All model and GPU pairings
DeepSeekv4 Pro 0813 1.6TNVIDIA Hopper

Running DeepSeek V4 Pro on H200

Quick answer

DeepSeek V4 Pro runs on H200: 100 benchmarked configs so far. See the interactivity ladder below for measured operating points.

Benchmarked configs

100

Serving engines

Dynamo SGLang, SGLang, vLLM

Precisions

fp8

Run dates

2026-07-14 β†’ 2026-09-16

Throughput at every interactivity target

Serving is a trade-off: push more concurrent users through a GPU and each user's tokens arrive slower. The ladder below reads the measured frontier at each per-user speed target on the AgentX agentic coding workload, using the best engine and precision at that point.

Per-user targetTokens/s per GPU$ / 1M tokensEnginePrecision
30 tok/s--Dynamo SGLangfp8
50 tok/s--Dynamo SGLangfp8
75 tok/s5,771$0.059Dynamo SGLangfp8
100 tok/s5,139$0.066Dynamo SGLangfp8
150 tok/s2,648$0.13Dynamo SGLangfp8
200 tok/s--Dynamo SGLangfp8

Frequently asked questions

How fast is DeepSeek V4 Pro on H200?
The InferenceX fleet has 100 benchmarked configs for this pairing; see the interactivity ladder above for the operating points reached so far.
How much does it cost to serve DeepSeek V4 Pro on H200?
Cost per million tokens is derived from measured throughput and $/GPU/hr rates from the SemiAnalysis AI Cloud TCO model; it appears once this pairing reaches the primary interactivity tier.
Which serving engines run DeepSeek V4 Pro on H200?
The runs behind this page used Dynamo SGLang, SGLang, vLLM in FP8 and multi-node serving. Engines are rebuilt and re-benchmarked continuously, so the best config can change between visits.
How are these DeepSeek V4 Pro numbers measured?
Every number is measured on real H200 hardware by the InferenceX fleet, sweeping concurrency on the AgentX agentic coding workload to trace the throughput-versus-interactivity frontier; the newest run landed on 2026-09-16. The same derivation powers the InferenceX overview leaderboard.

Explore the data