Model Library
InclusionAIReleased April 21, 2026Ling 2.6 Flash
InclusionAI · Released April 21, 2026
Intelligence score
14
At a glance
- Intelligence
- 14
- Speed
- 177.4tokens/sec
- Latency
- 1.45stime to first token
- Input price
- $0.10per 1M tokens
- Output price
- $0.30per 1M tokens
- Context window
- 260Ktokens
- Parameters
- 107billions
Summary
Comparison summary
Ling 2.6 Flash scores 14 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 7). Ling 2.6 Flash generates output at 177.4 tokens per second (based on the median across providers serving the model), which is well above average compared to other open weight non-reasoning models of similar size (median: 81.5 t/s). Ling 2.6 Flash costs $0.10 per 1M input tokens (very competitive, median: $0.53) and $0.30 per 1M output tokens (very competitive, median: $1.05), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | Ling 2.6 Flash |
|---|---|
| Provider | InclusionAI |
| Release date | April 21, 2026 |
| Intelligence score | 14 |
| Speed | 177.4 tokens/sec |
| Latency (TTFT) | 1.45s |
| Input price | $0.10 / 1M tokens |
| Output price | $0.30 / 1M tokens |
| Context window | 260,000 tokens |
| Parameters | 107B |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | Mit |
| API availability | — |
| Source | Model Intelligence legacy profile: ling-2-6-flash |
Pricing
Token prices
Price per 1M tokens
Ling 2.6 Flash, as listed in the catalog record
- Input$0.10
- Output$0.30
| Token type | Price per 1M |
|---|---|
| Input | $0.10 |
| Output | $0.30 |
Model Intelligence legacy profile: ling-2-6-flash
FAQ · 21
Frequently asked questions
Ling 2.6 Flash was released on April 21, 2026.
Ling 2.6 Flash was created by InclusionAI.
Ling 2.6 Flash scores 14 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 7).
Ling 2.6 Flash generates output at 177.4 tokens per second (based on the median across providers serving the model), which is well above average compared to other open weight non-reasoning models of similar size (median: 81.5 t/s).
Ling 2.6 Flash has a time to first token (TTFT) of 1.45s (based on the median across providers serving the model), which is better than average compared to other open weight non-reasoning models of similar size (median: 1.59s).
Ling 2.6 Flash costs $0.10 per 1M input tokens (very competitive, median: $0.53) and $0.30 per 1M output tokens (very competitive, median: $1.05), based on the median across providers serving the model.
Ling 2.6 Flash costs $0.10 per 1M input tokens and $0.30 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 $0.06 per 1M tokens. Pricing may vary by provider.
When evaluated on the Intelligence Index, Ling 2.6 Flash generated 20M output tokens, which is somewhat higher than average compared to other open weight non-reasoning models of similar size (median: 9.2M).
No, Ling 2.6 Flash is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Ling 2.6 Flash supports text input.
Ling 2.6 Flash supports text output.
No, Ling 2.6 Flash does not support image input. It can only process text.
No, Ling 2.6 Flash is not multimodal. It only supports text input.
Ling 2.6 Flash has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Ling 2.6 Flash is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Ling 2.6 Flash has 107 billion parameters (7.4 billion active).
Ling 2.6 Flash is a Mixture of Experts (MoE) model with 107 billion total parameters, but only 7.4 billion active parameters are used during inference.
Ling 2.6 Flash is released under the Mit license. This license allows commercial use.
Ling 2.6 Flash achieves a score of 14 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Ling 2.6 Flash is available via API through 1 provider.
Ling 2.6 Flash is available through 1 API provider.