Model
DeepSeek V4 Flash 0731
Recorded as suitable for chat, rag, coding, reasoning, multilingual, zh, agentic, long context.
- Source
- Model registry API
- Verified
- 19 Sep 2026
- Confidence
- High
01What this is
- Author
- deepseek-ai
- Family
- DeepSeek V4
- Task
- text-generation
- Hugging Face
- deepseek-ai/DeepSeek-V4-Flash-0731
- OpenRouter
- deepseek/deepseek-v4-flash-0731
- Also known as
- DeepSeek V4 Flash, DeepSeek V4 Flash 0731, deepseek-v4-flash, deepseek-v4-flash-0731, deepseek flash
02Registry facts
- LicenceFACT
mit
- FreshRetrieved 19 Sep 2026
- ParametersFACT
304.2B
- FreshRetrieved 19 Sep 2026
- Context lengthFACT
not returned by the registry
- Evidence not verified
- Downloads (30 days)FACT
4,178,593
- FreshRetrieved 19 Sep 2026
- LikesFACT
3,978
- FreshRetrieved 19 Sep 2026
- GatedFACT
no
- FreshRetrieved 19 Sep 2026
Model
- downloadsFACT
4178593
- Verification may be outdatedRetrieved 19 Sep 2026
- gatedFACT
false
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · BaiduFACT
1048576
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · StreamLakeFACT
1024000
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · RelaceFACT
1048576
- Verification may be outdatedRetrieved 19 Sep 2026
- likesFACT
3978
- Verification may be outdatedRetrieved 19 Sep 2026
- model licenseFACT
mit
- Verification may be outdatedRetrieved 19 Sep 2026
- parameter countFACT
304180418494
- Verification may be outdatedRetrieved 19 Sep 2026
Pricing
- hosted price completion per m · BaiduFACT
0.1439
- AgeingRetrieved 19 Sep 2026
- hosted price completion per m · StreamLakeFACT
0.1320
- AgeingRetrieved 19 Sep 2026
- hosted price completion per m · RelaceFACT
0.0800
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · BaiduFACT
0.0480
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · StreamLakeFACT
0.0440
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · RelaceFACT
0.0400
- AgeingRetrieved 19 Sep 2026
Other
- available on platform · vendorFACT
vendor
Evidence not verified — the quoted phrase was not found in the fetched document.
- Evidence not verified
- available on platform · azureFACT
azure
Evidence not verified — the quoted phrase was not found in the fetched document.
- Evidence not verified
- last modifiedFACT
2026-08-01T03:07:41.000Z
- Verification may be outdatedRetrieved 19 Sep 2026
- libraryFACT
transformers
- AgeingRetrieved 19 Sep 2026
03VRAM by quantisation
Peak VRAM for serving this model, computed by lib/deployment/hardware.ts from weights + KV cache + 15% runtime overhead. Inputs: 304.2B parameters, 8,192 tokens of context (assumed — none fetched yet), 4 concurrent requests (assumed).
| Quantisation | Weights | Total |
|---|---|---|
| bf16bf16 is two bytes per weight, the same arithmetic as fp16. | 608.36 GB | 716.9 GB |
| fp8 | 304.18 GB | 367.09 GB |
| int4 | 152.09 GB | 192.19 GB |
What this estimate assumes
- Weights: 304.2B parameters × 2 bytes per parameter (fp16) = 608.36 GB.
- No model configuration was supplied, so the KV cache uses the size heuristic for this band: 0.459 MB per token, from extrapolated above 90B — no configuration was fetched for this band.
- KV cache: 0.459 MB per token × 8,192 tokens of context × 4 concurrent requests = 15.03 GB, sized for every user holding a full context at once.
- Overhead: 15% of weights plus KV cache for the runtime, activations and memory fragmentation = 93.51 GB.
- GB means 10⁹ bytes, matching how GPU memory is advertised.
- KV cache held at fp16 (2 bytes per element); quantising weights does not by itself quantise the cache.
- Peak figure, not average: prefix caching and paged attention usually keep real usage lower, while speculative decoding, CUDA graphs and a second resident model push it higher.
- "Concurrent" counts requests generated at the same instant, not people: 4 simultaneous requests is the worst case this estimate is built on — measure yours before buying.
04Hardware profiles
No hardware profile was sized for this answer.
05Hosted providers
- Prompt (per million tokens, USD)FACT
0.04
Source: openrouter
- FreshRetrieved 19 Sep 2026
- Completion (per million tokens, USD)FACT
0.08
- FreshRetrieved 19 Sep 2026
| Provider | Context |
|---|---|
| Relace | 1,048,576 |
| StreamLake | 1,024,000 |
| Baidu | 1,048,576 |
| DeepInfra | 1,048,576 |
| Sail Research | 1,048,576 |
| Inceptron | 1,048,576 |
06Deployment stacks
No published deployment stack names this model yet.
07Evidence
- 01–09Tier 4official repository / model cardOpenRouter
OpenRouter endpoints — deepseek/deepseek-v4-flash-0731
https://openrouter.ai/api/v1/models/deepseek/deepseek-v4-flash-0731/endpoints
AgeingRetrieved 19 Sep 2026sha256:14b30c8337c19 records · · · · · · · ·
- 10–16Tier 4official repository / model cardHugging Face Hub
Hugging Face model card data — deepseek-ai/DeepSeek-V4-Flash-0731
https://huggingface.co/api/models/deepseek-ai/DeepSeek-V4-Flash-0731
Verification may be outdatedRetrieved 19 Sep 2026sha256:bf918a1ce4417 records · · · · · ·
Improve this page
Sign in to contribute
From the field
0 deployments · 0 questions
Nobody has reported deploying this here yet, and no question has been opened against this page. Both appear once a reviewer accepts them.