DeepSeek V4 Flash 0423
DeepSeekhuggingface.co/deepseek-ai/DeepSeek-V4-Flash
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
Updated 33 min ago · first seen 11 Sept 2026
model_01M294WW0M9SRBDTMYPH56GG7K
- Parameters
- 290.9B
- T2 · 5 h ago
- Context
- 1.05M tokens
- T2 · 5 h ago
- Released
- 22 Apr 2026
- T2 · 33 min ago
- License
- mit
- T2 · 5 h ago
Specification
- Release date
- 22 Apr 2026
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 33 min agomedium
- Openness
- open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
- License
- mit
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
- Architecture
- DeepseekV4ForCausalLM
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
- Parameters
- 290.9B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
- Context window
- 1.05M tokens
Source:OpenRouter public model & pricing listingT2observed 5 h agomedium
- Max output
- 384K tokens
Source:OpenRouter public model & pricing listingT2observed 5 h agomedium
- Modalities
- text
Source:OpenRouter public model & pricing listingT2observed 5 h agomedium
- Input modalities
- text
Source:OpenRouter public model & pricing listingT2observed 5 h agomedium
- Output modalities
- text
Source:OpenRouter public model & pricing listingT2observed 5 h agomedium
- Tokenizer
- DeepSeek
Source:OpenRouter public model & pricing listingT2observed 5 h agomedium
- Quantization format
- fp8
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
- File size
- 159.6 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
- Hugging Face repo
- deepseek-ai/DeepSeek-V4-Flash
Source:OpenRouter public model & pricing listingT2observed 5 h agomedium
- Pipeline tag
- text-generation
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
- Downloads
- 1,783,023
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 33 min agomedium
- Likes
- 2,212
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 33 min agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
- Hf inference providers
- deepinfra, featherless-ai, novita
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
- Is quantized
- Yes
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
- Last modified
- 2026-06-22T12:12:13+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
- Library name
- transformers
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
- Downloads all time
- 11,642,153
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 33 min agomedium
- Model type
- deepseek_v4
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
- Openrouter id
- deepseek/deepseek-v4-flash
Source:OpenRouter public model & pricing listingT2observed 5 h agomedium
- Supported parameters
- frequency_penalty, include_reasoning, logit_bias, logprobs, max_completion_tokens, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_a, top_k, top_logprobs, top_p
Source:OpenRouter public model & pricing listingT2observed 5 h agomedium
- Tags
- transformers, safetensors, deepseek_v4, text-generation, 8-bit, fp8
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
- Weights dtype
- BF16, F32, F8_E4M3, I64, I8
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 5 h agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
33
Source tiers
T233
Freshest observation
33 min ago
Conflicts
None
Modalities
- Modalities
- text
- Input
- text
- Output
- text
Capabilities
Tool calling
Yes
OpenRouter public model & pricing listing · T2
Structured output
Yes
OpenRouter public model & pricing listing · T2
Reasoning
Yes
OpenRouter public model & pricing listing · T2
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 1.05M tokens
Source:OpenRouter public model & pricing listingT2observed 5 h agomedium
- Max output
- 384K tokens
Source:OpenRouter public model & pricing listingT2observed 5 h agomedium
- Tokenizer
- DeepSeek
Source:OpenRouter public model & pricing listingT2observed 5 h agomedium
No benchmark results recorded
Current prices
| Provider | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| DeepSeek APIdeepseek/deepseek-v4-flash | $0.067 | $0.135 | $0.013 | — | 1.02M | 1 h ago | openrouter.aiT2 |
USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Available through 1
Price history
Input price · USD / 1M tokens
Output price · USD / 1M tokens
- DeepSeek API
Memory need = bytes per parameter (4-bit ≈ 0.5 × 1.15 overhead, 8-bit 1.0, fp16 2.0) + a KV-cache allowance. Not a measurement.
| Hardware | Quantization | Memory | Est. need | Fits |
|---|---|---|---|---|
| NVIDIA DGX B200 | 4bit | 1,440 GB | 167.8 GB | Yes |
| Apple M3 Ultra | 4bit | — | 167.8 GB | Yes |
| Mac Studio (Apple M5 Ultra) | 4bit | — | 167.8 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 167.8 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 167.8 GB | Yes |
| Apple M2 Ultra | 4bit | — | 167.8 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 167.8 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 167.8 GB | No |
| NVIDIA H200 NVL | 4bit | 141 GB | 167.8 GB | No |
| Apple M1 Ultra | 4bit | — | 167.8 GB | No |
| Apple M3 Max | 4bit | — | 167.8 GB | No |
| Apple M4 Max | 4bit | — | 167.8 GB | No |
| Mac Studio (Apple M5 Max) | 4bit | — | 167.8 GB | No |
| MacBook Pro (Apple M5 Max) | 4bit | — | 167.8 GB | No |
| NVIDIA DGX Spark | 4bit | 128 GB | 167.8 GB | No |
| Apple M2 Max | 4bit | — | 167.8 GB | No |
| NVIDIA H100 NVL | 4bit | 94 GB | 167.8 GB | No |
| NVIDIA A100 80GB | 4bit | 80 GB | 167.8 GB | No |
| NVIDIA H100 SXM | 4bit | 80 GB | 167.8 GB | No |
| Apple M1 Max | 4bit | — | 167.8 GB | No |
| Apple M4 Pro | 4bit | — | 167.8 GB | No |
| Mac mini (Apple M5 Pro) | 4bit | — | 167.8 GB | No |
| MacBook Pro (Apple M5 Pro) | 4bit | — | 167.8 GB | No |
| Apple M3 Pro | 4bit | — | 167.8 GB | No |
| Apple M1 Pro | 4bit | — | 167.8 GB | No |
| Apple M2 Pro | 4bit | — | 167.8 GB | No |
| Apple M4 | 4bit | — | 167.8 GB | No |
| iMac (Apple M4) | 4bit | — | 167.8 GB | No |
| Mac mini (Apple M6) | 4bit | — | 167.8 GB | No |
| MacBook Air (Apple M5) | 4bit | — | 167.8 GB | No |
| MacBook Pro (Apple M5) | 4bit | — | 167.8 GB | No |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 167.8 GB | No |
| Apple M2 | 4bit | — | 167.8 GB | No |
| Apple M3 | 4bit | — | 167.8 GB | No |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 167.8 GB | No |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 167.8 GB | No |
| Apple M1 | 4bit | — | 167.8 GB | No |
No lineage recorded
Papers 1
- arXiv:2606.19348Active35
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Supported parameters
Supported parameterssupported_parameters1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| frequency_penalty, include_reasoning, logit_bias, logprobs, max_completion_tokens, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_a, top_k, top_logprobs, top_p | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
DeepSeek API changed pricing for DeepSeek V4 Flash 0423: $0.06762 in / $0.13524 out per 1M tokens → $0.06734 in / $0.13468 out per 1M tokens
{"input_per_mtok":0.06762,"output_per_mtok":0.13524}→{"input_per_mtok":0.06734,"output_per_mtok":0.13468}openrouterDeepSeek API changed pricing for DeepSeek V4 Flash 0423: $0.08456 in / $0.16912 out per 1M tokens → $0.06762 in / $0.13524 out per 1M tokens
{"input_per_mtok":0.08456,"output_per_mtok":0.16912}→{"input_per_mtok":0.06762,"output_per_mtok":0.13524}openrouterDeepSeek API changed pricing for DeepSeek V4 Flash 0423: $0.08484 in / $0.16968 out per 1M tokens → $0.08456 in / $0.16912 out per 1M tokens
{"input_per_mtok":0.08484,"output_per_mtok":0.16968}→{"input_per_mtok":0.08456,"output_per_mtok":0.16912}openrouterDeepSeek V4 Flash 0423: release date changed from 2026-04-22 to 2026-04-24
Release date22 Apr 2026→24 Apr 2026openrouterDeepSeek V4 Flash 0423: release date changed from 2026-04-24 to 2026-04-22
Release date24 Apr 2026→22 Apr 2026huggingfaceDeepSeek API lists DeepSeek V4 Flash 0423 at $0.08484 in / $0.16968 out per 1M tokens
openrouter
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/deepseek-ai/DeepSeek-V4-Flash | model_page | T2· Quality secondary | 33 min ago | 3 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=deepseek-ai&p=0&sort=downloads | listing | T2· Quality secondary | 46 min ago | 4 |
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 1 h ago | 4 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/deepseek-ai/DeepSeek-V4-Flash/raw/main/README.md | model_card | T2· Quality secondary | 3 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.