Ling 3.0 Flash Fin overview
The model is no longer available on AI/ML API. Its replacement is Ling-3.0-flash.
Ling 3.0 Flash Fin by inclusionAI
Ling 3.0 Flash Fin is inclusionAI's finance-specialised variant of Ling-3.0-flash, keeping the 262K-token context window and adding domain tuning for financial reasoning.
Ling 3.0 Flash Fin specs
- Model ID
inclusionai/ling-3.0-flash-fin- Developer
- inclusionAI
- Context window
- 262,144 tokens
- Input
- Text
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
What Is Ling 3.0 Flash Fin?
Ling 3.0 Flash Fin is the finance-tuned member of inclusionAI's Ling 3.0 family, built by Ant Group's inclusionAI team. It keeps the speed and cost profile of Ling-3.0-flash while being adapted for financial analysis, reporting and quantitative reasoning.
Technical Specifications
- Context window: 262,144 tokens
- Reasoning, streaming, tool calling and structured outputs
Where Ling 3.0 Flash Fin Fits
Financial document analysis
A 262K context lets whole filings, prospectuses and annual reports be read in one prompt.
Quantitative reasoning
Domain tuning targets the numeric and tabular reasoning that general chat models handle unevenly.
Available on AI/ML API since August 27, 2026.
Use cases
End-to-end financial research: the model is documented as handling information retrieval, evidence review, calculation, modeling, and report preparation as a single workflow.
Source-grounded financial search: it is described as prioritizing authoritative sources to produce accurate, complete, and traceable answers for financial questions.
Multi-document financial reasoning: it is suited to reconciling reporting periods, definitions, assumptions, and conflicting figures across annual reports, earnings releases, regulatory filings, and research materials.
Valuation and spreadsheet workflows: it is documented as understanding formulas, actual-versus-estimate updates, cross-sheet dependencies, balance checks, scenario analysis, and editable financial-model delivery.
Capabilities
- Reasoning
- Streaming
- Structured outputs
- Function calling
Ling 3.0 Flash Fin benchmarks by 
Artificial Analysis
See how Ling 3.0 Flash Fin scores on independent evaluations. Data retrieved Nov 4, 2026.
Benchmark results
Compare 8 models available on AI/ML API across 4 independent benchmarks.
Humanity's Last Exam
Expert-written questions across academic subjects.
Terminal-Bench 4.0
Agentic tasks completed in a command-line environment.
AA-LCR
Reasoning across long documents of about 100k tokens.
SciCode
Python coding tasks drawn from scientific research.
Models similar to Ling 3.0 Flash Fin
Related articles
Ling 3.0 Flash Fin FAQ
What is Ling 3.0 Flash Fin?
Ling 3.0 Flash Fin is a chat model from inclusionAI. It is the finance-tuned member of the Ling 3.0 Flash line.
How does Ling 3.0 Flash Fin differ from Ling 3.0 Flash?
It keeps the Flash line's speed-oriented design and adds domain tuning aimed at financial material.
Who builds Ling 3.0 Flash Fin?
inclusionAI, the AI research group at Ant Group.
Does Ling 3.0 Flash Fin support tool calling?
Yes, the model supports function calling.
Does Ling 3.0 Flash Fin support streaming?
Yes. Responses can be streamed as they are generated rather than returned in one block.
What inputs and outputs does Ling 3.0 Flash Fin support?
It takes text and returns text.
How do I call Ling 3.0 Flash Fin on AI/ML API?
Send a request to the chat completions endpoint with the model id inclusionai/ling-3.0-flash-fin.
What is the Ling 3.0 Flash Fin model ID?
Use inclusionai/ling-3.0-flash-fin as the model parameter. Requests go to the OpenAI-compatible endpoint with your AI/ML API key.
What is the context window of Ling 3.0 Flash Fin?
Ling 3.0 Flash Fin accepts up to 262,144 tokens of context.