aiticker

DeepSeek · Released Sep 10, 2026

DeepSeek V4.1 Flash

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...

ReasoningOpen weightsVision
  • Top 10%OTIS Mock AIME
  • Top 14%GPQA Diamond
  • Top 20%WebDev Arena
  • Top 21%Chess Puzzles
Compare in showdown → OpenRouter ↗ All DeepSeek models
Released
Sep 10 2026
Context window
1M 944K out
Input / 1M tokens
$0.30 from Free
Output / 1M tokens
$1.20 from Free

Where to run it

92 providers compared

Free to try on SenseNova (China), Nvidia, OpenCode, NaN — free endpoints are often limited-time and rate-limited. Included in SCNet Token Plan, Alibaba Token Plan, Alibaba Token Plan (China), OpenCode Go. Cheapest: engy at $0.04 / $0.08 per 1M input / output tokens — 96% less than the priciest option.

ProviderInputOutputCache readContextMax outputUptimevs. best
SenseNova (China)free · may be limited-time Free Free Free1M66K— Free
Nvidiafree · may be limited-time Free Free —1M384K— Free
OpenCodefree · may be limited-time Free Free Free200K32K— Free
NaNfree · may be limited-time Free Free —1M384K— Free
SCNet Token Plansubscription plan Plan Plan Plan1M384K— Plan
Alibaba Token Plansubscription plan Plan Plan Plan1M384K— Plan
Alibaba Token Plan (China)subscription plan Plan Plan Plan1M384K— Plan
OpenCode Gosubscription plan Plan Plan Plan1M384K— Plan
engy $0.04 $0.08 $0.0081M66K— Cheapest
DecartFP4 $0.09 $0.18 $0.0181M262K100%24h +125%
Sail Researchus · FP4 $0.09 $0.25 $0.0061M384K100%24h +160%
Sail ResearchFP4 $0.09 $0.25 $0.0061M384K100%24h +160%
ZenMux $0.075 $0.30 $0.0021M384K— +162%
DeepInfraFP8 $0.11 $0.34 $0.0031M131K90.5%24h +236%
Subconscious $0.14 $0.28 $0.0035M384K— +250%
OpenInferenceFP4 $0.07 $0.50 $0.0081M944K99.8%24h +255%
Relace $0.07 $0.50 $0.0081M944K99.8%24h +255%
Kenari $0.16 $0.31 $0.0041M384K— +292%
DeepInfraFP8 $0.14 $0.42 $0.0041M131K100%24h +320%
Standard Compute $0.14 $0.42 $0.0041M50K— +320%
AtlasCloudFP8 $0.14 $0.54 $0.0141M393K100%24h +372%
DevPass (LLM Gateway) $0.14 $0.54 $0.0031.05M384K— +372%
InferenceNetus · FP8 $0.10 $0.71 $0.0081.04M393K100%24h +412%
InferenceNetFP8 $0.10 $0.71 $0.0081.04M393K100%24h +412%
StreamLakeFP8 $0.15 $0.59 $0.0031.02M384K100%24h +414%
302.AI $0.15 $0.60 $0.0031M384K— +425%
ClinePass $0.15 $0.60 $0.0031M384K— +425%
Vultr $0.15 $0.60 —1M384K— +425%
Tempr Gateway $0.15 $0.60 $0.0031M384K— +425%
Ollama Cloud $0.15 $0.60 $0.0031M384K— +425%
Merge Gateway $0.15 $0.60 $0.0031M384K— +425%
CommandCode $0.16 $0.58 $0.0161M384K— +430%
AIHubMix $0.15 $0.62 $0.0031M384K— +443%
CoreWeaveFP8 $0.15 $0.65 $0.0021M944K100%24h +450%
Reka $0.10 $0.84 $0.0071M393K94.3%24h +477%
above.dev $0.17 $0.66 $0.0031M384K— +477%
Cortecs $0.20 $0.60 $0.0041M393K— +501%
IteraCompute $0.17 $0.70 $0.0051M393K— +505%
Wafermxfp4 · MXFP4 $0.19 $0.65 $0.0121M944K100%24h +510%
GMICloudFP8 $0.18 $0.72 $0.0041.05M944K100%24h +530%
DeepInfrapriority · FP8 $0.21 $0.63 $0.0061M131K84.1%24h +530%
Arcee $0.22 $0.66 $0.0071M384K— +560%
NovitaFP8 $0.20 $0.78 $0.0041M393K99.9%24h +582%
MorphFP8 $0.28 $0.60 $0.0251M944K98.8%24h +626%
Fireworksspot $0.21 $0.84 $0.0041M944K100%24h +635%
Phala $0.21 $0.84 $0.0041M944K100%24h +635%
ai& $0.30 $0.60 $0.021M384K— +650%
DigitalOcean $0.23 $0.90 $0.0061M944K100%24h +688%
Boundless $0.20 $1.00 $0.011M384K— +700%
Vancine $0.24 $0.96 $0.0051M384K— +740%
Melious $0.23 $1.16 $0.0121M384K— +827%
MakoraFP8 $0.26 $1.17 $0.0061M944K99.9%24h +875%
CoralBricks $0.25 $1.20 $0.0051M393K— +875%
AKI.IO $0.28 $1.12 $0.111M82K— +881%
GreenPT $0.26 $1.28 $0.0131M384K— +923%
CrusoeFP8 $0.29 $1.20 $0.0071M944K100%24h +935%
Alibaba (China) $0.30 $1.19 $0.0151M384K— +942%
NebiusFP8 $0.30 $1.20 $0.011.05M943K100%24h +950%
PrimeIntellect $0.30 $1.20 $0.031M131K100%24h +950%
BaiduFP8 $0.30 $1.20 $0.0061M393K100%24h +950%
BaseTenus $0.30 $1.20 $0.0071M262K100%24h +950%
Together $0.30 $1.20 $0.0061M944K100%24h +950%
SiliconFlowFP8 $0.30 $1.20 $0.0061M393K100%24h +950%
Modal $0.30 $1.20 $0.031M944K100%24h +950%
BaseTen $0.30 $1.20 $0.0071M262K100%24h +950%
ParasailFP8 $0.30 $1.20 $0.0061M944K100%24h +950%
VeniceFP8 $0.30 $1.20 $0.0081M131K100%24h +950%
Fireworks $0.30 $1.20 $0.0061M944K99.2%24h +950%
Googleglobal $0.30 $1.20 $0.031M944K98.5%24h +950%
Venice AI $0.30 $1.20 $0.0081M131K— +950%
Kilo Gateway $0.30 $1.20 $0.0061M944K— +950%
LLM Gateway $0.30 $1.20 $0.0061M393K— +950%
Nebius Token Factory $0.30 $1.20 $0.301.05M1.05M— +950%
Together AI $0.30 $1.20 $0.0061M384K— +950%
Fireworks AI $0.30 $1.20 $0.0061M384K— +950%
Novita AI $0.30 $1.20 $0.0061M393K— +950%
Azure $0.30 $1.20 $0.0061M128K— +950%
Prime Inference $0.30 $1.20 $0.031M131K— +950%
Neon $0.30 $1.20 $0.031M384K— +950%
Azure Cognitive Services $0.30 $1.20 $0.0061M128K— +950%
CrossModel $0.30 $1.20 $0.0061M384K— +950%
Hugging Face $0.30 $1.20 —1M384K— +950%
Ofox $0.30 $1.20 $0.0061M384K— +950%
OpenCode $0.30 $1.20 $0.0061M384K— +950%
EmpirioLabs AI $0.30 $1.20 $0.301M393K— +950%
Vivgrid $0.31 $1.23 $0.011M384K— +980%
Charm Hyper $0.33 $1.31 $0.031M262K— +1050%
Alibaba $0.33 $1.32 $0.0331M393K100%24h +1055%
AI/ML API $0.39 $1.56 $0.0081M384K— +1265%
Requesty $0.50 $1.50 $0.051M393K— +1400%
Synthetic $0.60 $1.20 $0.03524K66K— +1400%
TensorX $0.50 $1.50 $0.131M384K— +1400%
Fireworksus $0.45 $1.80 $0.0091M944K100%24h +1475%
NanoGPT $0.65 $1.45 $0.131M384K— +1600%
Tinfoil $0.65 $1.45 $0.131M384K— +1600%
Scaleway $0.67 $2.02 $0.13256K33K— +1916%
Eden AI $0.67 $2.02 $0.14256K384K— +1922%
BaseTenfast $0.60 $2.40 $0.0141M131K99.7%24h +2000%
Vercel AI Gateway $0.60 $2.40 $0.0141M33K— +2000%
Inco $0.60 $2.40 $0.0121M384K— +2000%
Thinking Machines $0.60 $3.60 $0.12262K262K— +2600%

Value

Price vs. performance

On the value frontierNo cheaper model beats DeepSeek V4.1 Flash on GPQA Diamond.
23.2%47.6%72.0%96.4% $0.001$0.01$0.10$1.00$10.00$100.00 Gemini 4 Argon (Google) — 96.4% · $2.00/1M in Claude Haiku 5.5 (Anthropic) — 89.6% · $0.10/1M in Mistral Large 4 (Mistral) — 88.1% · $1.36/1M in GPT-6.1 Sol (OpenAI) — 95.4% · $2.00/1M in Claude Sonnet 5.5 (Anthropic) — 95.6% · $2.00/1M in GPT-6 Luna (OpenAI) — 90.5% · $0.10/1M in GPT-6 Sol (OpenAI) — 94.3% · $2.00/1M in Claude Opus 5.5 (Anthropic) — 90.6% · $4.00/1M in Grok 4.7 (xAI) — 92.7% · $2.00/1M in GPT-6 Astra (OpenAI) — 95.8% · $10.00/1M in Qwen3.8 Max (0902) (Qwen) — 92.7% · $2.00/1M in Gemini 3.8 Flash (Google) — 95.4% · $0.82/1M in GLM 5.3 Flash (Z.ai) — 90.1% · $0.005/1M in GLM 5.3 (Z.ai) — 90.9% · $0.079/1M in Gemini 3.7 Flash (Google) — 94.8% · $0.75/1M in Grok 4.6 (xAI) — 94.0% · $2.00/1M in Qwen3.7 Flash (Qwen) — 82.3% · $0.03/1M in Claude Opus 5 (Anthropic) — 93.9% · $5.00/1M in Gemini 3.6 Flash (Google) — 94.1% · $0.75/1M in Gemini 3.5 Flash Lite (Google) — 83.3% · $0.30/1M in Kimi K3 (Moonshot AI) — 93.1% · $0.24/1M in GPT-5.6 Luna (OpenAI) — 91.6% · $0.20/1M in GPT-5.6 Terra (OpenAI) — 93.3% · $2.00/1M in GPT-5.6 Sol (OpenAI) — 93.5% · $4.00/1M in Grok 4.5 (xAI) — 93.4% · $2.00/1M in Claude Sonnet 5 (Anthropic) — 90.5% · $2.00/1M in GLM 5.2 (Z.ai) — 91.9% · $0.034/1M in Kimi K2.7 Code (Moonshot AI) — 87.9% · $0.67/1M in Claude Fable 5 (Anthropic) — 85.9% · $10.00/1M in Qwen3.7 Plus (Qwen) — 87.9% · $0.32/1M in MiniMax M3 (MiniMax) — 90.9% · $0.30/1M in Claude Opus 4.8 (Anthropic) — 91.0% · $5.00/1M in Qwen3.7 Max (Qwen) — 90.9% · $1.48/1M in Gemini 3.5 Flash (Google) — 92.8% · $1.50/1M in Gemini 3.1 Flash Lite (Google) — 81.8% · $0.25/1M in Grok 4.3 (xAI) — 88.8% · $1.25/1M in Qwen3.5 Plus 2026-04-20 (Qwen) — 84.9% · $0.30/1M in Qwen3.6 Flash (Qwen) — 83.3% · $0.19/1M in Qwen3.6 35B A3B (Qwen) — 84.9% · $0.10/1M in Qwen3.6 27B (Qwen) — 85.9% · $0.25/1M in GPT-5.5 (OpenAI) — 90.7% · $5.00/1M in Kimi K2.6 (Moonshot AI) — 90.8% · $0.65/1M in Claude Opus 4.7 (Anthropic) — 90.1% · $5.00/1M in GLM 5.1 (Z.ai) — 89.9% · $1.40/1M in Gemma 4 26B A4B (Google) — 73.2% · $0.09/1M in Gemma 4 31B (Google) — 75.8% · $0.20/1M in Qwen3.6 Plus (Qwen) — 88.4% · $0.33/1M in GPT-5.4 Nano (OpenAI) — 78.5% · $0.20/1M in GPT-5.4 Mini (OpenAI) — 86.9% · $0.75/1M in Mistral Small 4 (Mistral) — 47.5% · $0.15/1M in Qwen3.5-9B (Qwen) — 79.0% · $0.08/1M in GPT-5.4 Pro (OpenAI) — 94.6% · $30.00/1M in GPT-5.4 (OpenAI) — 93.3% · $2.50/1M in Gemini 3.1 Flash Lite Preview (Google) — 81.8% · $0.25/1M in Qwen3.5-35B-A3B (Qwen) — 83.5% · $0.14/1M in Gemini 3.1 Pro Preview (Google) — 94.4% · $2.00/1M in Claude Sonnet 4.6 (Anthropic) — 87.4% · $3.00/1M in Qwen3.5 397B A17B (Qwen) — 86.4% · $0.50/1M in GLM 5 (Z.ai) — 87.8% · $1.00/1M in Claude Opus 4.6 (Anthropic) — 90.5% · $5.00/1M in GLM 4.7 Flash (Z.ai) — 60.5% · $0.061/1M in GLM 4.7 (Z.ai) — 83.3% · $0.54/1M in Gemini 3 Flash Preview (Google) — 89.4% · $0.50/1M in GPT-5.2 (OpenAI) — 91.4% · $1.75/1M in Ministral 3 8B 2512 (Mistral) — 27.2% · $0.15/1M in Ministral 3 3B 2512 (Mistral) — 25.3% · $0.10/1M in Mistral Large 3 2512 (Mistral) — 51.3% · $0.50/1M in Claude Opus 4.5 (Anthropic) — 86.1% · $5.00/1M in GPT-5.1 (OpenAI) — 87.6% · $1.25/1M in Claude Haiku 4.5 (Anthropic) — 71.2% · $1.00/1M in Claude Sonnet 4.5 (Anthropic) — 82.3% · $3.00/1M in GPT-5 (OpenAI) — 86.2% · $1.25/1M in GPT-5 Mini (OpenAI) — 75.0% · $0.25/1M in GPT-5 Nano (OpenAI) — 69.4% · $0.05/1M in gpt-oss-120b (OpenAI) — 75.8% · $0.15/1M in gpt-oss-20b (OpenAI) — 60.8% · $0.018/1M in Claude Opus 4.1 (Anthropic) — 77.3% · $15.00/1M in Qwen3 30B A3B Instruct 2507 (Qwen) — 55.6% · $0.09/1M in Qwen3 235B A22B Thinking 2507 (Qwen) — 80.0% · $0.45/1M in Qwen3 235B A22B Instruct 2507 (Qwen) — 70.7% · $0.09/1M in Gemini 2.5 Pro (Google) — 85.3% · $1.25/1M in Gemini 2.5 Pro Preview 06-05 (Google) — 85.3% · $1.25/1M in Qwen3 30B A3B (Qwen) — 61.7% · $0.12/1M in Qwen3 14B (Qwen) — 63.8% · $0.12/1M in Qwen3 32B (Qwen) — 65.7% · $0.08/1M in o3 (OpenAI) — 81.8% · $2.00/1M in o4 Mini (OpenAI) — 79.6% · $1.10/1M in GPT-4.1 (OpenAI) — 66.9% · $2.00/1M in GPT-4.1 Mini (OpenAI) — 65.8% · $0.40/1M in GPT-4.1 Nano (OpenAI) — 48.9% · $0.10/1M in Gemma 3 4B (Google) — 23.2% · $0.04/1M in Gemma 3 12B (Google) — 39.5% · $0.05/1M in Gemma 3 27B (Google) — 47.7% · $0.08/1M in Qwen-Plus (Qwen) — 48.1% · $0.26/1M in o3 Mini (OpenAI) — 77.0% · $1.10/1M in Phi 4 (Microsoft) — 56.1% · $0.07/1M in o1 (OpenAI) — 76.8% · $15.00/1M in Llama 3.3 70B Instruct (Meta) — 47.4% · $0.10/1M in GPT-4o (2024-11-20) (OpenAI) — 49.2% · $2.50/1M in Mistral Large 2407 (Mistral) — 51.3% · $2.00/1M in Llama 3.2 1B Instruct (Meta) — 23.9% · $0.027/1M in GPT-4o (2024-08-06) (OpenAI) — 49.2% · $2.50/1M in Llama 3.1 70B Instruct (Meta) — 44.2% · $0.40/1M in Llama 3.1 8B Instruct (Meta) — 27.0% · $0.05/1M in GPT-4o-mini (OpenAI) — 37.7% · $0.15/1M in GPT-4o-mini (2024-07-18) (OpenAI) — 37.7% · $0.15/1M in Gemma 2 27B (Google) — 36.5% · $0.65/1M in GPT-4o (OpenAI) — 49.2% · $2.50/1M in GPT-4o (2024-05-13) (OpenAI) — 49.2% · $5.00/1M in GPT-4 Turbo (OpenAI) — 46.6% · $10.00/1M in Mistral Large (Mistral) — 51.3% · $2.00/1M in GPT-3.5 Turbo (older v0613) (OpenAI) — 28.0% · $1.00/1M in GPT-3.5 Turbo (OpenAI) — 28.0% · $0.50/1M in GPT-4 (OpenAI) — 35.7% · $30.00/1M in DeepSeek V4.1 Flash 1017 (DeepSeek) — 93.2% · $0.15/1M in DeepSeek V4 Pro 0813 (DeepSeek) — 91.7% · $0.66/1M in DeepSeek V4 Flash 0731 (DeepSeek) — 91.0% · $0.044/1M in DeepSeek V4 Pro 0423 (DeepSeek) — 91.7% · $0.44/1M in DeepSeek V4 Flash 0423 (DeepSeek) — 91.0% · $0.091/1M in R1 0528 (DeepSeek) — 76.3% · $0.50/1M in DeepSeek V3 (DeepSeek) — 71.2% · $0.26/1M in DeepSeek V4.1 Flash (DeepSeek) — 93.2% · $0.30/1M in DeepSeek V4.1 Flash

DeepSeek V4.1 Flash Other DeepSeek Other labs Value frontier · GPQA Diamond vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.

Benchmarks

18 benchmark scores

BenchmarkScoreRankLeader
FrontierCodeSoftware engineering · Mergeable fixes for hard open-source issues 43.9% #16of 41 Claude Opus 5.554.6%
SciCodeSoftware engineering · Research-coding problems from the natural sciences 51.8% #39of 102 Claude Opus 5.566.9%
WeirdML v3Software engineering · Unfamiliar ML and data tasks with vague goals 5.9% #18of 22 GPT-6 Astra42.2%
APEX-AgentsAgents & computer use · Long professional tasks in banking, consulting and law 39.5% #40of 51 Gemini 4 Argon82.4%
GDP.pdfWriting & content · Answer questions about real professional PDFs 19.8% #22of 38 GPT-6.1 Sol35.0%
SimpleQA VerifiedWriting & content · Factual accuracy on 1,000 short questions 42.9% #39of 79 Gemini 4 Argon76.0%
WebDev ArenaDesign & visual · People vote on which model builds the better website (Elo) 1614 #18of 90 Claude Opus 5.51820
Furniture AssemblyDesign & visual · Spot mistakes in photos of IKEA builds 34.2% #20of 34 Claude Opus 5.583.3%
GPQA DiamondReasoning & knowledge · PhD-level biology, chemistry and physics questions 93.2% #17of 122 Gemini 4 Argon96.4%
ARC-AGI-2Reasoning & knowledge · Few-shot abstract reasoning on grid puzzles 72.9% #19of 75 GPT-6 Astra95.0%
ARC-AGI-1Reasoning & knowledge · Pattern induction from input–output examples 94.5% #16of 75 Gemini 4 Argon98.5%
CritPtReasoning & knowledge · Open-ended, research-level physics problems 14.3% #40of 111 GPT-5.6 Sol32.3%
Chess PuzzlesReasoning & knowledge · Find the single best move in 100 new puzzles 48.0% #17of 83 GPT-6 Astra76.0%
LMCAReasoning & knowledge · Judge the quality of conceptual arguments like experts 47.0% #32of 123 Claude Sonnet 5.568.3%
FrontierMathMaths · Expert-written problems, undergrad to early research (tiers 1–3) 71.2% #25of 87 GPT-6.1 Sol93.7%
FrontierMath Tier 4Maths · Exceptionally hard research-level problems 46.3% #19of 64 GPT-6.1 Sol100.0%
ProofBenchMaths · Graduate maths proofs verified in Lean 4 54.0% #27of 70 Claude Sonnet 5.5100.0%
OTIS Mock AIMEMaths · Competition-style problems harder than MATH Level 5 99.4% #12of 120 Gemini 4 Argon100.0%

Specs

Details

Model ID
deepseek/deepseek-v4.1-flash
Developer
DeepSeek
Release date
Sep 10, 2026 ·
Context window
1,048,576 tokens
Max output
943,718 tokens
API price
$0.30 / $1.20 per 1M input / output tokens
Providers
92
Input types
text, image
Reasoning
Yes
Tool calling
Yes
Open weights
Yes
Free tier
No

Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.