> ## Documentation Index
> Fetch the complete documentation index at: https://aisa.one/docs/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> - Base URLs: models `https://api.aisa.one/v1` (Gemini GenerateContent: `https://api.aisa.one/v1beta`); data APIs `https://api.aisa.one/apis/v1`. The `servers` of each operation in https://aisa.one/openapi.yaml is authoritative.
> - Auth: `Authorization: Bearer $AISA_API_KEY`. Never print, log, or commit the key.
> - MCP (preferred for agents): `https://mcp.aisa.one/mcp`, signed in with OAuth, so there is no key to paste.
> - Agent Skill: `npx skills add AIsa-team/agent-skills --skill aisa`. Fallback with the AIsa CLI: `aisa skills install aisa`.
> - Spending: docs, https://aisa.one/models, https://aisa.one/api, `/v1/models`, and MCP `search`, `list_categories`, `get_details`, `batch_quote`, and the `account` operation are free. Quote the exact calls before running them (MCP `batch_quote`, CLI `aisa quote --json`). If the quote reports `auto_execute_eligible: true`, run it unless the user set a tighter limit or asked only for a quote. Otherwise, tell the user in one message the planned calls, the quoted price, and a total USD budget for the task, then wait for approval. Direct HTTP calls follow the stricter rule at https://aisa.one/docs/get-started/cli.md#direct-http-fallback. Do not make paid calls to test availability. Full rule: https://aisa.one/llms.txt

# DeepSeek API - Access DeepSeek Models via AIsa

> Current AIsa guide to DeepSeek model IDs and endpoints, including deepseek-v4.1-flash, deepseek-v4-pro, and deepseek-v4-flash-vision-exp.

AIsa gives you OpenAI-compatible access to the current DeepSeek model family with one API key, unified billing, usage logs, and gateway routing.

The table lists the endpoints each model accepts.

## Supported DeepSeek models

| Model ID | Type | Endpoints | Best for |
| - | - | - | - |
| `deepseek-v4-flash-vision-exp` | Text | `/v1/chat/completions`, `/v1/messages`, `/v1/responses` | Experimental vision variant of V4 Flash |
| `deepseek-v4-pro` | Text | `/v1/chat/completions`, `/v1/messages`, `/v1/responses` | Stronger DeepSeek route with multiple endpoint styles |
| `deepseek-v4-pro-0813` | Text | `/v1/chat/completions`, `/v1/messages`, `/v1/responses` | Pinned snapshot of `deepseek-v4-pro` |
| `deepseek-v4.1-flash` | Text | `/v1/chat/completions`, `/v1/messages`, `/v1/responses` | Lowest-cost high-throughput DeepSeek route (V4.1) |

Current prices for these models are on [aisa.one/models](https://aisa.one/models).

## Quickstart

```python theme={null}
from openai import OpenAI

client = OpenAI(api_key="YOUR_AISA_API_KEY", base_url="https://api.aisa.one/v1")

response = client.chat.completions.create(
    model="deepseek-v4.1-flash",
    messages=[{"role": "user", "content": "Review this pull request for security and correctness."}]
)
print(response.choices[0].message.content)
```

## Common choices

| Need | Use |
| - | - |
| Cheapest DeepSeek text/coding | `deepseek-v4.1-flash` |
| Stronger DeepSeek route | `deepseek-v4-pro` |
| Pinned production route | `deepseek-v4-pro-0813` |

## Data privacy

AIsa routes DeepSeek requests through an enterprise-backed aggregation path. Customer data is not used for model training under AIsa's enterprise agreements. For compliance details, [contact us](mailto:developer@aisa.one).

## Next

* [Model Catalog](https://aisa.one/docs/guides/models.md)
* [Qwen models](https://aisa.one/docs/models/qwen.md)
* [AI model pricing](https://aisa.one/docs/guides/pricing.md#models)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.