DeepSeek V3 0324
DeepSeekhuggingface.co/deepseek-ai/DeepSeek-V3-0324
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...
Updated 10 min ago · first seen 11 Sept 2026
model_01M294WWHTCRTKN8AHRV7H4SBP
- Parameters
- 684.5B
- T2 · 6 h ago
- Context
- 163.8K tokens
- T2 · 3 h ago
- Released
- 24 Mar 2025
- T2 · 6 h ago
- License
- mit
- T2 · 6 h ago
- Knowledge cutoff
- Jul 2024
- T2 · 6 h ago
Specification
- Release date
- 24 Mar 2025
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Status
- deprecated
Source:Artificial AnalysisT2observed 5 h agomedium
- Openness
- open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 6 h agomedium
- License
- mit
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 6 h agomedium
- Architecture
- DeepseekV3ForCausalLM
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 6 h agomedium
- Parameters
- 684.5B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 6 h agomedium
- Context window
- 163.8K tokens
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Max output
- 147.5K tokens
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Knowledge cutoff
- Jul 2024
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Modalities
- text
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Input modalities
- text
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Output modalities
- text
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Tokenizer
- DeepSeek
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Quantization format
- fp8
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 6 h agomedium
- File size
- 688.6 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 6 h agomedium
- Hugging Face repo
- deepseek-ai/DeepSeek-V3-0324
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Pipeline tag
- text-generation
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 6 h agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 6 h agomedium
- Downloads
- 908,647
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 10 min agomedium
- Likes
- 3,169
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 10 min agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 6 h agomedium
- Hf inference providers
- deepinfra, featherless-ai, novita
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 6 h agomedium
- Is quantized
- Yes
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 6 h agomedium
- Last modified
- 2025-03-27T04:01:53+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 6 h agomedium
- Library name
- transformers
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 6 h agomedium
- Downloads all time
- 8,977,770
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 10 min agomedium
- Model type
- deepseek_v3
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 6 h agomedium
- Openrouter id
- deepseek/deepseek-chat-v3-0324
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Supported parameters
- frequency_penalty, logit_bias, logprobs, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Tags
- transformers, safetensors, deepseek_v3, text-generation, custom_code, fp8
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 6 h agomedium
- Weights dtype
- BF16, F32, F8_E4M3
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 6 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
35
Source tiers
T235
Freshest observation
10 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
No
Artificial Analysis · T2
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 163.8K tokens
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Max output
- 147.5K tokens
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Knowledge cutoff
- Jul 2024
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Tokenizer
- DeepSeek
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
| Benchmark | Score | Metric | Config | Evaluated | Source |
|---|---|---|---|---|---|
| τ²-bench | 47.08% | pass^1 | aa_slug=deepseek-v3-0324 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Aider polyglot | 55.1% | pass_rate_2 | date=2025-03-24 · command=aider --model deepseek/deepseek-chat · dirname=2025-03-24-15-41-33--deepseek-v3-0324-polyglot-diff · versions=0.78.1.dev | 24 Mar 2025 | aider.chatT2 |
| Aider polyglot | 99.6% | percent_cases_well_formed | date=2025-03-24 · command=aider --model deepseek/deepseek-chat · dirname=2025-03-24-15-41-33--deepseek-v3-0324-polyglot-diff · versions=0.78.1.dev | 24 Mar 2025 | aider.chatT2 |
| Artificial Analysis Intelligence Index | 9.72 | index | aa_slug=deepseek-v3-0324 · version=4.3 · estimated=false | — | artificialanalysis.aiT2 |
| GPQA | 65.45% | accuracy | aa_slug=deepseek-v3-0324 · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Humanity's Last Exam | 4.74% | accuracy | aa_slug=deepseek-v3-0324 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| IFBench | 41.02% | accuracy | aa_slug=deepseek-v3-0324 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| SciCode | 39% | accuracy | aa_slug=deepseek-v3-0324 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| SWE-bench Verified | 42% | resolved | date=2025-08-06 · board=Verified · system=SWE-Exp · model_tag=DeepSeek-V3-0324 | 6 Aug 2025 | swebench.comT2 |
| Terminal-Bench | 13.86% | accuracy | aa_slug=deepseek-v3-0324 · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Terminal-Bench | 15.15% | accuracy | aa_slug=deepseek-v3-0324 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Terminal-Bench | 0% | accuracy | aa_slug=deepseek-v3-0324 · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
Scores are reported as published, with their evaluation configuration (harness, prompting, judge). Results with different configs are not directly comparable — see methodology.
Current prices
| Provider | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| DeepSeek APIdeepseek/deepseek-chat-v3-0324 | $0.25 | $1 | — | — | 163.8K | 2 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 | 394.1 GB | Yes |
| Apple M3 Ultra | 4bit | — | 394.1 GB | Yes |
| Mac Studio (Apple M5 Ultra) | 4bit | — | 394.1 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 394.1 GB | No |
| AMD Instinct MI300X | 4bit | 192 GB | 394.1 GB | No |
| Apple M2 Ultra | 4bit | — | 394.1 GB | No |
| NVIDIA B200 | 4bit | 180 GB | 394.1 GB | No |
| NVIDIA H200 | 4bit | 141 GB | 394.1 GB | No |
| NVIDIA H200 NVL | 4bit | 141 GB | 394.1 GB | No |
| Apple M1 Ultra | 4bit | — | 394.1 GB | No |
| Apple M3 Max | 4bit | — | 394.1 GB | No |
| Apple M4 Max | 4bit | — | 394.1 GB | No |
| Mac Studio (Apple M5 Max) | 4bit | — | 394.1 GB | No |
| MacBook Pro (Apple M5 Max) | 4bit | — | 394.1 GB | No |
| NVIDIA DGX Spark | 4bit | 128 GB | 394.1 GB | No |
| Apple M2 Max | 4bit | — | 394.1 GB | No |
| NVIDIA H100 NVL | 4bit | 94 GB | 394.1 GB | No |
| NVIDIA A100 80GB | 4bit | 80 GB | 394.1 GB | No |
| NVIDIA H100 SXM | 4bit | 80 GB | 394.1 GB | No |
| Apple M1 Max | 4bit | — | 394.1 GB | No |
| Apple M4 Pro | 4bit | — | 394.1 GB | No |
| Mac mini (Apple M5 Pro) | 4bit | — | 394.1 GB | No |
| MacBook Pro (Apple M5 Pro) | 4bit | — | 394.1 GB | No |
| Apple M3 Pro | 4bit | — | 394.1 GB | No |
| Apple M1 Pro | 4bit | — | 394.1 GB | No |
| Apple M2 Pro | 4bit | — | 394.1 GB | No |
| Apple M4 | 4bit | — | 394.1 GB | No |
| iMac (Apple M4) | 4bit | — | 394.1 GB | No |
| Mac mini (Apple M6) | 4bit | — | 394.1 GB | No |
| MacBook Air (Apple M5) | 4bit | — | 394.1 GB | No |
| MacBook Pro (Apple M5) | 4bit | — | 394.1 GB | No |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 394.1 GB | No |
| Apple M2 | 4bit | — | 394.1 GB | No |
| Apple M3 | 4bit | — | 394.1 GB | No |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 394.1 GB | No |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 394.1 GB | No |
| Apple M1 | 4bit | — | 394.1 GB | No |
No lineage recorded
Papers 1
- arXiv:2412.19437Active35
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
Release daterelease_date1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 24 Mar 2025 | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Opennessopenness1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| open-weights | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Licenselicense1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| mit | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Architecturearchitecture1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| DeepseekV3ForCausalLM | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Parametersparameter_count1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 684.5B | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Context windowcontext_length1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 163.8K tokens | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Max outputmax_output_tokens1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 147.5K tokens | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Knowledge cutoffknowledge_cutoff1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Jul 2024 | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Modalitiesmodalities1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| text | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Input modalitiesmodalities_input1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| text | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Output modalitiesmodalities_output1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| text | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Tokenizertokenizer1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| DeepSeek | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Quantization formatquant_format1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| fp8 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
File sizefile_size_gb1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 688.6 GB | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Hugging Face repohf_repo1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| deepseek-ai/DeepSeek-V3-0324 | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Pipeline tagpipeline_tag1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| text-generation | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Model cardmodel_card_url1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| https://huggingface.co/deepseek-ai/DeepSeek-V3-0324 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Downloadsmetric.downloads1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 908,647 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Likesmetric.likes1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 3,169 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Descriptiondescription1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well... | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Gatedgated1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| No | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Hf inference providershf_inference_providers1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| deepinfra, featherless-ai, novita | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Is quantizedis_quantized1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Yes | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Last modifiedlast_modified1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 2025-03-27T04:01:53+00:00 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Library namelibrary_name1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| transformers | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Downloads all timemetric.downloads_all_time1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 8,977,770 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Model typemodel_type1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| deepseek_v3 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Openrouter idopenrouter_id1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| deepseek/deepseek-chat-v3-0324 | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Structured outputstructured_output1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Yes | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Supported parameterssupported_parameters1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| frequency_penalty, logit_bias, logprobs, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Tool callingtool_calling1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Yes | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Weights dtypeweights_dtype1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| BF16, F32, F8_E4M3 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | 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 V3 0324: context length changed from 128000 to 163840
Context window128K tokens→163.8K tokensopenrouterDeepSeek V3 0324 scores 42% on SWE-bench Verified
swebench_leaderboardDeepSeek V3 0324 scores 15.15% on Terminal-Bench
artificial_analysisDeepSeek V3 0324 scores 13.86% on Terminal-Bench
artificial_analysisDeepSeek V3 0324 scores 0% on Terminal-Bench
artificial_analysisDeepSeek V3 0324 scores 47.08% on τ²-bench
artificial_analysisDeepSeek V3 0324 scores 41.02% on IFBench
artificial_analysisDeepSeek V3 0324 scores 39% on SciCode
artificial_analysisDeepSeek V3 0324 scores 4.74% on Humanity's Last Exam
artificial_analysisDeepSeek V3 0324 scores 65.45% on GPQA
artificial_analysisDeepSeek V3 0324 scores 9.72 on Artificial Analysis Intelligence Index
artificial_analysisDeepSeek V3 0324: context length changed from 163840 to 128000
Context window163.8K tokens→128K tokensartificial_analysisDeepSeek V3 0324 scores 99.6% on Aider polyglot
aider_leaderboardDeepSeek V3 0324 scores 55.1% on Aider polyglot
aider_leaderboardDeepSeek API lists DeepSeek V3 0324 at $0.25 in / $1 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-V3-0324 | model_page | T2· Quality secondary | 10 min ago | 4 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=deepseek-ai&p=0&sort=downloads | listing | T2· Quality secondary | 24 min ago | 6 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/deepseek-ai/DeepSeek-V3-0324/raw/main/README.md | model_card | T2· Quality secondary | 46 min ago | 1 |
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 2 h ago | 4 |
| SWE-bench leaderboards | swebench.com/ | leaderboard | T2· Quality secondary | 4 h ago | 1 |
| Artificial Analysis | artificialanalysis.ai/leaderboards/models | leaderboard | T2· Quality secondary | 5 h ago | 1 |
| Aider polyglot leaderboard (data file on GitHub) | raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml | leaderboard | T2· Quality secondary | 5 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.