Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage
API
Suggestions and bugs
Terms

|

Privacy

|

Refunds
Balance
Subscription
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksEarn crypto
  1. Models
  2. Text
  3. DeepSeek

DeepSeek V4 Flash 0423 (Thinking)

The original 0423 checkpoint of DeepSeek V4 Flash, with a 1M-token context window, text input, tool calling, structured output, and optional reasoning.

  • Reasoning
  • Tool Calling
  • Structured Output

Added Oct 7, 2026

Pricing

Auto routing · per 1M tokens
Input
$0.14
Output
$0.28
Cache read
$0.028
Compare provider prices

Specifications

Context window
1M
Max output
N/A
Parameters
284B / 13B
Total / active
Avg output (7d)
1.1K tokens
Longer than 73% of models

Benchmarks

Sourced from Artificial Analysis.

Intelligence Index

24.4

Intelligence Index: 24.4
Better than 75% of models compared

Coding Index

52.0

Coding Index: 52.0
Better than 59% of models compared

Agentic work

AutomationBench-AA

Workflow automation with guardrail penalties

28.5%

Better than 46% of models compared

AutomationBench-AA Tasks Completed

Fully completed workflows without guardrail violations

8.7%

Better than 49% of models compared

AA-Briefcase v1.1

Agentic knowledge work (Elo)

1041 Elo

Better than 49% of models compared

GDPval-AA v2.1

Economically valuable tasks (Elo)

1000 Elo

Better than 43% of models compared

Document reasoning

GDP.pdf

Professional PDF reasoning: all-pass rate

10.4%

Better than 41% of models compared

AA-LCR v1.1

Long context reasoning with updated grading

72.0%

Better than 65% of models compared

Reasoning

HLE

Humanity's Last Exam

30.3%

Better than 76% of models compared

IFBench

Instruction-following benchmark

73.5%

Better than 91% of models compared

Coding

Terminal-Bench v4.0

Practical coding and terminal tasks

3.0%

Better than 49% of models compared

SciCode

Python programming for scientific computing

40.2%

Better than 25% of models compared

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

86.7%

Better than 82% of models compared

Terminal-Bench Hard (legacy)

Agentic coding and terminal use

38.6%

Better than 86% of models compared

T²-Bench Telecom (legacy)

Conversational AI agents in dual-control scenarios

95.6%

Better than 95% of models compared

AA-LCR (unversioned / legacy)

Long context reasoning evaluation

72.0%

Better than 65% of models compared

Last updated Oct 27, 2026

Artificial Analysis

Providers

Loading provider options…

Related text models

Compare DeepSeek V4 Flash 0423 (Thinking) with similar models from the same provider or model family.

DeepSeek V4 Flash 0423

deepseek/deepseek-v4-flash-0423

The original 0423 checkpoint of DeepSeek V4 Flash, with a 1M-token context window, text input, tool calling, structured output, and optional reasoning.

DeepSeek V4.1 Flash 0910 Uncensored

deepseek/deepseek-v4.1-flash-0910-uncensored

Uncensored DeepSeek V4.1 Flash with text input, optional reasoning, and tool calling. The date label is retained for compatibility; the served checkpoint can vary with availability.

DeepSeek V4.1 Flash 0910 Uncensored Thinking

deepseek/deepseek-v4.1-flash-0910-uncensored:thinking

Uncensored DeepSeek V4.1 Flash with text input, optional reasoning, and tool calling. The date label is retained for compatibility; the served checkpoint can vary with availability.

DeepSeek V4.1 Flash 1017 Uncensored

deepseek/deepseek-v4.1-flash-1017-uncensored

Uncensored DeepSeek V4.1 Flash with text input, optional reasoning, and tool calling. The date label is retained for compatibility; the served checkpoint can vary with availability.

DeepSeek V4.1 Flash 1017 Uncensored Thinking

deepseek/deepseek-v4.1-flash-1017-uncensored:thinking

Uncensored DeepSeek V4.1 Flash with text input, optional reasoning, and tool calling. The date label is retained for compatibility; the served checkpoint can vary with availability.

DeepSeek V4.1 Flash 1017

deepseek/deepseek-v4.1-flash-1017

The October 17, 2026 snapshot of DeepSeek V4.1 Flash supports text and image input, tool calling, and optional reasoning with low, high, and max effort. It has a shared 1,048,576-token context window and supports up to 393,216 output tokens within the remaining context. Released under the MIT license.