What is DeepSeek V4 Flash good for?

Long-context agent and coding work. It is the cheapest of DeepSeek's chat models, and its MIT weights need about 170 GB at 4-bit to self-host, far less than V4 Pro.

When is DeepSeek V4 Flash not a good fit?

Image input, which DeepSeek offers only through the separate V4 Flash Vision Exp variant. DeepSeek's own API charges the list rate at peak hours, so the price depends on time of day.

What is the cheapest way to run DeepSeek V4 Flash?

Hosted, unless you push serious volume. DeepSeek charges $0.44 in / $1.32 out per 1M tokens. The cheapest rental that fits is 8x RTX 3090 at $749 a month, which costs the same as about 1B tokens a month on that API.

Can I self-host DeepSeek V4 Flash?

Yes. The weights are MIT licensed. At 4-bit it needs about 166 GB of GPU memory, which starts at roughly $749 a month on the cheapest rental that fits. See the table above for 8-bit and 16-bit.

Open weights · MIT

DeepSeek V4 Flash

DeepSeek's lightweight 284B MoE (13B active) under the MIT license, previewed April 2026 and released as DeepSeek-V4-Flash-0731 in July 2026 with gains in agentic and coding work.

Visit website Compare vs other LLMs →

Jump to: Specs Pricing Self-hosting Similar models FAQ More from DeepSeek

List price via DeepSeek

Input: $0.44 / 1M tokens
Output: $1.32 / 1M tokens

Cheapest: $0.14 / $0.28 per 1M tokens via Novita

6 providers

Key Specifications

Context window: 1M tokens
Max output: 384K tokens
Released: Apr 2026
Parameters: 284B, 13B active
Inputs: Text

Capabilities Show details: Reasoning Thinks before it answers, always on or as a switchable mode. Function calling Connect to external tools, APIs, and systems. Structured output Return responses in structured formats like JSON. Web search Search the web for up-to-date information.

Hosted API pricing

Input tokens M Output tokens M

Provider	Input / 1M tokens	Output / 1M tokens	Cached input / 1M	Cost at 10M in + 2M out
Novita	$0.14	$0.28		$1.96	View
Together AI	$0.14	$0.28	$0.03	$1.96	View
Geodd	$0.14	$0.30		$2.00	View
GPUhub	$0.15	$0.30		$2.10	View
Lyceum	$0.15	$0.30		$2.10	View
DeepSeek Creator	$0.44	$1.32		$7.04	View

Heads up: Prices are estimates using base-tier, on-demand rates per 1M tokens from published pages; cached, batch and long-context tiers are shown only where listed. Providers may serve a shorter context or a quantized build than the creator's release. Verify with the provider before provisioning. How we estimate costs.

Estimated cost to self-host

DeepSeek V4 Flash needs about 166 GB of GPU memory at 4-bit. The cheapest rental that fits is 8× RTX 3090 at about $749 a month.

That costs the same as roughly 1B tokens a month on DeepSeek's API. Self-hosting is more expensive below that volume.

Precision	Cheapest, 1x concurrency	Cheapest, 8x concurrency
4-bit	8× RTX 3090 166 GB · $749/mo	8× RTX 5090 222 GB · $2,650/mo
8-bit	8× RTX A6000 294 GB · $3,226/mo	8× A100 350 GB · $10,138/mo
16-bit	8× RTX PRO 6000 578 GB · $12,614/mo	8× RTX PRO 6000 634 GB · $12,614/mo

Estimates, not quotes. Nvidia cards at median on-demand rates, 32K context per request. Break-even assumes 5:1 input to output. How we estimate costs.

Similarly priced models

The models nearest DeepSeek V4 Flash by blended rate, five each way, each at its own cheapest provider.

Model	Blended / 1M	Input / 1M	Output / 1M	Context	Cutoff	vs DeepSeek V4 Flash
Gemini 2.5 Flash-Lite Google Cloud	$0.15	$0.10	$0.40	1M	Jan 2025	−8%
GPT-4.1 Nano OpenAI	$0.15	$0.10	$0.40	1M	Jun 2024	−8%
Ministral 3 8B Mistral	$0.15	$0.15	$0.15	256K		−8%
Qwen3.5-Flash Alibaba Cloud	$0.15	$0.10	$0.40	1M		−8%
Nemotron 3 Super 120B A12B Nvidia	$0.16	$0.09	$0.50	1M	Jun 2025	−3%
DeepSeek V4 Flash This model DeepSeek	$0.16	$0.14	$0.28	1M
Gemma 4 31B Google Cloud	$0.17	$0.13	$0.37	256K	Jan 2025	+4%
Qwen3-235B-A22B Instruct (2507) Alibaba Cloud	$0.17	$0.09	$0.58	262K		+5%
Gemma 4 26B A4B Google Cloud	$0.18	$0.13	$0.40	256K	Jan 2025	+7%
Llama 3.3 70B Meta	$0.18	$0.14	$0.40	128K	Dec 2023	+12%
Ministral 3 14B Mistral	$0.20	$0.20	$0.20	256K		+22%

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.

Thunder Compute

Our sponsor

NVIDIA H100 from $1.38/hr, A100 80GB from $0.78/hr, RTX A6000 from $0.27/hr

No commitments, billed per minute, SOC 2 and GDPR compliant

Hot swappable hardware, templates for ComfyUI and Ollama

One-click connection to VS Code or Cursor, simple CLI to connect without SSH

Try now

Frequently Asked Questions

What is DeepSeek V4 Flash good for?: Long-context agent and coding work. It is the cheapest of DeepSeek's chat models, and its MIT weights need about 170 GB at 4-bit to self-host, far less than V4 Pro.
When is DeepSeek V4 Flash not a good fit?: Image input, which DeepSeek offers only through the separate V4 Flash Vision Exp variant. DeepSeek's own API charges the list rate at peak hours, so the price depends on time of day.
What is the cheapest way to run DeepSeek V4 Flash?: Hosted, unless you push serious volume. DeepSeek charges $0.44 in / $1.32 out per 1M tokens. The cheapest rental that fits is 8x RTX 3090 at $749 a month, which costs the same as about 1B tokens a month on that API.
Can I self-host DeepSeek V4 Flash?: Yes. The weights are MIT licensed. At 4-bit it needs about 166 GB of GPU memory, which starts at roughly $749 a month on the cheapest rental that fits. See the table above for 8-bit and 16-bit.

More from DeepSeek

Model	Context	Input / 1M	Output / 1M
DeepSeek V3.2 Open weights	131K	$0.27	$0.40
DeepSeek V3.1 Open weights	131K	$0.27	$1.00
DeepSeek V3.1 Terminus Open weights	131K	$0.27	$1.00
DeepSeek V3 Open weights	128K	$0.27	$1.12
DeepSeek V4 Pro Open weights	1M	$0.45	$0.89
DeepSeek V3 Turbo Open weights	64K	$0.40	$1.30
DeepSeek V4 Flash Vision Exp	1M	$0.44	$1.32
DeepSeek R1 Distill Llama 70B Open weights	131K	$0.80	$0.80