DeepSeek logo Open weights · MIT

DeepSeek Prover V2

A 671B MoE model (37B active) for formal theorem proving in Lean 4, with weights under the MIT license.

Jump to: Specs Pricing Self-hosting FAQ More from DeepSeek
Visit website Compare vs other LLMs →

Key Specifications

Context window
164K tokens
Released
Parameters
671B, 37B active
Inputs
Text

Hosted API pricing

Provider Input /1M tokens Output /1M tokens Cost at 10M in + 2M out
DeepSeek logo DeepSeek Creator Open weights, no hosted price View

Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.

Estimated cost to self-host

DeepSeek Prover V2 needs about 373 GB of GPU memory at 4-bit with 32K context. The cheapest rental that fits is 8× A100 at about $10,138 a month.

Single node ≤ 8
Precision Memory Cheapest fit (32K context) Cost /mo
4-bitINT4 / FP4
373 GB
Nvidia logo 8× A100
$10,138
8-bitFP8 / INT8
674 GB
Nvidia logo 8× RTX PRO 6000
$12,672
16-bitFP16 / BF16
1,346 GB
Nvidia logo 8× B300
$45,446

Estimates based on median on-demand rates for Nvidia GPUs. Memory is weights plus KV cache for one request, using FP8 KV cache where supported and FP16/BF16 otherwise. No guarantee of runtime support, usable performance, or that a matching quantized build exists. How we estimate costs.

Frequently Asked Questions

What is DeepSeek Prover V2 good for?

Formal theorem proving in Lean 4. MIT-licensed weights for teams running their own proof pipelines, on a multi-GPU node.

When is DeepSeek Prover V2 not a good fit?

General chat, coding or agent use: it has no tool calling, and it takes text only. Running it takes a multi-GPU node.

What is the cheapest way to run DeepSeek Prover V2?

No provider we track hosts it; self-hosting on the cheapest rental that fits (8x A100, $14.08 per hour) costs about $10,138 a month.

Can I self-host DeepSeek Prover V2?

Yes. The weights are MIT licensed. At 4-bit it needs about 373 GB of GPU memory, which starts at roughly $10,138 a month on the cheapest rental that fits.

More from DeepSeek

Model Context Input /1M Output /1M
DeepSeek DeepSeek V4 Flash Open weights 1M $0.08 $0.25
DeepSeek DeepSeek V4 Flash Vision Exp 1M $0.44 $1.32
DeepSeek DeepSeek V4 Pro Open weights 1M $0.45 $0.89
DeepSeek DeepSeek V4.1 Flash Open weights 1M $0.30 $1.20
DeepSeek DeepSeek R1 Distill Llama 70B Open weights 131K $0.80 $0.80
DeepSeek DeepSeek V3.1 Open weights 131K $0.27 $1.00
DeepSeek DeepSeek V3.1 Terminus Open weights 131K $0.27 $1.00
DeepSeek DeepSeek V3.2 Open weights 131K $0.25 $0.80