Model Library
InclusionAIReleased September 19, 2025Ring-flash-2.0
InclusionAI · Released September 19, 2025
Intelligence score
8
At a glance
- Intelligence
- 8
- Speed
- —
- Latency
- —
- Input price
- $0.14per 1M tokens
- Output price
- $0.57per 1M tokens
- Context window
- 130Ktokens
- Parameters
- 103billions
Summary
Comparison summary
Ring-flash-2.0 scores 8 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight models of similar size (median: 9). Ring-flash-2.0 costs $0.14 per 1M input tokens (very competitive, median: $0.40) and $0.57 per 1M output tokens (very competitive, median: $0.84), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | Ring-flash-2.0 |
|---|---|
| Provider | InclusionAI |
| Release date | September 19, 2025 |
| Intelligence score | 8 |
| Speed | — |
| Latency (TTFT) | — |
| Input price | $0.14 / 1M tokens |
| Output price | $0.57 / 1M tokens |
| Context window | 130,000 tokens |
| Parameters | 103B |
| Reasoning | Yes |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | MIT |
| API availability | — |
| Source | Model Intelligence legacy profile: ring-flash-2-0 |
Pricing
Token prices
Price per 1M tokens
Ring-flash-2.0, as listed in the catalog record
- Input$0.14
- Output$0.57
| Token type | Price per 1M |
|---|---|
| Input | $0.14 |
| Output | $0.57 |
Model Intelligence legacy profile: ring-flash-2-0
FAQ · 18
Frequently asked questions
Ring-flash-2.0 was released on September 19, 2025.
Ring-flash-2.0 was created by InclusionAI.
Ring-flash-2.0 scores 8 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight models of similar size (median: 9).
Ring-flash-2.0 costs $0.14 per 1M input tokens (very competitive, median: $0.40) and $0.57 per 1M output tokens (very competitive, median: $0.84), based on the median across providers serving the model.
Ring-flash-2.0 costs $0.14 per 1M input tokens and $0.57 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.18 per 1M tokens. Pricing may vary by provider.
Yes, Ring-flash-2.0 is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
Ring-flash-2.0 supports text input.
Ring-flash-2.0 supports text output.
No, Ring-flash-2.0 does not support image input. It can only process text.
No, Ring-flash-2.0 is not multimodal. It only supports text input.
Ring-flash-2.0 has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Ring-flash-2.0 is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Ring-flash-2.0 has 103 billion parameters (6.1 billion active).
Ring-flash-2.0 is a Mixture of Experts (MoE) model with 103 billion total parameters, but only 6.1 billion active parameters are used during inference.
Ring-flash-2.0 is released under the MIT license. This license allows commercial use.
Ring-flash-2.0 achieves a score of 8 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Ring-flash-2.0 is available via API through 1 provider.
Ring-flash-2.0 is available through 1 API provider.