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
Use cases

|

Terms

|

Privacy

|

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

Ling 3.0 Flash Thinking

Ling-3.0-flash Thinking enables visible reasoning on inclusionAI's token-efficient 124B-parameter Mixture-of-Experts model for harder coding, tool use, planning, and production-scale agent workflows.

  • Reasoning
  • Tool Calling

Added Jul 23, 2026

Model weights

Pricing

Auto routing · per 1M tokens
Input
$0.075
Output
$0.22
Cache read
$0.015
Compare provider prices

Specifications

Context window
262.1K
Max output
32.8K
Avg output (7d)
324 tokens
Longer than 32% of models

Benchmarks

Sourced from Artificial Analysis.

Coding Index

50.6

Coding Index: 50.6
Better than 61% of models compared

Agentic Index

19.3

Agentic Index: 19.3
Better than 56% of models compared

Agentic work

AutomationBench-AA

Workflow automation with guardrail penalties

3.2%

Better than 22% of models compared

AutomationBench-AA Tasks Completed

Fully completed workflows without guardrail violations

0.6%

Better than 27% of models compared

AA-Briefcase v1.1

Agentic knowledge work (Elo)

798 Elo

Better than 31% of models compared

GDPval-AA v2.1

Economically valuable tasks (Elo)

957 Elo

Better than 39% of models compared

Document reasoning

GDP.pdf

Professional PDF reasoning: all-pass rate

5.4%

Better than 27% of models compared

AA-LCR v1.1

Long context reasoning with updated grading

73.0%

Better than 67% of models compared

MLCR-AA

Medical long-context reasoning

5.0%

Better than 13% of models compared

Reasoning

HLE

Humanity's Last Exam

23.7%

Better than 70% of models compared

CritPt

Research-level physics reasoning

1.7%

Coding

Terminal-Bench v4.0

Practical coding and terminal tasks

0.0%

Better than 15% of models compared

SciCode

Python programming for scientific computing

42.0%

Better than 29% of models compared

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

85.5%

Better than 79% of models compared

AA-LCR (unversioned / legacy)

Long context reasoning evaluation

73.0%

Better than 67% of models compared

GDPval-AA (unversioned / legacy)

Economically valuable tasks

22.9%

Last updated Nov 1, 2026

Artificial Analysis

Providers

Provider information for this model’s automatic routing. These routes cannot be selected individually.

Loading provider options…

Related text models

Compare Ling 3.0 Flash Thinking with similar models from the same provider or model family.

Ling 3.1 Flash

inclusionai/ling-3.1-flash

Ling 3.1 Flash is inclusionAI's hybrid reasoning model for coding, tool use, planning, and long-context agent workflows. It has 560B total parameters with 25B active parameters per token. Thinking is enabled by default and can be turned off in settings.

Ling 3.0 Flash VL

inclusionai/ling-3.0-flash-vl

Ling 3.0 Flash VL is inclusionAI's native multimodal Mixture-of-Experts model with 124B total parameters and 5.5B active parameters per token. It combines image and video understanding with reasoning and tool use for document analysis, charts, visual verification, and interface-based agent tasks. Thinking is enabled by default and can be turned off in settings.

Ling 3.0 Flash

inclusionai/ling-3.0-flash

Ling-3.0-flash is a 124B-parameter Mixture-of-Experts model with approximately 5.1B parameters active per token. It prioritizes token efficiency and production-scale agentic inference, helping coding and tool-using agents complete more work within constrained latency and serving budgets.

DeepSeek V4.1 Flash Heretic

pqhaz/DeepSeek-V4.1-Flash-1017-heretic

pqhaz's Heretic checkpoint of DeepSeek V4.1 Flash 1017, served by Sable at original mixed precision (FP8 dense/Engram and MXFP4 experts). Supports text and image input, tools, structured output, and optional reasoning. Separate from the DeAlign uncensored checkpoint.

DeepSeek V4.1 Flash Heretic Thinking

pqhaz/DeepSeek-V4.1-Flash-1017-heretic:thinking

pqhaz's Heretic checkpoint of DeepSeek V4.1 Flash 1017, served by Sable at original mixed precision (FP8 dense/Engram and MXFP4 experts). Supports text and image input, tools, structured output, and optional reasoning. Separate from the DeAlign uncensored checkpoint.

DeepSeek V4.1 Flash 0910 Uncensored

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

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