DeepSeek R1 Turbo

Estimated cost to self-host

DeepSeek R1 Turbo 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.

That costs the same as roughly 10B tokens a month on Novita's API. Self-hosting is more expensive below that volume.

32K context Full 64K context

Single node ≤ 8

Precision	Memory	Cheapest fit (32K context)(Full 64K context)	Cost /mo	Break-even vs API
4-bitINT4 / FP4	373 GB376 GB	8× A100 8× A100	$10,138$10,138	10B tokens /mo10B tokens /mo
8-bitFP8 / INT8	674 GB675 GB	8× RTX PRO 6000 8× RTX PRO 6000	$12,672$12,672	13B tokens /mo13B tokens /mo
16-bitFP16 / BF16	1,346 GB1,349 GB	8× B300 8× B300	$45,446$45,446	45B tokens /mo45B tokens /mo

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. Break-even assumes a 5:1 input-to-output ratio. No guarantee of runtime support, usable performance, or that a matching quantized build exists. How we estimate costs.

Similarly priced models

The models nearest DeepSeek R1 Turbo by blended rate, each at its own cheapest provider.

Model	Blended /1M	Input /1M	Output /1M	Context	Cutoff	vs DeepSeek R1 Turbo
Gemini 3 Flash Preview Google Cloud	$0.9167	$0.50	$3.00	1M	Jan 2025	−8%
Qwen3.6-Plus Alibaba Cloud	$0.9167	$0.50	$3.00	1M		−8%
GLM-5.2 Z.AI	$0.95	$0.70	$2.20	1M		−5%
Nemotron 3 Ultra 550B A55B Nvidia	$0.99	$0.66	$2.64	1M	Sep 2025	−1%
DeepSeek R1 DeepSeek	$1.00	$0.70	$2.50	128K		0%
DeepSeek R1 Turbo This model DeepSeek	$1.00	$0.70	$2.50	64K
Llama 3 70B Meta	$1.00	$0.65	$2.75	8K	Dec 2023	0%
Qwen3-VL-235B-A22B Thinking Alibaba Cloud	$1.00	$0.40	$4.00	262K		0%
Kimi K2.6 Moonshot AI	$1.0333	$0.60	$3.20	262K		+3%
Grok Build 0.1 xAI	$1.1667	$1.00	$2.00	256K		+17%
Command A+ Cohere	$1.20	$0.80	$3.20	128K		+20%

Prices are USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.

Frequently Asked Questions

What is DeepSeek R1 Turbo good for?

Reasoning work through Novita AI's own build of DeepSeek R1, which it says is tuned for speed. The same MIT-licensed weights as standard R1, and the same multi-GPU node to run them yourself.

When is DeepSeek R1 Turbo not a good fit?

Long-context work: its window is shorter than standard R1's. No function calling or structured output, and it is text only.

What is the cheapest way to run DeepSeek R1 Turbo?

Hosted, unless you push serious volume. Novita charges $0.70 in / $2.50 out per 1M tokens. The cheapest rental that fits is 8x A100 at $10,138 a month, which costs the same as about 10B tokens a month on that API.

Can I self-host DeepSeek R1 Turbo?

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	Cutoff	Input /1M	Output /1M
DeepSeek R1 Open weights	128K		$0.70	$2.50
DeepSeek R1 Distill Llama 70B Open weights	131K		$0.80	$0.80
DeepSeek V4 Flash Vision Exp	1M		$0.44	$1.32
DeepSeek V3 Turbo Open weights	64K		$0.40	$1.30
DeepSeek V4 Pro Open weights	1M		$0.45	$0.89
DeepSeek V4.1 Flash Open weights	1M		$0.30	$1.20
DeepSeek V3 Open weights	128K		$0.27	$1.12
DeepSeek V3.1 Open weights	131K		$0.27	$1.00