Where models run — clouds (Bedrock, Vertex), GPU providers, inference platforms (Together, Fireworks, Baseten, Modal), self-hosted serving (vLLM).
36 verified facts across 27 companies
Together AI Runs a custom SSM inference engine for real-time voice.
Receipts · 1
“To support these requirements — and serve millions of audio minutes daily — Cartesia uses Together AI.” — together.ai, Jul 2026
Source last verified Jul 27, 2026
Modal Runs computational biology workflows from research through production.
Receipts · 2
“With Modal, building infrastructure has shifted from being an imperative task to a declarative one.” — modal.com, Jan 15, 2026
“With Modal Volumes it’s downloaded once, instantly available everywhere, and scales to thousands of queries.” — modal.com, Jan 15, 2026
Source last verified Jul 27, 2026
Fireworks AI Serves low-latency LLMs for real-time contact center applications.
Receipts · 1
“The low-latency, high-throughput serving of LLMs has been particularly valuable, as latency is crucial for our real-time applications.” — fireworks.ai, Dec 8, 2024
Source last verified Jul 27, 2026
Fireworks AI Inference host serving Cursor's custom fine-tuned models.
Receipts · 4
“Fireworks deployed Cursor's special fine-tune of Llama-3-70b for the coding task 'Fast Apply' using the speculative API flag.” — fireworks.ai, Jun 23, 2024
“Fireworks provides the inference layer that makes these RL loops practical.” — fireworks.ai, Jun 26, 2026
“host their own custom models on Fireworks” — simonwillison.net, May 11, 2025
“We'd also like to thank Fireworks and Colfax for their collaboration and partnership.” — cursor.com, Mar 27, 2026
Source last verified Jul 27, 2026
Receipts · 2
“We are very much a 'cloud shop.' We mostly rely on AWS and then Azure for inference.” — newsletter.pragmaticengineer.com, Jun 10, 2025
“AWS for primary infrastructure, Azure and GCP for "some secondary infrastructure"” — simonwillison.net, May 11, 2025
Source last verified Jul 26, 2026
Together GPU Clusters
by Together AI Runs production inference on dedicated NVIDIA Blackwell GPU clusters.
Receipts · 1
“Cursor partnered with Together AI to deploy production inference on NVIDIA Blackwell” — together.ai, Jul 2026
Source last verified Jul 27, 2026
Modal Trains and serves real-time voice AI models at scale.
Receipts · 1
“Modal’s infrastructure powered this progress, enabling Decagon to train and serve increasingly capable models” — modal.com, Nov 13, 2025
Source last verified Jul 27, 2026
Together AI Runs low-latency production inference for the voice stack.
Receipts · 1
“Decagon uses Together’s inference engine as the execution layer” — together.ai, Jul 2026
Source last verified Jul 27, 2026
Together AI Hosts the full Cogito model lineup on dedicated infrastructure.
Receipts · 1
“Together hosts the full Cogito model lineup, from 3B to 671B parameters, on dedicated inference infrastructure.” — together.ai, Jul 2026
Source last verified Jul 27, 2026
Fireworks AI Delivers reliable inference and rapid model access for agents.
Receipts · 1
“Fireworks supports us by having these models available on basically day zero, typically well ahead of most other inference providers.” — fireworks.ai, Jun 26, 2026
Source last verified Jul 27, 2026
Fireworks AI Primary inference layer for the DarcyIQ multi-agent platform.
Receipts · 1
“the company moved its DarcyIQ platform to Fireworks AI as its primary inference layer.” — fireworks.ai, May 5, 2026
Source last verified Jul 27, 2026
Provides centralized low-latency model access for GenAI use cases company-wide.
Receipts · 1
“manage and operate Klarna's AI Gateway, ensuring reliable, low-latency access to AI models at scale” — jobsinforex.com, Jul 21, 2026
Source last verified Jul 26, 2026
Fireworks AI Hosts and serves fine-tuned and open-weight models for low-latency features.
Receipts · 2
“By fine-tuning models, we reduced latency from about 2 seconds to 350 milliseconds” — fireworks.ai, Jul 25, 2025
“Service provider for hosting large language models and embeddings” — registora.com, Jul 9, 2026
Source last verified Jul 26, 2026
Anyscale (Ray)
by Anyscale Runs the near-real-time embeddings indexing pipeline on managed Ray.
Receipts · 3
“we set out to migrating our near real-time embeddings pipeline to Ray running on Anyscale” — notion.com, Feb 19, 2026
“Ray lets us run open-source embedding models directly, without being gated by external providers” — notion.com, Feb 19, 2026
“pull a model from Hugging Face and run it ourselves on-prem” — anyscale.com, Jul 2026
Source last verified Jul 26, 2026
Custom Rust and CUDA engine serving every query across a multi-cloud GPU fleet.
Receipts · 2
“We build and run the inference engine behind every Perplexity query and deploy dozens of model architectures at scale” — jobs.ashbyhq.com, Apr 13, 2026
“a large GPU fleet spread across several cloud providers” — jobs.ashbyhq.com, Jul 16, 2026
Source last verified Jul 26, 2026
TensorRT-LLM
by NVIDIA Served LLMs on GPU pods before the in-house engine took over.
Receipts · 2
“Triton Inference Server is a critical component of Perplexity's deployment architecture.” — developer.nvidia.com, Dec 5, 2024
“Our stack is Rust, Python, CUDA, and CuTe DSL” — jobs.ashbyhq.com, Apr 13, 2026
Source last verified Jul 26, 2026
Cerebras Inference
by Cerebras Wafer-scale inference serving the Sonar model for near-instant answers.
Receipts · 1
“1,200 tokens per second, delivering near-instant answer generation” — cerebras.ai, Feb 11, 2025
Source last verified Jul 26, 2026
Open-sourced RDMA library powering disaggregated serving of large MoE models.
Receipts · 2
“KvCache transfer for disaggregated inference with dynamic scaling” — arxiv.org, Oct 31, 2025
“Perplexity open source garden for inference technology” — github.com, Nov 4, 2025
Source last verified Jul 26, 2026
Modal Runs real-time remote inference for robotic control.
Receipts · 1
“On Modal, PI can allocate larger, data-center-class GPUs per deployment and run GPU-intensive experiments immediately.” — modal.com, Apr 8, 2026
Source last verified Jul 27, 2026
Modal Powers the Ramp Inspect background coding agent.
Receipts · 2
“Ramp uses Modal to power Ramp Inspect” — modal.com, Feb 19, 2026
“Leveraging Modal Sandboxes, Ramp spins up full development environments in seconds,” — modal.com, Feb 19, 2026
Source last verified Jul 27, 2026
Modal Scales GPU inference for multi-model document processing.
Receipts · 1
“Reducto continues to expand its use of Modal with the deployment of new large language and vision-language models.” — modal.com, Nov 19, 2025
Source last verified Jul 27, 2026
Together GPU Clusters
by Together AI Provides on-demand GPU capacity for rapid model deployment.
Receipts · 1
“Together provides immediate access to NVIDIA H100s, H200s, and B200s without long-term commitments.” — together.ai, Jul 2026
Source last verified Jul 27, 2026
Fireworks AI Powers multi-agent chat and search with high-concurrency inference.
Receipts · 1
“It was running on Fireworks.” — fireworks.ai, Jul 17, 2025
Source last verified Jul 27, 2026
Vertex AI
by Google Cloud Serves Claude models for Sidekick at merchant scale.
Receipts · 1
“The combination of Claude and Vertex AI helps us empower millions of merchants with our AI-enabled commerce assistant, Sidekick” — cloud.google.com, Feb 5, 2026
Source last verified Jul 26, 2026
Triton Inference Server
by NVIDIA Self-hosts fine-tuned vision models across the GPU fleet.
Receipts · 2
“Orchestrates model serving across our GPU fleet, handling request preprocessing, batching, and routing” — shopify.engineering, Jul 16, 2025
“40 million LLM calls daily, representing about 16 billion tokens inferred per day” — shopify.engineering, Jul 16, 2025
Source last verified Jul 26, 2026
Receipts · 1
“Artificial intelligence services” — help.shopify.com, Jul 2026
Source last verified Jul 26, 2026
Fireworks AI Provides scalable model inference for real-time code assistance.
Receipts · 1
““Fireworks has been a fantastic partner in building AI dev tools at Sourcegraph.” — fireworks.ai, Jan 22, 2025
Source last verified Jul 27, 2026
Vercel AI Gateway
by Vercel Provides scalable model access with high throughput limits.
Receipts · 1
“leveraging AI Gateway for AI scalability and large TPM limits” — vercel.com, Feb 17, 2026
Source last verified Jul 27, 2026
Modal Runs ML training and deployment, replacing AWS SageMaker.
Receipts · 1
“For nearly all these models Substack has moved both training and deployment from AWS SageMaker to Modal.” — modal.com, May 20, 2024
Source last verified Jul 27, 2026
Together AI Serves open models behind a public AI journalism platform.
Receipts · 1
“They deployed open models on Together AI with dedicated endpoints and hybrid serverless capacity, maintaining full model control and predictable pricing.” — together.ai, Jul 2026
Source last verified Jul 27, 2026
Fireworks AI Primary inference layer for internal agentic workflow deployments.
Receipts · 1
“Over time, Fireworks became the primary inference layer for internal deployment testing and early production workloads.” — fireworks.ai, Jun 2026
Source last verified Jul 27, 2026
Fireworks AI Runs v0 composite and Auto Fix models with speculative decoding.
Receipts · 1
“Both Vercel’s Auto Fix model and its v0 composite model uses Fireworks’ Speculative Decoding to speed up token generation.” — fireworks.ai, Nov 3, 2025
Source last verified Jul 27, 2026
Together AI Deploys custom computer vision models via load-balanced inference.
Receipts · 1
“Together provides auto-scaling that monitors response latency and queue depth, enabling instant scaling without pre-provisioning.” — together.ai, Jul 2026
Source last verified Jul 27, 2026
Together AI Serves fine-tuned models as endpoints for structured extraction.
Receipts · 1
“Together AI turned fine-tuning, evaluations, and deployment into a repeatable loop from experimentation to generating a testable endpoint” — together.ai, Jul 2026
Source last verified Jul 27, 2026
Together AI Serves browser-use agents behind Scouts, Delegate, and Navigator.
Receipts · 1
“Yutori runs on Together AI, the AI Native Cloud” — together.ai, Jul 2026
Source last verified Jul 27, 2026
