DeepSeek V4 Flash
Summary
DeepSeek V4 Flash is an open-weight language model from DeepSeek, released on 24 Apr 2026. It accepts text and generates text, with a 1M-token context window and up to 384K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.09 per million input tokens and $0.18 per million output tokens (DeepInfra), across 6 providers we track.
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | DeepSeek |
|---|---|
| Release date | 24 Apr 2026 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | mit [Hugging Face] |
| Parameters | 291B [Hugging Face] |
| Context window | 1M (1,000,000 tokens) [models.dev] |
| Max output | 384K tokens [models.dev] |
| Knowledge cutoff | May 2025 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | Yes [models.dev] |
| Hugging Face | deepseek-ai/DeepSeek-V4-Flash [Hugging Face] |
DeepSeek V4 Flash API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| DeepInfra deepseek-ai/DeepSeek-V4-Flash | $0.09 | $0.18 | $0.02 | 1M | models.dev, 18 Nov 2026 |
| OpenRouter deepseek/deepseek-v4-flash | $0.09 | $0.18 | $0.02 | 1M | OpenRouter, 18 Nov 2026 |
| SiliconFlow deepseek-ai/DeepSeek-V4-Flash | $0.13 | $0.28 | $0.03 | 1M | models.dev, 18 Nov 2026 |
| Vercel AI Gateway deepseek/deepseek-v4-flash | $0.13 | $0.26 | $0.03 | 1M | models.dev, 18 Nov 2026 |
| Hugging Face Inference Providers deepseek-ai/DeepSeek-V4-Flash | $0.14 | $0.28 | – | 1M | models.dev, 18 Nov 2026 |
| Azure AI Foundry deepseek-v4-flash | $0.19 | $0.51 | – | 1M | models.dev, 18 Nov 2026 |
Running DeepSeek V4 Flash locally
Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 176 GB | 178 GB | 180 GB |
| Q8_0 (8-bit) | 309 GB | 311 GB | 313 GB |
| FP16 / BF16 (16-bit) | 582 GB | 583 GB | 586 GB |
At 4-bit with an 8K conversation, DeepSeek V4 Flash needs about 178 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.
Frequently asked questions
What is the context window of DeepSeek V4 Flash?
DeepSeek V4 Flash has a context window of 1,000,000 tokens (1M) and can generate up to 384,000 tokens in a single response, according to models.dev.
How much does the DeepSeek V4 Flash API cost?
DeepSeek V4 Flash is listed from $0.09 per million input tokens and $0.18 per million output tokens (DeepInfra). Prices last verified 18 Nov 2026.
Is DeepSeek V4 Flash open source?
DeepSeek V4 Flash is an open-weight model: its weights are published on Hugging Face as deepseek-ai/DeepSeek-V4-Flash under the mit license. Check the license terms before commercial use.
When was DeepSeek V4 Flash released?
DeepSeek released DeepSeek V4 Flash on 24 Apr 2026, according to models.dev.
Which providers offer DeepSeek V4 Flash?
We track DeepSeek V4 Flash on 6 providers: DeepInfra, OpenRouter, SiliconFlow, Vercel AI Gateway, Hugging Face Inference Providers, Azure AI Foundry.
How much VRAM does DeepSeek V4 Flash need?
About 178 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 311 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Muse Spark 1.2 Contributor | Meta | 21 Aug 2026 | 1M | $0.10 | $0.20 | – |
| Muse Spark 1.3 Contributor | Meta | 2 Sept 2026 | 1M | $0.10 | $0.20 | – |
| MiMo-V2.6-Flash | Xiaomi (MiMo) | 22 Sept 2026 | 1M | $0.14 | $0.28 | Open |
| MiniMax-M3.1-Flash | MiniMax | 19 Oct 2026 | 1M | $0.07 | $0.30 | Open |
| GLM-5.3-Flash | Zhipu AI (Z.ai) | 26 Aug 2026 | 1M | $0.15 | $0.50 | Open |
| ricursiveAI/Ripple-65B-Preview | Ricursiveai | 4 Nov 2026 | 1M | $0.10 | $0.30 | Open |
Change history
- Context window changed from 1M to 1M
- Context window changed from 1M to 1M
- Name changed from DeepSeek-V4-Flash to DeepSeek V4 Flash
- Name changed from DeepSeek V4 Flash to DeepSeek-V4-Flash
- Context window changed from 1M to 1M
- Name changed from DeepSeek-V4-Flash to DeepSeek V4 Flash
- Context window changed from 1M to 1M
- Name changed from DeepSeek V4 Flash to DeepSeek-V4-Flash
- Max output changed from 16K to 384K
- Context window changed from 1M to 1M
- Context window changed from 1M to 1M
- Name changed from DeepSeek-V4-Flash to DeepSeek V4 Flash
- Max output changed from 384K to 16K
- OpenRouter price changed: input $0.09 → $0.09, output $0.18 → $0.18 per 1M tokens
- Name changed from DeepSeek V4 Flash to DeepSeek-V4-Flash
- Context window changed from 1M to 1M
- Max output changed from 16K to 384K
- Max output changed from 384K to 16K
- Context window changed from 1M to 1M
- Context window changed from 1M to 1M
- Max output changed from 944K to 384K
- Max output changed from 384K to 944K
- Max output changed from 16K to 384K
- Max output changed from 384K to 16K
- Context window changed from 1M to 1M
Sources
- https://openrouter.ai/deepseek/deepseek-v4-flash
- https://github.com/sst/models.dev/blob/dev/providers/vercel/models/deepseek/deepseek-v4-flash.toml
- https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash
- https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/deepseek-ai/DeepSeek-V4-Flash.toml
- https://github.com/sst/models.dev/blob/dev/providers/siliconflow/models/deepseek-ai/DeepSeek-V4-Flash.toml
- https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/deepseek-ai/DeepSeek-V4-Flash.toml
- https://github.com/sst/models.dev/blob/dev/providers/azure/models/deepseek-v4-flash.toml