a full-stack, conversational AI platform. Take control of voices, languages, and call flows. [Learn more](https://telnyx.com/products/voice-ai) * ### Text-to-Speech One API for leading voice engines. Access ElevenLabs, MiniMax, Resemble AI, and others without lock-in. [Learn more](https://telnyx.com/products/text-to-speech-api) * ### Model Library Choose from a range of state-of-the-art proprietary and open-source LLMs and stay on the bleeding edge of AI. [Learn more](https://telnyx.com/llm-library) ## Sign up and start building. Test frontier models running on edge compute. Telnyx gives you the infrastructure and support to deploy inference workloads globally from one platform. [SIGN UP](https://telnyx.com/sign-up)[TALK TO US](https://telnyx.com/contact-us) ## Sign up and start building. Test frontier models running on edge compute. Telnyx gives you the infrastructure and support to deploy inference workloads globally from one platform. [SIGN UP](https://telnyx.com/sign-up)[TALK TO US](https://telnyx.com/contact-us) ## FAQ ### What is an inference API? An inference API lets your application send prompts over HTTP and receive model outputs (text, tool calls, or embeddings) without managing GPU hardware yourself. Telnyx Inference runs a curated frontier of open-source models on Telnyx-owned GPUs, with [OpenAI-compatible](https://developers.telnyx.com/docs/inference/openai) chat completions, autoscaling, and per-token billing. Use it when you need production model serving behind a standard API rather than a chat UI. ### Is the Telnyx Inference API OpenAI-compatible? ### How much does the Telnyx Inference API cost? ### Which models can I run on the Telnyx Inference API? ### How does Telnyx Inference handle regions and latency? ### Does Telnyx retain or train on Inference API data? ### What is AI inference vs training? ### Does the Inference API support embeddings, tools, and structured JSON? [Start building](https://telnyx.com/sign-up)