Poolside: Laguna S 2.1
Poolside: Laguna S 2.1 is a powerful AI model capable of handling large text inputs with a context length of up to 1,048,576 tokens and can generate up to 131,072 tokens in response. It supports both reasoning and tools integration, making it versatile for complex tasks that require logical thinking and interaction with external data. While Poolside: Laguna S 2.1 offers robust capabilities such as reasoning and tool support, its current lack of benchmark coverage means its performance remains unproven against industry standards. Given its pricing at $0.09 per million input tokens and $0.18 per million output tokens, it may be more suitable for users willing to pay for premium features without the immediate benefit of verified benchmarks.
- Model ID
- poolside/laguna-s-2.1
- Vendor
- poolside
- Released
- July 2026
- Tokenizer
- Other
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 131,072 tokens
- Tool Calling
- ✓ supported
- Structured Output
- not supported
- Reasoning Mode
- ✓ supported
- Vision
- text only
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.09/M input and $0.18/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | under $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.05 |
| A month of a busy support chatbot | 5M in / 2M out | $0.81 |
Price & spec history
Tracked daily by PicksByModel since 2026-07-22.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-07-31 | $0.09 | $0.18 | 1,048,576 |
| 2026-07-22 | $0.10 | $0.20 | 1,048,576 |
Similar models
Quick answers
- How much does Poolside: Laguna S 2.1 cost?
- $0.09 per million input tokens and $0.18 per million output tokens.
- What is Poolside: Laguna S 2.1's context window?
- 1,048,576 tokens, roughly 1,572 pages of text in a single request.
- Does Poolside: Laguna S 2.1 support tool calling?
- It supports tool calling, a reasoning mode.
- Can Poolside: Laguna S 2.1 process images?
- No, it is text-only on the input side.