Get large scale batch inference with Modular & San Fransisco Compute

Get a personalized quote
View pricing

Modular has partnered with San Francisco Compute 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. San Francisco Compute 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.

Get a large scale inference quote

or schedule a 30min call instead

Thank you for your submission.

Your report has been received and is being reviewed by the Sales team. A member from our team will reach out to you shortly.

Thank you,

Modular Sales Team

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 technical demo, get a quote.

SF Compute Inference Models
Model Hugging Face Name Size Price 1M Tokens
gpt‑oss‑120b
New
 openai/gpt-oss-120b 120B $0.04 input $0.20 output
gpt‑oss‑20b
New
 openai/gpt-oss-20b 20B $0.02 input $0.08 output
Llama‑3.1‑405B‑Instruct
 meta-llama/Llama-3.1-405B-Instruct 405B $0.50 input $1.50 output
Llama‑3.3‑70B‑Instruct
 meta-llama/Llama-3.3-70B-Instruct 70B $0.052 input $0.156 output
Llama‑3.1‑8B‑Instruct
 meta-llama/Meta-Llama-3.1-8B-Instruct 8B $0.008 input $0.02 output
Llama 3.2 Vision
 meta-llama/Llama-3.2-11B-Vision-Instruct 11B $0.072 input $0.072 output
Qwen‑2.5‑72B‑Instruct
 Qwen/Qwen2.5-72B-Instruct 72B $0.065 input $1.25 output
Qwen2.5-VL 72B
 Qwen/Qwen2.5-VL-72B-Instruct 72B $0.125 input $0.325 output
Qwen2.5-VL 32B
 Qwen/Qwen2.5-VL-32B-Instruct 32B $0.125 input $0.325 output
Qwen3 32B
 Qwen/Qwen3-32B 32B $0.05 input $0.15 output
Qwen3 A3B 30B
 Qwen/Qwen3-30B-A3B-Instruct-2507 30B $0.05 input $0.15 output
Qwen 3‑14B
 Qwen/Qwen3-14B 14B $0.04 input $0.12 output
Qwen 3‑8B
 Qwen/Qwen3-8B 8B $0.014 input $0.055 output
QwQ‑32B
 Qwen/QwQ-32B 32B $0.075 input $0.225 output
Gemma‑3‑27B‑in‑chat
 google/gemma-3-27b-it 27B $0.05 input $0.15 output
Gemma‑3‑12B‑in‑chat
 google/gemma-3-12b-it 12B $0.04 input $0.08 output
Gemma‑3‑4B‑in‑chat
 google/gemma-3-4b-it 4B $0.016 input $0.032 output
Mistral Small 3.2 2506
 mistralai/Mistral-Small-3.2-24B-Instruct-2506 24B $0.04 input $0.08 output
Mistral Nemo 2407
 mistralai/Mistral-Nemo-Instruct-2407 12B $0.02 input $0.06 output
InternVL3‑78B
 OpenGVLab/InternVL3-78B 78B $0.125 input $0.325 output
InternVL3‑38B
 OpenGVLab/InternVL3-38B 38B $0.125 input $0.325 output
InternVL3‑14B
 OpenGVLab/InternVL3-14B 14B $0.072 input $0.072 output
InternVL3‑9B
 OpenGVLab/InternVL3-9B 9B $0.05 input $0.05 output
DeepSeek‑R1
Coming Soon
 deepseek-ai/DeepSeek-R1 671B $0.28 input $1.00 output
DeepSeek‑V3
Coming Soon
 deepseek-ai/DeepSeek-V3 671B $0.112 input $0.456 output
Llama‑4‑Maverick‑17B‑128E‑Instruct
Coming Soon
 meta-llama/Llama-4-Maverick-17B-128E-Instruct 400B $0.075 input $0.425 output
Llama‑4‑Scout‑17B‑Instruct
Coming Soon
 meta-llama/Llama-4-Scout-17B-16E-Instruct 109B $0.05 input $0.25 output
Qwen3 Coder A35B 480B
Coming Soon
 Qwen/Qwen3-Coder-480B-A35B-Instruct 480B $0.32 input $1.25 output
Qwen3 A22B 2507 235B
Coming Soon
 Qwen/Qwen3-235B-A22B-Instruct-2507 235B $0.075 input $0.40 output
Kimi K2
Coming Soon
 moonshotai/Kimi-K2-Instruct 1T $0.30 input $1.25 output
GLM 4.5
Coming Soon
 zai-org/GLM-4.5 358B $0.30 input $1.10 output
GLM 4.5 Air
Coming Soon
 zai-org/GLM-4.5-Air 110B $0.16 input $0.88 output
GLM 4.5V
Coming Soon
 zai-org/GLM-4.5V 108B $0.30 input $0.90 output
No models found matching your search criteria.
Request one above

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.

The best available accuracy

Our MAX inference engine consistently outperforms other providers across key benchmarks like DocVQA, MathVista, and ChartQA on accuracy. We save you money and get you more accurate results while we do it.

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.