inclusionAI: Ling 3.1 Flash
by inclusionAIinclusionAI: Ling 3.1 Flash is a large language model from inclusionAI. It costs $0.075 per million input tokens and $0.225 per million output tokens. Its context window is 262K tokens.
- Input / 1M tokens
- $0.075
- Output / 1M tokens
- $0.225
- Cached input / 1M
- $0.015
- Context window
- 262K
On repeated prefixes
tokens
Who serves it cheapest
2 hosts serve Ling 3.1 Flash. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| DeepInfraCheapestfp4 | $0.075 | $0.225 | 262K | - | 100.0% |
| Novita | $0.075 | $0.225 | 262K | - | 100.0% |
The spread between DeepInfra and Novita is about the same for identical weights. Quantization and context limits differ, so check both columns before switching.
Benchmarks
Independent scores published alongside the catalogue.
- Intelligence index
- 41.1
About Ling 3.1 Flash
Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.
Specifications
| Model ID | inclusionai/ling-3.1-flash |
|---|---|
| Provider | inclusionAI |
| Context window | 262K tokens |
| Max output | 236K tokens |
| Input modalities | text |
| Output modalities | text |
| Knowledge cutoff | - |
| Open weights | No |
| Released | October 2, 2026 |
Cheaper alternatives
Models that cost less than Ling 3.1 Flash while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does inclusionAI: Ling 3.1 Flash cost?
$0.075 per million input tokens and $0.225 per million output tokens. Cached input reads cost $0.015 per million tokens.
What is the context window of inclusionAI: Ling 3.1 Flash?
262K tokens, with up to 236K tokens of output per request.
Which provider serves inclusionAI: Ling 3.1 Flash cheapest?
DeepInfra at $0.075 per million input tokens - about the same cheaper than Novita, the most expensive of the 2 hosts serving it.