Laguna XS 2.1
General purposeToolsPoolside · Released July 2026
Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...
Facts and pricing
- Provider
- Poolside
- Context window
- 262K tokens
- Input price
- 0.66 credits / 1M tokens ($0.060 raw)
- Output price
- 1.3 credits / 1M tokens ($0.12 raw)
- Vision (image input)
- No
- Tool calling
- Yes
- Extended reasoning
- No
Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.
Try Laguna XS 2.1 now
What Laguna XS 2.1 is best for
- Balanced everyday work: writing, questions, brainstorming and summarization
- Long documents: the 262K-token window holds lengthy reports, contracts or papers whole
- Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows
Poolside family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| Laguna XS 2.1 (free) | 262K | 0 | 0 | July 2026 |
| Laguna XS 2.1 | 262K | 0.66 | 1.3 | July 2026 |
| Laguna M.1 (free) | 262K | 0 | 0 | April 2026 |
| Laguna M.1 | 262K | 2.2 | 4.4 | April 2026 |
Frequently asked questions
- What is Laguna XS 2.1?
- Laguna XS 2.1 is an AI model by Poolside. Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...
- How much does Laguna XS 2.1 cost on Zeplik?
- Input tokens cost 0.66 credits per million and output tokens 1.3 credits per million (1 credit = $0.10; the raw provider rates are $0.060 and $0.12 per million). New accounts start with free credits.
- How long can a conversation with Laguna XS 2.1 be?
- Laguna XS 2.1 has a 262K-token context window (262,144 tokens), which covers the conversation plus any documents you attach.
- Does Laguna XS 2.1 support images and tools?
- Laguna XS 2.1 is text-only and supports tool calling.
Related models
Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...
Laguna M.1 is the flagship coding agent model from [Poolside](https://poolside.ai/), optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling and reasoning, with a 256K...
Laguna M.1 is the flagship coding agent model from [Poolside](https://poolside.ai/), optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling and reasoning, with a 256K...
GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode
GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...
GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode