Patchwire

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 21%WebDev Arena
  • Top 23%OTIS Mock AIME
  • Top 25%Chess Puzzles
  • Top 26%ARC-AGI-1
Compare in showdown → OpenRouter ↗ All DeepSeek models
Released
Sep 10 2026
Context window
1M 944K out
Input / 1M tokens
$0.056
Output / 1M tokens
$0.12

Where to run it

28 providers compared

Cheapest: OpenInference at $0.056 / $0.12 per 1M input / output tokens — 93% less than the priciest option.

ProviderInputOutputCache readContextMax outputUptimevs. best
OpenInferenceFP4 $0.056 $0.12 $0.0021M944K99.9%24h Cheapest
DecartFP4 $0.09 $0.18 $0.0181M262K100%24h +56%
Sail Researchus · FP4 $0.10 $0.15 $0.0071M384K100%24h +57%
Sail ResearchFP4 $0.10 $0.15 $0.0071M384K100%24h +57%
DeepInfraFP8 $0.11 $0.34 $0.0031M131K92.1%24h +133%
Relace $0.07 $0.50 $0.0081M944K100%24h +147%
DeepInfraFP8 $0.14 $0.42 $0.0041M131K100%24h +192%
MorphFP8 $0.084 $0.60 $0.0071M944K99.7%24h +196%
AtlasCloudFP8 $0.14 $0.54 $0.0141M393K100%24h +228%
InferenceNetFP8 $0.10 $0.71 $0.0081.04M393K100%24h +256%
StreamLakeFP8 $0.15 $0.59 $0.0031.02M384K97.3%24h +257%
CoreWeaveFP8 $0.15 $0.65 $0.0021M944K100%24h +282%
Wafermxfp4 · MXFP4 $0.19 $0.65 $0.0061M944K100%24h +324%
DeepInfrapriority · FP8 $0.21 $0.63 $0.0061M131K100%24h +337%
GMICloudFP8 $0.18 $0.72 $0.0041.05M944K99.9%24h +337%
NovitaFP8 $0.20 $0.78 $0.0041M393K97.4%24h +374%
Fireworksno tool calling $0.21 $0.84 $0.0041M944K100%24h +410%
Phala $0.21 $0.84 $0.0041M944K98.5%24h +410%
Ionstream $0.27 $0.75 $0.0061M944K99.9%24h +442%
DigitalOcean $0.23 $0.90 $0.0061M944K99.7%24h +447%
MakoraFP8 $0.26 $1.17 $0.0061M944K99.9%24h +577%
BaiduFP8 $0.30 $1.20 $0.0061M393K100%24h +629%
BaseTenus $0.30 $1.20 $0.0071M262K100%24h +629%
Together $0.30 $1.20 $0.0061M944K100%24h +629%
SiliconFlowFP8 $0.30 $1.20 $0.0061M393K100%24h +629%
Modal $0.30 $1.20 $0.031M944K100%24h +629%
BaseTen $0.30 $1.20 $0.0071M262K100%24h +629%
Fireworks $0.30 $1.20 $0.0061M944K99.8%24h +629%
NebiusFP8 $0.30 $1.20 —1.05M943K98.5%24h +629%
VeniceFP8 $0.30 $1.20 $0.0081M131K97.5%24h +629%
PrimeIntellect $0.30 $1.20 $0.031M131K95.5%24h +629%
ParasailFP8 $0.30 $1.20 $0.0061M944K72.1%24h +629%
Alibaba $0.33 $1.32 $0.0331M393K100%24h +702%
Fireworksus $0.45 $1.80 $0.0091M944K100%24h +994%
BaseTenfast $0.60 $2.40 $0.0141M131K99.9%24h +1358%

Value

Price vs. performance

1 model scores higher for the same price or lesson GPQA Diamond, e.g. GLM 5.3 Flash.
25.3%49.0%72.7%96.4% $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% · $0.68/1M 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% · $0.047/1M 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% · $0.62/1M 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% · $0.97/1M 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% · $0.10/1M 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% · $0.15/1M 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% · $0.39/1M in GLM 5 (Z.ai) — 87.8% · $0.60/1M 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 DeepSeek V4.1 Flash 1017 (DeepSeek) — 89.8% · $0.30/1M in DeepSeek V4 Pro 0813 (DeepSeek) — 91.7% · $0.66/1M in DeepSeek V4 Flash 0731 (DeepSeek) — 91.0% · $0.44/1M in DeepSeek V4 Pro 0423 (DeepSeek) — 91.7% · $0.95/1M in DeepSeek V4 Flash 0423 (DeepSeek) — 91.0% · $0.091/1M in R1 0528 (DeepSeek) — 76.3% · $0.50/1M in DeepSeek V4.1 Flash (DeepSeek) — 89.8% · $0.056/1M 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 93 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% #38of 66 Gemini 4 Argon76.0%
WebDev ArenaDesign & visual · People vote on which model builds the better website (Elo) 1614 #18of 88 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 89.8% #41of 92 Gemini 4 Argon96.4%
ARC-AGI-2Reasoning & knowledge · Few-shot abstract reasoning on grid puzzles 72.9% #19of 63 GPT-6 Astra95.0%
ARC-AGI-1Reasoning & knowledge · Pattern induction from input–output examples 94.5% #16of 63 Gemini 4 Argon98.5%
CritPtReasoning & knowledge · Open-ended, research-level physics problems 14.3% #40of 96 GPT-5.6 Sol32.3%
Chess PuzzlesReasoning & knowledge · Find the single best move in 100 new puzzles 48.0% #17of 70 GPT-6 Astra76.0%
LMCAReasoning & knowledge · Judge the quality of conceptual arguments like experts 47.0% #32of 96 Claude Sonnet 5.568.3%
FrontierMathMaths · Expert-written problems, undergrad to early research (tiers 1–3) 67.4% #29of 72 GPT-6.1 Sol93.7%
FrontierMath Tier 4Maths · Exceptionally hard research-level problems 26.8% #32of 62 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 98.3% #20of 90 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
$0.056 / $0.12 per 1M input / output tokens
Providers
28
Input types
text, image
Reasoning
Yes
Tool calling
Yes
Open weights
Yes
Free tier
No

Release date, prices and providers from OpenRouter's catalog; buying directly from a provider can cost a little differently. 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.