Singularity Logs

THE MODEL, IN DETAIL / DeepSeek

DeepSeek V4.1 Flash (max)

deepseek/deepseek-v4.1-flashOpen weightsReasoningmax configuration

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...

OpenRouter
Source-linked model intelligenceCatalog added 10 Sept 2026Specifications observed 28 Oct 2026

Specifications and providers describe DeepSeek: DeepSeek V4.1 Flash. Evaluation scores retain the exact max configuration.

GPQA Diamond

89.8%

Source-reported

Context window

1M

131.1K max output tokens

Input price

$0.14

USD / million input tokens

Output price

$0.42

USD / million output tokens

Inference providers

33

41 provider routes observed

Measured output speed

—

No model-level measurement

01 / PERFORMANCE

A clearer view of capability.

Read the score, understand the context, and explore where this model sits among its peers.

Performance fingerprint

Individual published accuracy scores · not a composite index

Individual benchmark accuracy. Axes represent different tasks, not a composite index.FrontierMath Ti…FrontierMath Ti…GPQA DiamondOTIS Mock AIME …SimpleQA VerifiedFrontierMath Tier 4 v2: 26.8FrontierMath Tiers 1–3 v2: 67.4GPQA Diamond: 89.8OTIS Mock AIME 2024–2025: 98.3SimpleQA Verified: 42.9Each axis: 0–100% · Individual evaluations

Performance meets price

GPQA Diamond · same published source and version

Higher score · lower cost70$077.5$2.87585$5.7592.5$8.625100$11.5Gemini 4 Argon (high) GPQA Diamond: 96.4 Input: $2/M tokensGPT-6 Astra (max) GPQA Diamond: 95.8 Input: $10/M tokensClaude Sonnet 5.5 (max) GPQA Diamond: 95.6 Input: $2/M tokensDeepSeek V4.1 Flash 1017 (max) GPQA Diamond: 93.2 Input: $0.15/M tokensDeepSeek V4 Pro 0813 (max) GPQA Diamond: 91.7 Input: $0.66/M tokensDeepSeek V4 Flash 0731 (max) GPQA Diamond: 91 Input: $0.119/M tokensGPT-6 Luna (max) GPQA Diamond: 90.5 Input: $0.1/M tokensClaude Opus 4.7 (xhigh) GPQA Diamond: 90.2 Input: $5/M tokensGLM-5.3-Flash (max) GPQA Diamond: 90.2 Input: $0.15/M tokensGLM-5.1 GPQA Diamond: 89.9 Input: $1.4/M tokensGPT-5.4 (high) GPQA Diamond: 89.9 Input: $2.5/M tokensGPT-5.6 Sol (low) GPQA Diamond: 89.9 Input: $4/M tokensDeepSeek V4.1 Flash (max) GPQA Diamond: 89.8 Input: $0.14/M tokensDeepSeek V4.1 Flash (max)Claude Haiku 5.5 (max) GPQA Diamond: 89.6 Input: $0.1/M tokensGemini 3 Flash Preview GPQA Diamond: 89.4 Input: $0.5/M tokensGPT-5.4 (medium) GPQA Diamond: 88.9 Input: $2.5/M tokensInput price · USD / million tokens
Google DeepMindOpenAIAnthropicDeepSeekZ.ai (Zhipu AI)

In good company

GPQA Diamond · Epoch AI · benchmark data

96.4
Google DeepMind
95.8
OpenAI
95.6
Anthropic
93.2
DeepSeek
91.7
DeepSeek
91
DeepSeek
90.5
OpenAI
90.2
Anthropic
90.2
Z.ai (Zhipu AI)
89.8
This model

Rank #40 in this published cohort. 325 models in the source cohort. Showing selected nearby models. Evaluation settings can differ.

Evidence, by task.

Coverage is not a capability score.

5published results
1 evaluation source
Reasoning5 evaluations
CodingAwaiting evidence
Mathematics3 evaluations
VisionAwaiting evidence
AgenticAwaiting evidence
Long contextAwaiting evidence

Documented features, task evaluations, and preference rankings describe different things. Missing coverage does not imply a model cannot perform a task.

Explore our methodology

02 / BENCHMARK EXPLORER

The numbers behind the model.

Original results, exact versions, and a direct path to the evidence behind every score.

5 published results
020406080100FrontierMath Tier 4 v2: 26.8% · Epoch AI · independent runs · Epoch AI · benchmark data26.8%FrontierMath Tie…Higher is betterFrontierMath Tiers 1–3 v2: 67.4% · Epoch AI · independent runs · Epoch AI · benchmark data67.4%FrontierMath Tie…Higher is betterGPQA Diamond: 89.8% · Epoch AI · independent runs · Epoch AI · benchmark data89.8%GPQA DiamondHigher is betterOTIS Mock AIME 2024–2025: 98.3% · Epoch AI · independent runs · Epoch AI · benchmark data98.3%OTIS Mock AIME 2…Higher is betterSimpleQA Verified: 42.9% · Epoch AI · independent runs · Epoch AI · benchmark data42.9%SimpleQA VerifiedHigher is better

5 percentage-based evaluations. Each benchmark measures a different task; compare results within the same evaluation and protocol.

Published benchmark results for DeepSeek V4.1 Flash (max)
BenchmarkScoreVersion & metricSourcePublishedEvidence
Epoch AI · independent runsAccuracy · Higher is betterEpoch AI · benchmark dataSource-reportedNot available
Epoch AI · independent runsAccuracy · Higher is betterEpoch AI · benchmark dataSource-reportedNot available
Epoch AI · independent runsAccuracy · Higher is betterEpoch AI · benchmark dataSource-reportedNot available
Epoch AI · independent runsAccuracy · Higher is betterEpoch AI · benchmark dataSource-reportedNot available
Epoch AI · independent runsAccuracy · Higher is betterEpoch AI · benchmark dataSource-reportedNot available

03 / COST & VALUE

Know what your workload costs.

Explore token prices, see where the spend goes, and model a workload of your own.

Input$0.14per million tokens
Output$0.42per million tokens
Cache read$0.0042per million tokens
Cache write—per million tokens

Workload cost calculator

Change the numbers. See the trade-offs.

Token estimate only. Excludes cache writes, tools, and other provider fees. Actual token usage and provider limits vary.

Your estimated spend

1,000 requests · 11M tokens

$1.82estimated total
Uncached input$1.4
Cached input$0
Output$0.42
Per request$0.0018
Without cache discount$1.82
Estimated cache savings$0

04 / INFERENCE NETWORK

One model. Different ways to run it.

Compare inference routes by price, context, quantization, and reported availability.

33 providers · 41 routes
Provider routes for DeepSeek V4.1 Flash (max), observed 28 Oct 2026
Provider / routeInput / MOutput / MCache / MContextOutput limitSpeedLatencyAvailability · 1dRates
OOpenInferenceFP4$0.0014$0.368$0.00131M943.7K——100%
MMorphFP8$0.044$0.383$0.0041M943.7K——100%
RRelaceQuantization not disclosed$0.07$0.5$0.0081M943.7K——100%
DDecartFP4$0.09$0.18$0.0181M262.1K——100%
SSail ResearchFP4$0.09$0.25$0.0061M384K——100%
SSail ResearchFP4$0.09$0.25$0.0061M384K——100%
IInferenceNetFP8$0.103$0.6$0.0081M393.2K——100%
IInferenceNetFP8$0.103$0.6$0.0081M393.2K——100%
RRekaQuantization not disclosed$0.105$0.84$0.0071M393.2K——99.24%
DDeepInfraFP8 · flex$0.112$0.336$0.00341M131.1K——98.09%
CCoreWeaveFP8$0.13$0.65$0.0021M943.7K——99.1%
AAtlasCloudFP8$0.135$0.54$0.01351M393.2K——99.93%
BBaiduFP8$0.1398$0.5592$0.00281M393.2K——100%
DDeepInfraFP8$0.14$0.42$0.00421M131.1K——100%
SStreamLakeFP8$0.147$0.588$0.00291M384K——99.93%
MModelRunFP4$0.17$0.67$0.0061M131.1K——100%
GGMICloudFP8$0.18$0.72$0.00361M943.7K——99.51%
WWaferMXFP4$0.19$0.65$0.0121M943.7K——100%
NNovitaFP8$0.195$0.78$0.00391M393.2K——100%
MMancer 2FP8$0.2$1—1M943.7K——97.37%
DDeepInfraFP8 · priority$0.21$0.63$0.00631M131.1K——69.29%
FFireworksQuantization not disclosed$0.21$0.84$0.00421M943.7K——100%
PPhalaQuantization not disclosed$0.21$0.84$0.00421M943.7K——100%
DDigitalOceanQuantization not disclosed$0.225$0.9$0.0061M943.7K——100%
MMakoraFP8$0.26$1.17$0.00581M943.7K——99.93%
CCrusoeFP8$0.29$1.2$0.0071M943.7K——100%
GGoogleQuantization not disclosed$0.3$1.2$0.031M943.7K——98.45%
NNebiusFP8$0.3$1.2$0.011M943.2K——100%
PPrimeIntellectQuantization not disclosed$0.3$1.2$0.0061M131.1K——100%
CCohereQuantization not disclosed$0.3$1.2$0.0031M384K——99.93%
BBaseTenQuantization not disclosed$0.3$1.2$0.0071M262.1K——100%
TTogetherQuantization not disclosed$0.3$1.2$0.0061M943.7K——100%
SSiliconFlowFP8$0.3$1.2$0.0061M393.2K——99.93%
MModalQuantization not disclosed$0.3$1.2$0.031M943.7K——99.92%
BBaseTenQuantization not disclosed$0.3$1.2$0.0071M262.1K——100%
PParasailFP8$0.3$1.2$0.0061M943.7K——100%
FFireworksQuantization not disclosed$0.3$1.2$0.0061M943.7K——99.02%
VVeniceFP8$0.3$1.2$0.00751M131.1K——100%
AAlibabaQuantization not disclosed$0.33$1.32$0.0331M393.2K——100%
FFireworksQuantization not disclosed$0.45$1.8$0.0091M943.7K——100%
BBaseTenQuantization not disclosed · priority$0.6$2.4$0.0141M131.1K——54.36%

Snapshot observed 28 Oct 2026. Speed and latency are the reported 30-minute median when available. This is a dated snapshot, not live monitoring.

Provider price comparison

USD per million tokens · input and output rates

InputOutput
OpenInferencefp4
Input
$0.0014
Output
$0.368
Morphfp8
Input
$0.044
Output
$0.383
Relace
Input
$0.07
Output
$0.5
Decartfp4
Input
$0.09
Output
$0.18
Sail Researchfp4
Input
$0.09
Output
$0.25
Sail Researchfp4
Input
$0.09
Output
$0.25
InferenceNetfp8
Input
$0.103
Output
$0.6
InferenceNetfp8
Input
$0.103
Output
$0.6
Reka
Input
$0.105
Output
$0.84
DeepInfrafp8 · flex
Input
$0.112
Output
$0.336

Reported availability

Provider availability over the selected observation window

OpenInference · FP4100%
Morph · FP8100%
Relace100%
Decart · FP4100%
Sail Research · FP4100%
Sail Research · FP4100%
InferenceNet · FP8100%
InferenceNet · FP8100%
Reka99.24%
DeepInfra · flex · FP898.09%

Output speed

Reported 30-minute p50 · tokens per second

No provider throughput measurements were returned in this snapshot.

Response latency

Reported 30-minute p50 · seconds

No provider latency measurements were returned in this snapshot.

Context by provider

Actual route limits can differ from the catalog maximum

OpenInference · FP41M
Morph · FP81M
Relace1M
Decart · FP41M
Sail Research · FP41M
Sail Research · FP41M
InferenceNet · FP81M
InferenceNet · FP81M
Reka1M
DeepInfra · flex · FP81M

05 / CAPABILITIES & MODALITIES

What goes in. What comes out.

A map of documented interfaces and API features, separate from benchmark performance.

INPUT MODALITIES

TextImage
DeepSeek V4.1 Flash (max)Reasoning supported

OUTPUT MODALITIES

Text

Feature support

Listed catalog API parameters and documented pricing features

ReasoningSupported
Tool callingSupported
Tool choiceSupported
Structured outputsSupported
Response formatSupported
Reasoning detailsSupported
Seed controlSupported
Stop sequencesSupported
Prompt cachingSupported
TemperatureSupported

Room to work

Context capacity and completion limits

1Mtotal context tokens
Context window
131.1Kmax output

Output tokens share the total context budget. The maximum completion length is a separate limit, and individual provider routes may have smaller limits.

Catalog context
1,048,576 tokens
Maximum output
131,072 tokens
Top-provider context
1,048,576 tokens

Features vary by route

Check the provider before depending on a specific API feature.

API feature support by provider
Provider routeReasoningToolsStructured outputResponse formatImplicit caching
OpenInference · FP4SupportedSupportedSupportedSupportedSupported
Morph · FP8SupportedSupportedSupportedSupportedSupported
RelaceSupportedSupportedSupportedSupportedSupported
Decart · FP4SupportedSupportedSupportedSupportedSupported
Sail Research · FP4SupportedSupportedSupportedSupportedSupported
Sail Research · FP4SupportedSupportedSupportedSupportedSupported
InferenceNet · FP8SupportedSupportedSupportedSupportedSupported
InferenceNet · FP8SupportedSupportedSupportedSupportedSupported
RekaSupportedSupportedSupportedSupportedSupported
DeepInfra · flex · FP8SupportedSupportedSupportedSupportedSupported
CoreWeave · FP8SupportedSupportedSupportedSupportedSupported
AtlasCloud · FP8SupportedSupportedSupportedSupportedSupported
Baidu · FP8SupportedSupportedSupportedSupportedSupported
DeepInfra · FP8SupportedSupportedSupportedSupportedSupported
StreamLake · FP8SupportedSupportedNot listedSupportedSupported
ModelRun · FP4SupportedSupportedSupportedSupportedSupported
GMICloud · FP8SupportedSupportedNot listedSupportedSupported
Wafer · MXFP4SupportedSupportedSupportedSupportedSupported
Novita · FP8SupportedSupportedNot listedSupportedSupported
Mancer 2 · FP8SupportedSupportedSupportedNot listedNot listed
DeepInfra · priority · FP8SupportedSupportedSupportedSupportedSupported
FireworksSupportedSupportedSupportedSupportedSupported
PhalaSupportedSupportedNot listedSupportedSupported
DigitalOceanSupportedSupportedSupportedSupportedSupported
Makora · FP8SupportedSupportedSupportedSupportedSupported
Crusoe · FP8SupportedSupportedSupportedSupportedSupported
GoogleSupportedSupportedSupportedSupportedSupported
Nebius · FP8SupportedSupportedSupportedSupportedSupported
PrimeIntellectSupportedSupportedSupportedSupportedSupported
CohereSupportedSupportedSupportedSupportedSupported
BaseTenSupportedSupportedSupportedSupportedSupported
TogetherSupportedSupportedSupportedSupportedSupported
SiliconFlow · FP8SupportedSupportedNot listedSupportedSupported
ModalSupportedSupportedSupportedSupportedSupported
BaseTenSupportedSupportedSupportedNot listedSupported
Parasail · FP8SupportedSupportedSupportedSupportedSupported
FireworksSupportedSupportedSupportedSupportedSupported
Venice · FP8SupportedSupportedSupportedSupportedSupported
AlibabaSupportedSupportedNot listedSupportedSupported
FireworksSupportedSupportedSupportedSupportedSupported
BaseTen · prioritySupportedSupportedSupportedSupportedSupported

06 / UNDER THE HOOD

The complete specification sheet.

Exact identities, model architecture, limits, and the defaults that shape a request.

Identity & architecture

Developer
DeepSeek
Exact identity
deepseek-v4.1-flash_max
Subject
Model Configuration
Access
Open weights
License
Not disclosed
Parameters
Not disclosed
Tokenizer
DeepSeek
Instruction format
Not disclosed

Reasoning & controls

Reasoning
Supported
Mandatory reasoning
No
Reasoning by default
Enabled
Published configuration
max
Supported reasoning efforts
max, high, low, none
Default reasoning effort
high
API parameters
22
Provider moderation
No
Quantization variants
fp4, fp8, mxfp4

Dates & limits

Catalog added
10 Sept 2026
Knowledge cutoff
Not disclosed
Catalog expiration
Not documented
Specifications observed
28 Oct 2026
Providers observed
28 Oct 2026
Request limits
Provider-specific / not supplied
Canonical catalog ID
deepseek/deepseek-v4.1-flash-20260910

API parameters & defaults

Availability is catalog-wide. Defaults can vary across providers.

frequency_penaltySupported · default not supplied
include_reasoningSupported · default not supplied
logit_biasSupported · default not supplied
logprobsSupported · default not supplied
max_tokensSupported · default not supplied
min_pSupported · default not supplied
parallel_tool_callsSupported · default not supplied
presence_penaltySupported · default not supplied
reasoningSupported · default not supplied
reasoning_effortSupported · default not supplied
repetition_penaltySupported · default not supplied
response_formatSupported · default not supplied
seedSupported · default not supplied
stopSupported · default not supplied
structured_outputsSupported · default not supplied
temperatureSupported · default not supplied
tool_choiceSupported · default not supplied
toolsSupported · default not supplied
top_aSupported · default not supplied
top_kSupported · default not supplied
top_logprobsSupported · default not supplied
top_pSupported · default not supplied

07 / BUILD WITH THIS MODEL

From exploration to your first request.

Use the documented catalog identifier and keep your API key in an environment variable.

Make an API request

const response = await fetch(
  "https://openrouter.ai/api/v1/chat/completions",
  {
    method: "POST",
    headers: {
      Authorization: `Bearer ${process.env.OPENROUTER_API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      "model": "deepseek/deepseek-v4.1-flash",
      "messages": [
        {
          "role": "user",
          "content": "Explain the trade-offs in this design."
        }
      ],
      "reasoning": {
        "effort": "max"
      }
    }),
  },
);
if (!response.ok) throw new Error(`HTTP ${response.status}`);
const data = await response.json();
console.log(data.choices[0].message.content);

08 / PROVENANCE & HISTORY

Every number has a story.

Follow the source, check the observation date, and distinguish published results from model specifications.

The observation trail

Recorded events, in chronological order

Added to the model catalog

Catalog creation date, as recorded by OpenRouter.

Model specifications observed

Catalog pricing, limits, and supported parameters captured.

Provider routes observed

41 inference routes in this snapshot.

Observation dates describe when data was captured. They do not represent newly run evaluations or continuous performance monitoring.

Published observation ledger

Historical evidence, with source and version preserved.

Published observation history for DeepSeek V4.1 Flash (max)
ObservedBenchmarkScoreVersionSourceVerification
28 Oct 2026SimpleQA VerifiedEpoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026FrontierMath Tier 4 v2Epoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026FrontierMath Tiers 1–3 v2Epoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026OTIS Mock AIME 2024–2025Epoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026GPQA DiamondEpoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026SimpleQA VerifiedEpoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026FrontierMath Tier 4 v2Epoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026FrontierMath Tiers 1–3 v2Epoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026OTIS Mock AIME 2024–2025Epoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026GPQA DiamondEpoch AI · independent runsEpoch AI · benchmark dataSource-reported

09 / A FEW MORE DETAILS

Questions worth asking.

Quick answers, drawn from this model’s connected specifications.

How much does DeepSeek V4.1 Flash (max) cost?

Catalog starting rates are $0.14 per million input tokens and $0.42 per million output tokens. Cache-read pricing is $0.0042 per million tokens. Compare provider routes and service tiers above for their specific prices.

How much context can it handle?

1,048,576 tokens in the catalog context window. The catalog lists a maximum of 131,072 completion tokens. Provider limits can differ.

Does it support tools and structured output?

Tool calling: listed as supported. Structured outputs: listed as supported. See the provider feature matrix for route-specific differences.

How should I interpret these benchmark results?

Read the benchmark name, exact version, metric, source, and model configuration together. Different evaluation settings can change the result. Preference ratings and source-defined composite indices remain separate from task accuracy.

Are these prices and provider measurements live?

This page uses dated source snapshots. Catalog data was observed on 28 Oct 2026. Provider routes were observed on 28 Oct 2026. Missing measurements are not estimated or treated as zero.

KEEP EXPLORING

More from DeepSeek.

Explore related identities from the same developer, or take them into a side-by-side comparison.

Source-backed evidence. Different tasks. A clearer picture.
AboutMethodologyBenchmark dashboard