Singularity Logs

THE MODEL, IN DETAIL / DeepSeek

DeepSeek V4 Pro 0423

deepseek/deepseek-v4-proAccess not documentedReasoning

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...

OpenRouter
Source-linked model intelligenceCatalog added 24 Apr 2026Specifications observed 30 Oct 2026

Published evaluations

0

Results connected

Context window

1M

384K max output tokens

Input price

$0.8162

USD / million input tokens

Output price

$1.6325

USD / million output tokens

Inference providers

14

15 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

At least three published accuracy scores are needed for this view.

Performance meets price

Source-aligned model comparison

A shared benchmark and documented prices are needed for this comparison.

In good company

Published model comparisons

No published measurements in this snapshot.

0 models in the source cohort. Showing selected nearby models. Evaluation settings can differ.

Evidence, by task.

Coverage is not a capability score.

0published results
0 evaluation sources
ReasoningAwaiting evidence
CodingAwaiting evidence
MathematicsAwaiting evidence
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.

0 published results

Percentage-based evaluations will appear here when published.

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

03 / COST & VALUE

Know what your workload costs.

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

Input$0.8162per million tokens
Output$1.6325per million tokens
Cache read$0.068per 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

$9.7948estimated total
Uncached input$8.1623
Cached input$0
Output$1.6325
Per request$0.0098
Without cache discount$9.7948
Estimated cache savings$0

04 / INFERENCE NETWORK

One model. Different ways to run it.

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

14 providers · 15 routes
Provider routes for DeepSeek V4 Pro 0423, observed 29 Oct 2026
Provider / routeInput / MOutput / MCache / MContextOutput limitSpeedLatencyAvailability · 1dRates
SStreamLakeFP8$0.894$1.788$0.07451M384K——99.93%
BBaiduFP8$0.8957$1.7914$0.07421M393.2K——99.79%
RRelaceFP4$0.9$1.5$0.251M393.2K——100%
GGMICloudFP8$0.957$1.914$0.07981M943.7K——99.93%
SSiliconFlowFP8$1$3.135$0.1351M393.2K——99.86%
DDigitalOceanQuantization not disclosed$1.044$2.088$0.20881M384K——100%
CCloudflareQuantization not disclosed$1.15$2.55$0.21M943.7K——99.58%
DDeepInfraFP8$1.3$2.6$0.11M16.4K——99.93%
AAlibabaFP8$1.416$2.832$0.1181M393.2K——98.04%
AAlibabaFP8$1.56$3.12$0.131M393.2K——99.78%
NNovitaFP8$1.6$3.2$0.1351M393.2K——99.93%
VVeniceQuantization not disclosed$1.65$3.301$0.331M32.8K——99.55%
AAtlasCloudFP4$1.68$3.38$0.131M393.2K——99.27%
CCrusoeFP8$1.74$3.48$0.151M943.7K——97.58%
AAzureQuantization not disclosed$1.91$3.83$0.161M384K——99.93%

Snapshot observed 29 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
StreamLakefp8
Input
$0.894
Output
$1.788
Baidufp8
Input
$0.8957
Output
$1.7914
Relacefp4
Input
$0.9
Output
$1.5
GMICloudfp8
Input
$0.957
Output
$1.914
SiliconFlowfp8
Input
$1
Output
$3.135
DigitalOcean
Input
$1.044
Output
$2.088
Cloudflare
Input
$1.15
Output
$2.55
DeepInfrafp8
Input
$1.3
Output
$2.6
Alibabafp8
Input
$1.416
Output
$2.832
Alibabafp8
Input
$1.56
Output
$3.12

Reported availability

Provider availability over the selected observation window

StreamLake · FP899.93%
Baidu · FP899.79%
Relace · FP4100%
GMICloud · FP899.93%
SiliconFlow · FP899.86%
DigitalOcean100%
Cloudflare99.58%
DeepInfra · FP899.93%
Alibaba · FP898.04%
Alibaba · FP899.78%

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

StreamLake · FP81M
Baidu · FP81M
Relace · FP41M
GMICloud · FP81M
SiliconFlow · FP81M
DigitalOcean1M
Cloudflare1M
DeepInfra · FP81M
Alibaba · FP81M
Alibaba · FP81M

05 / CAPABILITIES & MODALITIES

What goes in. What comes out.

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

INPUT MODALITIES

Text
DeepSeek V4 Pro 0423Reasoning 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
384Kmax 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
384,000 tokens
Top-provider context
1,024,000 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
StreamLake · FP8SupportedSupportedSupportedSupportedSupported
Baidu · FP8SupportedSupportedSupportedSupportedSupported
Relace · FP4SupportedSupportedNot listedSupportedSupported
GMICloud · FP8SupportedSupportedNot listedSupportedSupported
SiliconFlow · FP8SupportedSupportedNot listedSupportedSupported
DigitalOceanSupportedSupportedNot listedSupportedSupported
CloudflareSupportedSupportedSupportedSupportedSupported
DeepInfra · FP8SupportedSupportedSupportedSupportedSupported
Alibaba · FP8SupportedSupportedSupportedSupportedSupported
Alibaba · FP8SupportedSupportedSupportedSupportedSupported
Novita · FP8SupportedSupportedNot listedSupportedSupported
VeniceSupportedSupportedSupportedSupportedSupported
AtlasCloud · FP4SupportedSupportedSupportedSupportedSupported
Crusoe · FP8SupportedSupportedSupportedSupportedSupported
AzureSupportedSupportedNot listedSupportedSupported

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/deepseek-v4-pro
Subject
Model
Access
unknown
License
Not disclosed
Parameters
Not disclosed
Tokenizer
DeepSeek
Instruction format
Not disclosed

Reasoning & controls

Reasoning
Supported
Mandatory reasoning
No
Reasoning by default
Not documented
Published configuration
Not disclosed
Supported reasoning efforts
xhigh, high, none
Default reasoning effort
high
API parameters
21
Provider moderation
No
Quantization variants
fp8, fp4

Dates & limits

Catalog added
24 Apr 2026
Knowledge cutoff
Not disclosed
Catalog expiration
Not documented
Specifications observed
30 Oct 2026
Providers observed
29 Oct 2026
Request limits
Provider-specific / not supplied
Canonical catalog ID
deepseek/deepseek-v4-pro-20260423

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_completion_tokensSupported · default not supplied
max_tokensSupported · default not supplied
min_pSupported · 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
temperatureDefault: 1
tool_choiceSupported · default not supplied
toolsSupported · default not supplied
top_kSupported · default not supplied
top_logprobsSupported · default not supplied
top_pDefault: 1

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-pro",
      "messages": [
        {
          "role": "user",
          "content": "Explain the trade-offs in this design."
        }
      ]
    }),
  },
);
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.

Provider routes observed

15 inference routes in this snapshot.

Model specifications observed

Catalog pricing, limits, and supported parameters captured.

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.

No published benchmark observations for this selection. Published preference rankings appear separately above.

09 / A FEW MORE DETAILS

Questions worth asking.

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

How much does DeepSeek V4 Pro 0423 cost?

Catalog starting rates are $0.8162 per million input tokens and $1.6325 per million output tokens. Cache-read pricing is $0.068 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 384,000 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 30 Oct 2026. Provider routes were observed on 29 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.

THE RIGHT MODEL STARTS WITH THE RIGHT CONTEXT.

Put the details side by side.

Explore the trade-offs in a direct model comparison.

Compare DeepSeek V4 Pro 0423
Source-backed evidence. Different tasks. A clearer picture.
AboutMethodologyBenchmark dashboard