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

# Migrate to the Sail API

> Drop-in migration from OpenAI and Anthropic-compatible providers to Sail.

Sail is a drop-in replacement for OpenAI and Anthropic-compatible inference providers, supporting the OpenAI Responses (`/v1/responses`), OpenAI Chat Completions (`/v1/chat/completions`), and Anthropic Messages (`/v1/messages`) APIs. Switching from OpenAI, Anthropic, or any compatible provider is just a configuration change.

<div className="sail-oneshot-cta" id="copy-migration-prompt">
  <span className="sail-oneshot-cta-body">
    <span className="sail-oneshot-cta-title">Want an agent to do it?</span>

    <span className="sail-oneshot-cta-desc">
      Copy a migration prompt, paste it into your coding agent, and then use the
      guide below to review the changes.
    </span>
  </span>

  <button type="button" className="sail-oneshot-copy" data-sail-copy-prompt>
    Copy migration prompt
  </button>
</div>

<Note>
  Using Claude Code or Codex? Install the [Sail skills](/ai-quickstart) instead
  and ask your agent to "Migrate this app to Sail". The `sail-migrate` skill
  guides the full migration, including moving sandboxed execution to Sail.
</Note>

<div id="sail-one-shot-prompt" className="sail-hidden-prompt" aria-hidden="true">
  ```text Migration prompt theme={null}
  Migrate this project's LLM inference to Sail (https://sailresearch.com).

  Sail docs to consult as you work:
  - MCP server: https://docs.sailresearch.com/mcp (connect to it if you support MCP)
  - Full docs as plain text: https://docs.sailresearch.com/llms-full.txt
  - Key pages: https://docs.sailresearch.com/models (catalog),
    https://docs.sailresearch.com/pricing (per-window rates),
    https://docs.sailresearch.com/completion-windows,
    https://docs.sailresearch.com/support (API feature matrix)

  Sail is drop-in compatible with the OpenAI Responses and Chat Completions
  APIs and the Anthropic Messages API, all served from
  https://api.sailresearch.com. Keep whichever request shape this code
  already uses. Sail's Messages API supports system prompts, tool calling, and
  streaming for agentic use; one caveat is that prompt caching (`cache_control`)
  is accepted but not yet applied (see /support), so if an Anthropic call site
  relies on cache hits, expect full-price reads until that lands. The exact base
  URL differs by SDK (see step 4).

  If you can ask the user questions, ask whenever a step below is ambiguous
  instead of guessing. If you can't, make the best-supported choice and flag
  it in your final report.

  1. Survey the current setup. Find every place this project calls an LLM:
     SDK clients, raw HTTP calls, framework configs, env vars, and docs. For
     each call site record the provider, API shape, model, and features used
     (streaming, tool calls, structured outputs, images).

  2. Choose replacement model(s). For each model currently in use, pick the
     closest match from https://docs.sailresearch.com/models, comparing
     capability tags, context window, and what the model is known to be good
     at. If a current model is not one Sail serves, research it (web search
     if available) to understand its strengths before choosing. If multiple
     Sail models are plausible, ask the user. Otherwise pick the best fit
     and explain the choice in your report. Check the /support page for any
     features this code uses that Sail doesn't serve, and flag them.

  3. Choose a completion window per call site. Omitting completion_window gives
     low-latency inference by default, at lower prices than traditional inference
     providers for many models. Workloads that can wait save more with balanced
     or flex. The live
     https://docs.sailresearch.com/completion-windows and
     https://docs.sailresearch.com/pricing pages are the source of truth for
     public windows, token prices, and scheduling behavior. If you can't fetch
     them, use this summary and decide how long each workload can wait:
     - asap: low-latency serving that is cheaper than traditional inference
       providers
     - balanced: more tokens per dollar for autonomous agents and pipelines;
       use it for workloads that can tolerate more latency
     - flex: the lowest prices for batch jobs, evals, and offline processing; it
       has no latency target and requires background=True on the Responses API
     If the workload's latency tolerance isn't obvious from the code, ask
     the user. Omit metadata.completion_window when the default low-latency
     behavior is acceptable. Set it explicitly for balanced or flex, or pin asap
     when the request must fail instead of using a fallback window.
     Confirm the chosen window is available for the chosen model on
     https://docs.sailresearch.com/pricing. Some models are flex-only.

  4. Make the changes wherever the client is configured or called:
     - base URL: use https://api.sailresearch.com/v1 for OpenAI-compatible
       clients (Responses and Chat Completions). For the Anthropic SDK, use
       the bare host https://api.sailresearch.com (e.g. set
       ANTHROPIC_BASE_URL=https://api.sailresearch.com). The SDK appends
       /v1/messages itself, so a /v1 base URL would resolve to /v1/v1/messages
       and 404
     - API key: read from the SAIL_API_KEY environment variable. Never hardcode
       a key or paste a literal key value into the code
       (the Anthropic SDK can pass it as `api_key`; `auth_token` also works)
     - model: the Sail model(s) chosen in step 2
     - metadata.completion_window: the window(s) chosen in step 3
     - add background=True for flex or very long-running requests
     Update env var names, .env.example files, config templates, and any
     README/docs references. Do not change prompts, tools, or business logic.

  5. Estimate the savings. Compare the published per-1M-token list prices
     (input, cached input, and output) of the previous model(s) against the
     chosen Sail model(s) at the chosen completion window(s) from
     https://docs.sailresearch.com/pricing. Research current provider list
     prices if you don't know them. State the comparison as a simple table
     and an approximate overall multiplier (e.g. "roughly 6x cheaper per
     token"). Do not present this as a precise bill forecast.

  6. Verify. Run the project's tests. Then make one real smoke request through
     the new configuration: if SAIL_API_KEY is already set, use it; if not,
     walk the user through creating a key at
     https://app.sailresearch.com/api-keys and setting SAIL_API_KEY, then run
     the smoke request once they have. Don't ask them to paste the key to you.
     Have them export it in their own shell.

  Finish with a short migration report: call sites changed; model mapping
  with rationale; completion window(s) with rationale; the price comparison
  from step 5; and anything that needs human follow-up (unsupported
  features, ambiguous choices, untested paths). Close by telling the user
  exactly where to set SAIL_API_KEY for their setup (locally and in their
  production/deployment environment) so the migrated code can authenticate.
  ```
</div>

## 1. Get your API key

Sign up at the [Sail dashboard](https://app.sailresearch.com/api-keys) and create an API key. Export it where your agent and app can read it:

```bash theme={null}
export SAIL_API_KEY="YOUR_SAIL_API_KEY"
```

## 2. See what changes

Already calling the OpenAI Responses API? The request and response are identical:

```python Sail Responses API theme={null}
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.your-provider.com/v1",  # [!code --]
    base_url="https://api.sailresearch.com/v1",  # [!code ++]
    api_key=os.environ["PROVIDER_API_KEY"],  # [!code --]
    api_key=os.environ["SAIL_API_KEY"],  # [!code ++]
)

response = client.responses.create(
    model="<your-current-model>",  # [!code --]
    model="<sail-model>",  # [!code ++]
    input="Explain the key ideas behind transformers.",
)
print(response.output_text)
```

Already calling the Anthropic Messages API? Keep the Anthropic SDK and point it at the bare Sail host. The SDK appends `/v1/messages` itself:

```python Sail Messages API theme={null}
import os

from anthropic import Anthropic

client = Anthropic(
    base_url="https://api.sailresearch.com",  # [!code ++]
    api_key=os.environ["ANTHROPIC_API_KEY"],  # [!code --]
    api_key=os.environ["SAIL_API_KEY"],  # [!code ++]
)

message = client.messages.create(
    model="<your-current-model>",  # [!code --]
    model="<sail-model>",  # [!code ++]
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain the key ideas behind transformers."}],
)
```

## Notes

* **Synchronous by default.** `responses.create` blocks and returns the completed response, exactly like OpenAI. For long-running work, pass `background=True` to get an ID back immediately and poll, avoiding HTTP timeouts. See the [Quickstart](/quickstart).
* **Pick a completion window** for each call site. Omit `completion_window` for the default low-latency behavior, which pairs low latency with Sail's cost efficiency. `balanced` buys more tokens per dollar for autonomous work, and `flex` offers the lowest prices for background batches. See [Completion windows](/completion-windows).
* **Messages API caveat.** System prompts, tool calling, and streaming are supported. Prompt caching (`cache_control`) is accepted but not yet applied, so expect full-price input reads for now. See the [API support matrix](/support).

## Next steps

<CardGroup cols={2}>
  <Card title="AI Quickstart" href="/ai-quickstart">
    Set your coding agent up with Sail's docs and skills.
  </Card>

  <Card title="Quickstart" href="/quickstart">
    Make your first request against Sail.
  </Card>

  <Card title="Models" href="/models">
    Browse supported models and pick a replacement.
  </Card>

  <Card title="Completion windows" href="/completion-windows">
    How the latency-for-price tradeoff works.
  </Card>

  <Card title="Pricing" href="/pricing">
    Per-token rates by model and completion window.
  </Card>

  <Card title="Cost calculator" href="/cost-calculator">
    Estimate the cost of running your agent on Sail vs traditional inference
    providers.
  </Card>

  <Card title="Support" href="mailto:support@sailresearch.com">
    Email us if you hit anything unexpected.
  </Card>
</CardGroup>