DeepSeek Prover V2

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

Params: 671B, 37B active
Context: 164K tokens
Released: Apr 2025
License: MIT

Hosted API pricing

How we price

Order

Providers are listed cheapest input rate first, then by output rate, a tie going to the creator's own listing. A provider that lists the model without a published rate sits at the end.

Prices

Base-tier, on-demand rates in USD per 1M tokens, converted at ECB reference rates where a provider publishes in another currency. Cached-input and batch rates show only where a provider publishes them. "Cheapest" marks the one provider with the lowest input and output pair; a tie wears no badge.

Cost

Input rate times the input tokens plus output rate times the output tokens, at the monthly volume set above the table. Cached-input, batch, long-context and reasoning-token billing are not modelled.

Transparency and funding

Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.

Every provider serving DeepSeek Prover V2, cheapest input first. Set your monthly volume to see what each would bill.

Input M Output M

Every provider serving DeepSeek Prover V2, with its price per 1M input and output tokens and what the volume above would cost
Provider	Input /1M	Output /1M	Cost at 10M in + 2M out	Link
DeepSeek Creator	Open weights, no hosted price			Visit website

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 $9,850 a month.

Single node ≤ 8

What it costs to self-host DeepSeek Prover V2 at each precision: the memory it needs, the cheapest rental that holds it, that rental's month and the API volume it pays off at
Precision	Memory	Cheapest fit (32K context)(Full 163K context)	Cost /mo
4-bit INT4 / FP4	373 GB383 GB	8× A100	$9,850$9,850
8-bit FP8 / INT8	674 GB679 GB	8× RTX PRO 6000	$12,614$12,614
16-bit FP16 / BF16	1,346 GB1,356 GB	8× B300	$45,446$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. Pricing methodology.

Thunder Compute

RTX A6000 from $0.35, A100 from $1.09, per GPU per hour

Billed per minute, no commitment, no minimums

One click into VS Code or Cursor, no SSH setup

See live pricing

Capabilities

What DeepSeek Prover V2 accepts and can do, as published by DeepSeek.

Text Accepts and generates natural-language text.

Common 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, $13.68 per hour) costs about $9,850 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 $9,850 a month on the cheapest rental that fits.