Service Tiers

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.

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.
`Priority`	Set `service_tier: "priority"` on the request.	Faster or premium routing where supported. OpenAI also accepts `fast`.
`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:

The accepted service_tier values are standard, fast, priority, flex, and batch. Standard is the default behavior when service_tier is omitted. Phaseo uses Priority as the canonical premium tier name. For OpenAI routes, fast 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.

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.

{
  "model": "openai/gpt-5.5",
  "input": "Summarise this incident report."
}

Priority

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

{
  "model": "openai/gpt-5.5",
  "input": "Summarise this incident report.",
  "service_tier": "priority"
}

Anthropic Messages example

{
  "model": "anthropic/claude-sonnet-4",
  "max_tokens": 512,
  "messages": [
    { "role": "user", "content": "Summarise this incident report." }
  ],
  "service_tier": "priority"
}

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:

{
  "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.

Flex

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

{
  "model": "openai/gpt-5.5",
  "input": "Summarise this incident report.",
  "service_tier": "flex"
}

Chat Completions example

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

Responses example

{
  "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.

Overview

Models & Routing

Features

Integrations

Workspace & Access

Reliability & Operations

Platform & Research

Migration Guides

Community

Tier overview

API compatibility

Standard

Priority

Anthropic Messages example

Mistral Priority and EU routing

Flex

Chat Completions example

Responses example

Batch

Notes

​Tier overview

​API compatibility

​Standard

​Priority

​Anthropic Messages example

​Mistral Priority and EU routing

​Flex

​Chat Completions example

​Responses example

​Batch

​Notes

​Related pages

Tier overview

API compatibility

Standard

Priority

Anthropic Messages example

Mistral Priority and EU routing

Flex

Chat Completions example

Responses example

Batch

Notes

Related pages