DeepSeek V4 Pro 0423
DeepSeekhuggingface.co/deepseek-ai/DeepSeek-V4-Pro
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
Updated 50 min ago · first seen 11 Sept 2026
model_01M294WW0GPKNDS16RSPXC5YCE
- Parameters
- 1.6T
- T2 · 4 h ago
- Context
- 1.05M tokens
- T2 · 4 h ago
- Released
- 24 Apr 2026
- T2 · 50 min ago
- License
- mit
- T2 · 3 h ago
Specification
- Release date
- 24 Apr 2026
Source:OpenRouter public model & pricing listingT2observed 50 min agomedium
- Openness
- open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
- License
- mit
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Architecture
- DeepseekV4ForCausalLM
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Parameters
- 1.6T
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
- Context window
- 1.05M tokens
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Max output
- 384K tokens
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Modalities
- text
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Input modalities
- text
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Output modalities
- text
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Tokenizer
- DeepSeek
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Quantization format
- fp8
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- File size
- 864.7 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Hugging Face repo
- deepseek-ai/DeepSeek-V4-Pro
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Pipeline tag
- text-generation
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
- Downloads
- 619,127
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Likes
- 5,523
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Hf inference providers
- baseten, deepinfra, novita, together
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Is quantized
- Yes
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Last modified
- 2026-06-22T12:12:50+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium
- Library name
- transformers
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Downloads all time
- 10,412,271
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Model type
- deepseek_v4
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Openrouter id
- deepseek/deepseek-v4-pro
Source:OpenRouter public model & pricing listingT2observed 4 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_k, top_logprobs, top_p
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Tags
- transformers, safetensors, deepseek_v4, text-generation, 8-bit, fp8
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Weights dtype
- BF16, F32, F8_E4M3, I64, I8
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 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
50 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 4 h agomedium
- Max output
- 384K tokens
Source:OpenRouter public model & pricing listingT2observed 4 h agomedium
- Tokenizer
- DeepSeek
Source:OpenRouter public model & pricing listingT2observed 4 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-pro | $0.84 | $1.68 | $0.07 | — | 1.02M | 50 min 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 | 919.8 GB | Yes |
| Apple M3 Ultra | 4bit | — | 919.8 GB | No |
| Mac Studio (Apple M5 Ultra) | 4bit | — | 919.8 GB | No |
| AMD Instinct MI325X | 4bit | 256 GB | 919.8 GB | No |
| AMD Instinct MI300X | 4bit | 192 GB | 919.8 GB | No |
| Apple M2 Ultra | 4bit | — | 919.8 GB | No |
| NVIDIA B200 | 4bit | 180 GB | 919.8 GB | No |
| NVIDIA H200 | 4bit | 141 GB | 919.8 GB | No |
| NVIDIA H200 NVL | 4bit | 141 GB | 919.8 GB | No |
| Apple M1 Ultra | 4bit | — | 919.8 GB | No |
| Apple M3 Max | 4bit | — | 919.8 GB | No |
| Apple M4 Max | 4bit | — | 919.8 GB | No |
| Mac Studio (Apple M5 Max) | 4bit | — | 919.8 GB | No |
| MacBook Pro (Apple M5 Max) | 4bit | — | 919.8 GB | No |
| NVIDIA DGX Spark | 4bit | 128 GB | 919.8 GB | No |
| Apple M2 Max | 4bit | — | 919.8 GB | No |
| NVIDIA H100 NVL | 4bit | 94 GB | 919.8 GB | No |
| NVIDIA A100 80GB | 4bit | 80 GB | 919.8 GB | No |
| NVIDIA H100 SXM | 4bit | 80 GB | 919.8 GB | No |
| Apple M1 Max | 4bit | — | 919.8 GB | No |
| Apple M4 Pro | 4bit | — | 919.8 GB | No |
| Mac mini (Apple M5 Pro) | 4bit | — | 919.8 GB | No |
| MacBook Pro (Apple M5 Pro) | 4bit | — | 919.8 GB | No |
| Apple M3 Pro | 4bit | — | 919.8 GB | No |
| Apple M1 Pro | 4bit | — | 919.8 GB | No |
| Apple M2 Pro | 4bit | — | 919.8 GB | No |
| Apple M4 | 4bit | — | 919.8 GB | No |
| iMac (Apple M4) | 4bit | — | 919.8 GB | No |
| Mac mini (Apple M6) | 4bit | — | 919.8 GB | No |
| MacBook Air (Apple M5) | 4bit | — | 919.8 GB | No |
| MacBook Pro (Apple M5) | 4bit | — | 919.8 GB | No |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 919.8 GB | No |
| Apple M2 | 4bit | — | 919.8 GB | No |
| Apple M3 | 4bit | — | 919.8 GB | No |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 919.8 GB | No |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 919.8 GB | No |
| Apple M1 | 4bit | — | 919.8 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 · Tags
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 Pro 0423: $0.947778 in / $1.89556 out per 1M tokens → $0.839724 in / $1.67945 out per 1M tokens
{"input_per_mtok":0.947778,"output_per_mtok":1.895556}→{"input_per_mtok":0.839724,"output_per_mtok":1.679448}openrouterDeepSeek API changed pricing for DeepSeek V4 Pro 0423: $0.859908 in / $1.71982 out per 1M tokens → $0.947778 in / $1.89556 out per 1M tokens
{"input_per_mtok":0.859908,"output_per_mtok":1.719816}→{"input_per_mtok":0.947778,"output_per_mtok":1.895556}openrouterDeepSeek V4 Pro 0423: release date changed from 2026-04-22 to 2026-04-24
Release date22 Apr 2026→24 Apr 2026openrouterDeepSeek V4 Pro 0423: release date changed from 2026-04-24 to 2026-04-22
Release date24 Apr 2026→22 Apr 2026huggingfaceDeepSeek API lists DeepSeek V4 Pro 0423 at $0.859908 in / $1.71982 out per 1M tokens
openrouter
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 50 min ago | 3 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/deepseek-ai/DeepSeek-V4-Pro/raw/main/README.md | model_card | T2· Quality secondary | 1 h ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/deepseek-ai/DeepSeek-V4-Pro | model_page | T2· Quality secondary | 2 h ago | 2 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=deepseek-ai&p=0&sort=downloads | listing | T2· Quality secondary | 2 h ago | 3 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.