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

> ## Agent Instructions
> Phaseo Gateway base URL: https://api.phaseo.app/v1. Send `Authorization: Bearer $PHASEO_API_KEY` with every request.
> Model IDs look like `provider/model`, for example `openai/gpt-6-astra`. Do not guess IDs: list them with `GET /v1/models` or check https://phaseo.app/models. `phaseo/free` routes to an available free model and needs no wallet balance.
> For new text integrations prefer `POST /v1/responses`. `POST /v1/chat/completions` (OpenAI format) and `POST /v1/messages` (Anthropic format) suit existing code.
> The full API contract is https://phaseo.app/docs/openapi/v1/openapi.yaml. Official SDKs: `@phaseo/sdk` (TypeScript) and `phaseo` (Python), plus Go, C#, PHP, Ruby and Rust.
> Search these docs over MCP at https://phaseo.app/docs/mcp, and install Phaseo skills with `npx skills add https://phaseo.app/docs`. If a page is wrong or out of date, report it with the MCP `submit_feedback` tool.
> Manage Phaseo accounts with the `phaseo` CLI (`npm install -g @phaseo/cli`, then `phaseo login` or `phaseo login --device-code`), the `/v1` Management API or the MCP server at `https://mcp.phaseo.app/mcp?access=manage`. Do not send users to the dashboard for account tasks. A person is still needed for sign-up, approving a sign-in, paying the first top-up on the checkout link that `phaseo credits add` returns when no card is saved, confirming each saved-card top-up from the emailed link, and account security (password, MFA, passkeys). Create API keys with `phaseo keys create --name <name> --json`; never guess one. Credit top-ups need `phaseo login --scopes billing:write` first. Task map: https://phaseo.app/docs/v1/developers/manage-from-an-agent.md.

# Service Tiers

> How Standard, Fast, Ultrafast, Flex, and Batch pricing modes work in Phaseo Gateway.

Service tiers let you choose between different pricing and delivery modes when a provider supports them.

Availability varies by provider and model. If a tier is not supported for the model you requested, the Gateway will not route to it.

> [!NOTE]
>
> Service tiers are currently available only for supported text models on supported providers.

`service_tier` is supported across all three text request surfaces:

* Anthropic-compatible Messages at `/v1/messages`
* OpenAI-compatible Chat Completions at `/v1/chat/completions`
* OpenAI-compatible Responses at `/v1/responses`

## Tier overview

| Tier | How to request it | Typical use |
| - | - | - |
| `Standard` | Default behavior. No extra field required. | General production traffic. |
| `Fast` | Set `service_tier: "fast"` on the request. | Faster or premium routing where supported. OpenAI also accepts `priority`. |
| `Ultrafast` | Set `service_tier: "ultrafast"` on the request. | Highest-speed routing where supported. |
| `Flex` | Set `service_tier: "flex"` on the request. | Lower-cost routing where supported. |
| `Batch` | Use the Batch API rather than `service_tier`. | Large deferred workloads where latency is less important. |

## API compatibility

Use the same `service_tier` field when you call any supported synchronous text API:

* [Anthropic Messages API reference](https://phaseo.app/docs/v1/api-reference/endpoint/anthropic-messages.md)
* [Chat Completions API reference](https://phaseo.app/docs/v1/api-reference/endpoint/chat-completions.md)
* [Responses API reference](https://phaseo.app/docs/v1/api-reference/endpoint/responses.md)
* [Shared parameter reference](https://phaseo.app/docs/v1/api-reference/parameters.md)

The accepted `service_tier` values are `standard`, `fast`, `ultrafast`, `priority`, `flex`, and `batch`. `Standard` is the default behavior when `service_tier` is omitted. Phaseo uses `Fast` as the canonical premium tier name. For OpenAI routes, `priority` is accepted as a provider-compatible alias and uses the same routing and pricing. `Batch` is handled by the Batch API rather than synchronous text requests.

> [!NOTE]
>
> Phaseo maps the normalized gateway values to provider-native controls internally. For example, an Anthropic route may receive Anthropic-native tier fields upstream, but the client-facing request still uses the gateway values listed here.

## Standard

`Standard` is the default routing mode. You do not need to set `service_tier` to use it.

```json theme={null}
{
  "model": "openai/gpt-5.5",
  "input": "Summarise this incident report."
}
```

## Fast

Use `Fast` when you want the provider's premium or higher-priority offer. Phaseo uses `fast` as its provider-neutral name. OpenAI calls this Fast mode and accepts both `fast` and `priority` on supported models.

```json theme={null}
{
  "model": "openai/gpt-5.5",
  "input": "Summarise this incident report.",
  "service_tier": "fast"
}
```

### Anthropic Messages example

```json theme={null}
{
  "model": "anthropic/claude-sonnet-4",
  "max_tokens": 512,
  "messages": [
    { "role": "user", "content": "Summarise this incident report." }
  ],
  "service_tier": "fast"
}
```

Phaseo maps this to the appropriate provider-native control when routing to Anthropic.

### Mistral Priority and EU routing

Mistral Priority Tier requires an eligible Mistral enterprise account. Phaseo maps
`priority` to Mistral's automatic priority mode and bills the tier reported by Mistral;
if Mistral falls back to Standard, Standard pricing is used.

GLM 5.2 can be pinned to Mistral's EU regional endpoint with the `mistral-eu`
provider offer:

```json theme={null}
{
  "model": "z-ai/glm-5.2",
  "messages": [
    { "role": "user", "content": "Summarise this incident report." }
  ],
  "service_tier": "priority",
  "provider": {
    "only": ["mistral-eu"],
    "required_execution_region": "eu"
  }
}
```

Mistral regional inference applies a 10% price uplift. Batch pricing is available
on the global Mistral offer, but Mistral does not support Batch on regional endpoints.

Phaseo records Mistral's published Batch and Priority reference rates separately
from runtime availability. A price shown in the catalog does not make that tier
routable: Priority remains disabled unless the specific Mistral route advertises
Priority support, and Batch must use the global Mistral Batch API. Priority eligibility
still depends on the Mistral account and model.

## Ultrafast

Use `Ultrafast` for the highest-speed service tier when the model and provider offer it. Phaseo routes only to an Ultrafast-priced or Ultrafast-specific route; it does not fall back to Fast or Standard when that tier is unavailable.

```json theme={null}
{
  "model": "<model-id-with-ultrafast-pricing>",
  "input": "Summarise this incident report.",
  "service_tier": "ultrafast"
}
```

## Flex

Use `Flex` when the provider exposes a lower-cost service tier and you are willing to trade for that pricing mode.

```json theme={null}
{
  "model": "openai/gpt-5.5",
  "input": "Summarise this incident report.",
  "service_tier": "flex"
}
```

### Chat Completions example

```json theme={null}
{
  "model": "openai/gpt-5.5",
  "messages": [
    { "role": "user", "content": "Summarise this incident report." }
  ],
  "service_tier": "flex"
}
```

### Responses example

```json theme={null}
{
  "model": "openai/gpt-5.5",
  "input": [
    { "role": "user", "content": "Summarise this incident report." }
  ],
  "service_tier": "flex"
}
```

## Batch

`batch` is a recognized tier value for batch execution, but synchronous text APIs reject `service_tier: "batch"` with a validation error that points to the Batch API.

Use the Batch API or batch job workflow because batch pricing applies to deferred batch execution rather than normal synchronous requests.

## Notes

* Tier support is provider-specific and model-specific.
* Pricing cards on model pages show the tier-specific rates when we have data for them.
* Some providers expose specialized upstream offers that Phaseo maps into a unified tiered experience in the catalog.
* Client-facing `service_tier` values are normalized across supported text surfaces; provider-native names are handled inside the gateway.

## Related pages

* [Anthropic Messages API reference](https://phaseo.app/docs/v1/api-reference/endpoint/anthropic-messages.md)
* [Chat Completions API reference](https://phaseo.app/docs/v1/api-reference/endpoint/chat-completions.md)
* [Responses API reference](https://phaseo.app/docs/v1/api-reference/endpoint/responses.md)
* [Parameters](https://phaseo.app/docs/v1/api-reference/parameters.md)
* [Routing and Fallbacks](https://phaseo.app/docs/v1/guides/routing-and-fallbacks.md)
* [Chat completions (TypeScript SDK)](https://phaseo.app/docs/v1/sdk-reference/typescript/chat-completions.md)
* [Responses (TypeScript SDK)](https://phaseo.app/docs/v1/sdk-reference/typescript/responses.md)


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