Large Scale Inference

San Francisco Compute has partnered with Modular to create Large Scale Inference, the best priced OpenAI-compatible inference in the world. On most open source models, we're 85%+ cheaper than other options. We built LSI in close partnership with a tier-1 AI lab to help them print trillions of tokens of synthetic data, saving them tens of millions of dollars compared to the leading competitor.

The best available pricing

Unlike other providers, inference prices are market-based. The token price tracks the underlying market-based compute cost on SFC & current load. In other words, we give you the best available price.

Built for trillion-token, sensitive, multimodal use cases

LSI natively supports very large scale batch inference, with far higher rate limits & throughput than other providers. Unlike other services, we don't force you to upload petabytes of data to us. Our batch inference reads & writes to an S3-compatible object store, so your sensitive data isn't stored indefinitely on our servers. LSI natively handles multimodal use cases without forcing you to publicly share links to your content.

Bespoke enterprise support

LSI is designed for large scale, mostly enterprise, use cases. That lets us be more hands on than traditional, self-serve providers.

  • Want a deployment behind your private network?

  • Need to hit specific latency, throughput, or uptime requirements?

  • Is there a model that's performing better in your evals, but we're not serving it?

Between Modular's world-class engineering & SFC's dramatic price optimization, we'll work with you to get the best possible price & performance.

Supported models

We currently support the following models below the cost of every current provider on average. Exact prices, latency, and throughput depend on the use case & current market conditions. For a quote & technical demo, contact us.

ModelHugging Face NameSize
DeepSeek‑R1deepseek-ai/DeepSeek-R1671B
DeepSeek‑V3deepseek-ai/DeepSeek-V3671B
DeepSeek‑R1‑Distill‑Llama‑70Bdeepseek-ai/DeepSeek-R1-Distill-Llama-70B70B
Llama‑3‑70B‑chatmeta-llama/Llama-3-70b-chat-hf70B
Llama‑3.1‑405B‑Instructmeta-llama/Meta-Llama-3.1-405B-Instruct405B
Llama‑3.1‑70B‑Instructmeta-llama/Meta-Llama-3.1-70B-Instruct70B
Llama‑3.1‑8B‑Instructmeta-llama/Meta-Llama-3.1-8B-Instruct8B
Llama‑4‑Scout‑17B‑Instructmeta-llama/Llama-4-Scout-17B-16E-Instruct109B
Llama‑4‑Maverick‑17B‑128E‑Instructmeta-llama/Llama-4-Maverick-17B-128E-Instruct400B
Llama 3.2 Visionmeta-llama/Llama-3.2-11B-Vision-Instruct11B
Mistral‑7B‑Instructmistralai/Mistral-7B-Instruct-v0.17B
Mixtral‑8x7B‑Instructmistralai/Mixtral-8x7B-Instruct-v0.156B
Mistral‑Small‑24B‑Instructmistralai/Mistral-Small-24B-Instruct-250124B
Qwen‑2.5‑72B‑InstructQwen/Qwen2.5-72B-Instruct72.7B
Qwen‑2.5‑7B‑InstructQwen/Qwen2.5-7B-Instruct7B
Qwen 3‑14BQwen/Qwen3-14B14.8B
Qwen 3‑8BQwen/Qwen3-8B8.2B
QwQ‑32BQwen/QwQ-32B32.5B
InternVL3‑9BOpenGVLab/InternVL3-9B9B
InternVL3‑14BOpenGVLab/InternVL3-14B14B
InternVL3‑38BOpenGVLab/InternVL3-38B38B
InternVL3‑78BOpenGVLab/InternVL3-78B78B
Gemma‑3‑12B‑in‑chatgoogle/gemma-3-12b-it12B
Gemma‑3‑27B‑in‑chatgoogle/gemma-3-27b-it27B

Need a custom setup? Contact Us

© 2025 San Francisco Compute
PrivacyTerms
made with 💙 in SF