DeepSeek-V4.1-Flash
DeepSeekapi-docs.deepseek.com/quick_start/pricing
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
Updated 4 h ago · first seen 11 Sept 2026
model_01M293WR6HM862PR1R3X4523QG
- Context
- 1M tokens
- T1 · 6 h ago
- Released
- 10 Sept 2026
- T2 · 6 h ago
Specification
- Family
- DeepSeek
Source:DeepSeek — site & API docsT1observed 6 h agohigh
- Release date
- 10 Sept 2026
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Openness
- open-weights
Source:Artificial AnalysisT2observed 4 h agomedium
- Context window
- 1M tokens
Source:DeepSeek — site & API docsT1observed 6 h agohigh
- Max output
- 384K tokens
Source:DeepSeek — site & API docsT1observed 6 h agohigh
- Modalities
- image, text
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Input modalities
- text, image
Source:DeepSeek — site & API docsT1observed 6 h agohigh
- Output modalities
- text
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Tokenizer
- DeepSeek
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- API model id
- deepseek-flash
Source:DeepSeek — site & API docsT1observed 6 h agohigh
- Hugging Face repo
- deepseek-ai/DeepSeek-V4.1-Flash
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Official page
Source:DeepSeek — site & API docsT1observed 6 h agohigh
- Livebench hf link
- https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash
Source:LiveBenchT2observed 4 h agomedium
- Aa median output tokens per second
- 213.2
Source:Artificial AnalysisT2observed 4 h agomedium
- Openrouter id
- deepseek/deepseek-v4.1-flash
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Supported parameters
- frequency_penalty, include_reasoning, logit_bias, logprobs, 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 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
21
Source tiers
T1T210 / 11
Freshest observation
4 h ago
Conflicts
8 flagged
Modalities
- Modalities
- imagetext
- Input
- textimage
- Output
- text
Capabilities
Tool calling
Yes
DeepSeek — site & API docs · T1
Structured output
Yes
DeepSeek — site & API docs · T1
Reasoning
Yes
DeepSeek — site & API docs · T1
Vision
Yes
DeepSeek — site & API docs · T1
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 1M tokens
Source:DeepSeek — site & API docsT1observed 6 h agohigh
- Max output
- 384K tokens
Source:DeepSeek — site & API docsT1observed 6 h agohigh
- Tokenizer
- DeepSeek
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
| Benchmark | Score | Metric | Config | Evaluated | Source |
|---|---|---|---|---|---|
| Artificial Analysis Intelligence Index | 39.55 | index | aa_slug=deepseek-v4-1-flash · version=4.3 · estimated=false | — | artificialanalysis.aiT2 |
| Humanity's Last Exam | 39.25% | accuracy | aa_slug=deepseek-v4-1-flash · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| LiveBench | 77.27% | category:Agentic Coding | release=2026-06-25 · subtasks=["javascript","typescript","python"] · livebench_model_id=deepseek-v4.1-flash-max | 25 Jun 2026 | livebench.aiT2 |
| LiveBench | 93.29% | category:Mathematics | release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=deepseek-v4.1-flash-max | 25 Jun 2026 | livebench.aiT2 |
| LiveBench | 79.25% | category:Data Analysis | release=2026-06-25 · subtasks=["consecutive_events","tablejoin","tablereformat"] · livebench_model_id=deepseek-v4.1-flash-max | 25 Jun 2026 | livebench.aiT2 |
| LiveBench | 81.19% | category:Language | release=2026-06-25 · subtasks=["connections","plot_unscrambling","typos"] · livebench_model_id=deepseek-v4.1-flash-max | 25 Jun 2026 | livebench.aiT2 |
| LiveBench | 81.11% | global_average | release=2026-06-25 · aggregation=mean of category averages; category = mean of its subtasks · livebench_model_id=deepseek-v4.1-flash-max | 25 Jun 2026 | livebench.aiT2 |
| LiveBench | 86.69% | category:Reasoning | release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=deepseek-v4.1-flash-max | 25 Jun 2026 | livebench.aiT2 |
| LiveBench | 70.03% | category:IF | release=2026-06-25 · subtasks=["paraphrase","simplify","story_generation","summarize"] · livebench_model_id=deepseek-v4.1-flash-max | 25 Jun 2026 | livebench.aiT2 |
| LiveBench | 80.04% | category:Coding | release=2026-06-25 · subtasks=["code_generation","code_completion"] · livebench_model_id=deepseek-v4.1-flash-max | 25 Jun 2026 | livebench.aiT2 |
| MMMU-Pro | 76.99% | accuracy | aa_slug=deepseek-v4-1-flash · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| SciCode | 51.85% | accuracy | aa_slug=deepseek-v4-1-flash · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Terminal-Bench | 26.77% | accuracy | aa_slug=deepseek-v4-1-flash · 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-v4.1-flash | $0.15 | $0.60 | $0.003 | — | 1.05M | 2 h ago | openrouter.aiT2 |
| Fireworks AIfireworks/deepseek-v4p1-flash | $0.22 | $0.66 | $0.007 | — | — | 6 h ago | app.fireworks.aiT1 |
| DeepSeek APIdeepseek-flash | $0.30 | $1.2 | $0.006 | — | — | 6 h ago | api-docs.deepseek.comT1 |
USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Available through 2
Price history
Input price · USD / 1M tokens
Output price · USD / 1M tokens
- DeepSeek API
- Fireworks AI
No hardware estimate available
No lineage recorded
Papers 0
No papers linked yet.
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_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 | → 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-V4.1-Flash scores 70.033% on LiveBench
livebench_leaderboardDeepSeek-V4.1-Flash scores 81.19% on LiveBench
livebench_leaderboardDeepSeek-V4.1-Flash scores 79.253% on LiveBench
livebench_leaderboardDeepSeek-V4.1-Flash scores 93.29% on LiveBench
livebench_leaderboardDeepSeek-V4.1-Flash scores 77.273% on LiveBench
livebench_leaderboardDeepSeek-V4.1-Flash scores 80.037% on LiveBench
livebench_leaderboardDeepSeek-V4.1-Flash scores 86.692% on LiveBench
livebench_leaderboardDeepSeek-V4.1-Flash scores 81.11% on LiveBench
livebench_leaderboardDeepSeek-V4.1-Flash scores 26.77% on Terminal-Bench
artificial_analysisDeepSeek-V4.1-Flash scores 76.99% on MMMU-Pro
artificial_analysisDeepSeek-V4.1-Flash scores 51.85% on SciCode
artificial_analysisDeepSeek-V4.1-Flash scores 39.25% on Humanity's Last Exam
artificial_analysisDeepSeek-V4.1-Flash scores 39.55 on Artificial Analysis Intelligence Index
artificial_analysisDeepSeek API lists DeepSeek-V4.1-Flash at $0.15 in / $0.6 out per 1M tokens
openrouterFireworks AI lists DeepSeek-V4.1-Flash at $0.22 in / $0.66 out per 1M tokens
fireworks_pricingDeepSeek API lists DeepSeek-V4.1-Flash at $0.3 in / $1.2 out per 1M tokens
deepseek
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| DeepSeek — site & API docs | api-docs.deepseek.com/quick_start/pricing | pricing | T1· Official | 27 min ago | 1 |
| Fireworks AI — pricing | docs.fireworks.ai/serverless/pricing.md | pricing | T1· Official | 4 h ago | 1 |
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 2 h ago | 4 |
| LiveBench | livebench.ai/table_2026_06_25.csv | leaderboard | T2· Quality secondary | 4 h ago | 1 |
| Artificial Analysis | artificialanalysis.ai/leaderboards/models | leaderboard | T2· Quality secondary | 4 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.