multi-router.aidocs

Providers & Models

Model Catalog

The catalog of every model Multi-Router serves: identities, capabilities, limits, prices, lifecycle and updates.

For each model, the catalog records the identity, mode, capabilities and limits, and for each offering of the model it records the provider, variant, regions, model ids and prices. Multi-Router uses the catalog to check every request before calling the provider, to select the model id sent upstream, and to compute the cost of each request. The catalog is versioned and published by Multi-Router, and every installation serves one catalog version at a time.

Model entries

A model entry describes one model independently of where it is served. The Models page shows these fields in the Baseline panel of each model:

FieldDescription
PublisherThe company that built the model, such as Anthropic.
SlugThe model's unique name, such as anthropic/claude-sonnet-4.6. See Overview.
ProductThe product line the model belongs to, such as Claude Sonnet or Qwen.
VersionThe model version and its format, such as 4.6 · semver, or a date or snapshot id.
ReleasedThe release date, when the publisher states one.
ModeThe type of model, such as Chat or Embedding.
ContextThe context window and the maximum output tokens, such as 1,000,000 · 128,000 out.
StatusThe lifecycle status: active, deprecated or retired.
Replaced byThe slug of the successor model, when the publisher names one.

The Baseline panel also lists the model's capabilities, input modalities and aliases, with a link to the publisher's documentation.

Modes

The mode is the type of work a model performs. The Chat Completions and Messages endpoints serve chat models, and a request for a model of another mode returns wrong_endpoint_for_mode.

ModeDashboard labelModels
chatChatConversational and instruction models.
responsesResponsesModels offered through the OpenAI Responses API.
embeddingEmbeddingText embedding models.
image_generationImage genImage generation models.
image_editImage editImage editing models.
audio_transcriptionAudio transcribeSpeech-to-text models.
audio_speechAudio speechText-to-speech models.
realtimeRealtimeLow-latency audio and text conversation models.
rerankRerankSearch reranking models.
moderationModerationContent moderation models.
ocrOCRDocument text extraction models.
video_generationVideo genVideo generation models.
completionCompletionLegacy text completion models.

Capabilities and modalities

Capabilities are the request features a model supports, and modalities are the content types it accepts and produces, such as text, image, audio, video and PDF. Multi-Router checks every chat request against the model's capabilities and its image input modality, and rejects a request that uses a feature the model lacks before calling the provider:

CheckRequest featureError
Streamingstream: truestreaming_not_supported
ToolsA non-empty tools listtools_not_supported
Parallel tool callsparallel_tool_calls: trueparallel_tool_calls_not_supported
Structured outputA json_object or json_schema response formatstructured_output_not_supported
Reasoningreasoning_effort or thinkingreasoning_not_supported
Prompt cachingprompt_cache_key or any cache_controlprompt_caching_not_supported
Image input modalityImage content in a messagemodality_not_supported

Offerings

An offering is one way to call a model: a provider and variant, with the regions where it is available. Each region carries the model id Multi-Router sends to the provider and the price. An offering can set limits or capabilities that differ from the model's baseline, such as a smaller context window on one provider, and an expanded offering on the Models page shows them as Capability overrides and as Context or Max output with the baseline value. The Offerings panel lists each offering's Vendor, Variant, Regions and Pricing, marks whether the variant is a fixed snapshot or a rolling version the provider updates, and marks custom offerings. Expanding an offering shows every region with its model id and prices. See Regions & Variants.

Prices

Prices are set for each region of each offering, in US dollars per million tokens unless noted, and are the providers' published list prices.

PriceDescriptionUsed in cost
InputPrompt tokens that are not read from or written to the cache.Yes
OutputCompletion tokens, including reasoning tokens.Yes
Cache readPrompt tokens read from the prompt cache.Yes
Cache write (5 minutes)Prompt tokens written to the cache with a 5-minute lifetime.Yes
Cache write (1 hour)Prompt tokens written to the cache with a 1-hour lifetime.Yes
Long contextRates that replace all of the above when the prompt, including cached tokens, reaches a threshold such as 200,000 tokens.Yes
Service tiersRates for the Batch, Priority, Flex and Fast tiers some providers offer, each with its own long context rates. The Fast tier applies when the provider reports that it served the request in fast mode.Fast tier
Tool feesFees for provider-run tools, such as web search per 1,000 calls.Web search
Cache storageThe cost of keeping one million cached tokens for one hour.No
Modality ratesInput or output rates for audio, image or video content that differ from the token rates.No
Unit pricesPrices per image, audio minute, page, video second, character, search or request, for models priced by unit.No

Multi-Router computes the cost of each request from the token counts, the number of web searches and the service tier the provider reports, and the price of the region the request was served in, and records it in Traffic, where it also counts toward budgets. A price part the catalog omits is charged at zero, and an offering whose provider publishes no price shows No pricing published on the Models page. Negotiated rates are applied with Custom Models & Pricing.

Lifecycle

The lifecycle status records whether a model is still offered. Each model has its own status, and each offering of a model can also have a status of its own:

StatusModelOffering
ActiveServed normally.Served normally.
DeprecatedServed, with the response headers x-mr-model-deprecated: true and, when the catalog names a successor, x-mr-model-replaced-by.Served normally.
RetiredRefused with model_retired, whose message names the successor when there is one.Refused with router_variant_retired for routers set to the retired variant.

A model or offering with a scheduled retirement time becomes retired at that time, without a new catalog version. Claude Proxies serve active models only, and refuse a deprecated or retired model with HTTP 404 and a message that names its status.

Browsing the catalog

The Models page in the dashboard lists every model in the catalog, including models from providers the organization holds no key for, together with the organization's model groups and the installation's custom models.

ControlUse
Pinned viewsAll models, Active, Reasoning, Vision and Tools.
My viewsSaved views. Save view stores the current filters, search, status and Show choice.
ShowAll, Models or Groups.
StatusAll, Active or Deprecated. All includes retired models.
FiltersPublishers, Vendors, Capabilities (Vision, Audio, Video, Tools, Reasoning, Caching, Structured, Parallel tools, Streaming) and Mode (Chat only, All modes or a single mode).
SearchMatches the slug, name, publisher, aliases and provider model ids.
ColumnsKind, Publisher, Vendors, Capabilities, Context and Price, kept for each browser.
Engineering · org_7Tq2Wd9KxP

All models· Models

New groupSave view
Show:
AllModelsGroups
Status:
AllActiveDeprecated
Filters1
5.
Models16 of 281 · 0 groups · 16 models
1–16 of 1625 / page
Columns
NameKindPublisherVendorsCapabilitiesContextPrice
Claude Opus 5.5AnthropicAnthropicBedrock×2Vertex AI1M$4.00–4.40 / $20.00–22.00
Claude Fable 5.1AnthropicAnthropicBedrock×2Vertex AI1M$10.00–11.00 / $50.00–55.00
GPT-5.1OpenAIOpenAI400K$1.25 / $10.00
GPT-5.2OpenAIOpenAI400K$1.75 / $14.00
GPT-5.2-proOpenAIOpenAI400K$21.00 / $168.00
GPT-5.3-codexOpenAIOpenAI400K$1.75 / $14.00
GPT-5.4OpenAIOpenAI1.1M$2.50–2.75 / $15.00–16.50
GPT-5.4-miniOpenAIOpenAI400K$0.75–0.82 / $4.50–4.95
GPT-5.4-nanoOpenAIOpenAI400K$0.20–0.22 / $1.25–1.38
GPT-5.4-proOpenAIOpenAI1.1M$30.00–33.00 / $180.00–198.00
GPT-5.5OpenAIOpenAI1.1M$5.00–5.50 / $30.00–33.00
GPT-5.5-proOpenAIOpenAI1.1M$30.00–33.00 / $180.00–198.00
GPT-5.6-cyberOpenAIOpenAI400K$12.50 / $75.00
GPT-5.6-lunaOpenAIBedrock×2OpenAI1.1M$0.20–0.22 / $1.20–1.32
GPT-5.6-solOpenAIBedrock×2OpenAI1.1M$4.00–4.40 / $20.00–22.00
GPT-5.6-terraOpenAIBedrock×2OpenAI1.1M$2.00–2.20 / $12.00–13.20
Capabilities:streamingtoolsparallel tool callsstructured outputreasoningprompt cachingGroup guarantees use capability intersection and minimum context. Input and output price envelopes stay separate.
The Models table filtered to active Anthropic and OpenAI models, searching for the latest Claude and GPT-5 releases. Select to enlarge.

The Price column shows the lowest-to-highest input and output prices across every region, a model priced by unit shows its unit price, and a model with no published price shows a dash. Selecting a model opens its Baseline and Offerings panels. In an expanded offering that publishes more than one rate, the Rate switch selects among the rates it publishes, such as Standard, Long Context, Batch, Priority, Flex, Fast and Tools.

Engineering · org_7Tq2Wd9KxP

All models· Models

New groupSave view
Show:
AllModelsGroups
Status:
AllActiveDeprecated
Filters
opus
Models9 of 281 · 0 groups · 9 models
1–9 of 925 / page
Columns
NameKindPublisherVendorsCapabilitiesContextPrice
Claude Opus 5.5AnthropicAnthropicBedrock×2Vertex AI1M$4.00–4.40 / $20.00–22.00
Baseline
Publisher
Anthropic
Slug
anthropic/claude-opus-5.5
Product
Claude Opus
Version
5.5 · semver
Released
2026-09-22
Mode
Chat
Context
1,000,000 · 128,000 out
Status
active
Capabilities
Streaming
Tools
Parallel tool calls
Structured output
Reasoning
Prompt caching
Modalities
textimagepdf
platform.claude.com/docs/en/about-cl… ↗
Offerings — 4 routable coordinates
VendorVariantRegionsPricing
AnthropicStandardsnapshot2 regionsPrice varies by region
BedrockGeosnapshot18 regionsSame price in every region

Inference stays inside one geography (US, EU, APAC, Japan or Australia).

ap-northeast-1jp.anthropic.claude-opus-5-5$4.40 in · $22.00 out · $0.22 cache read · $5.50 5m cache write · $8.80 1h cache write
ap-northeast-3jp.anthropic.claude-opus-5-5$4.40 in · $22.00 out · $0.22 cache read · $5.50 5m cache write · $8.80 1h cache write
ap-southeast-2au.anthropic.claude-opus-5-5$4.40 in · $22.00 out · $0.22 cache read · $5.50 5m cache write · $8.80 1h cache write
ap-southeast-4au.anthropic.claude-opus-5-5$4.40 in · $22.00 out · $0.22 cache read · $5.50 5m cache write · $8.80 1h cache write
ca-central-1us.anthropic.claude-opus-5-5$4.40 in · $22.00 out · $0.22 cache read · $5.50 5m cache write · $8.80 1h cache write
ca-west-1us.anthropic.claude-opus-5-5$4.40 in · $22.00 out · $0.22 cache read · $5.50 5m cache write · $8.80 1h cache write
eu-central-1eu.anthropic.claude-opus-5-5$4.40 in · $22.00 out · $0.22 cache read · $5.50 5m cache write · $8.80 1h cache write
eu-central-2eu.anthropic.claude-opus-5-5$4.40 in · $22.00 out · $0.22 cache read · $5.50 5m cache write · $8.80 1h cache write
eu-north-1eu.anthropic.claude-opus-5-5$4.40 in · $22.00 out · $0.22 cache read · $5.50 5m cache write · $8.80 1h cache write
eu-south-1eu.anthropic.claude-opus-5-5$4.40 in · $22.00 out · $0.22 cache read · $5.50 5m cache write · $8.80 1h cache write
eu-south-2eu.anthropic.claude-opus-5-5$4.40 in · $22.00 out · $0.22 cache read · $5.50 5m cache write · $8.80 1h cache write
eu-west-1eu.anthropic.claude-opus-5-5$4.40 in · $22.00 out · $0.22 cache read · $5.50 5m cache write · $8.80 1h cache write
eu-west-2eu.anthropic.claude-opus-5-5$4.40 in · $22.00 out · $0.22 cache read · $5.50 5m cache write · $8.80 1h cache write
eu-west-3eu.anthropic.claude-opus-5-5$4.40 in · $22.00 out · $0.22 cache read · $5.50 5m cache write · $8.80 1h cache write
us-east-1us.anthropic.claude-opus-5-5$4.40 in · $22.00 out · $0.22 cache read · $5.50 5m cache write · $8.80 1h cache write
us-east-2us.anthropic.claude-opus-5-5$4.40 in · $22.00 out · $0.22 cache read · $5.50 5m cache write · $8.80 1h cache write
us-west-1us.anthropic.claude-opus-5-5$4.40 in · $22.00 out · $0.22 cache read · $5.50 5m cache write · $8.80 1h cache write
us-west-2us.anthropic.claude-opus-5-5$4.40 in · $22.00 out · $0.22 cache read · $5.50 5m cache write · $8.80 1h cache write
BedrockGlobalsnapshot33 regionsSame price in every region
Vertex AIStandardsnapshot3 regionsPrice varies by region

Each row is a curated, working way to call this model. Picking one (with a region) happens when you wire a router; cross-vendor fallback composes routers.

Claude Opus 5AnthropicAnthropicBedrock×2Vertex AI1M$5.00–5.50 / $25.00–27.50
Claude Opus 4.8AnthropicAnthropicBedrock×3Vertex AI1M$5.00–5.50 / $25.00–27.50
Claude Opus 4.7AnthropicAnthropicBedrock×3Vertex AI1M$5.00–5.50 / $25.00–27.50
Claude Opus 4.6AnthropicAnthropicBedrock×3Vertex AI1M$5.00–5.50 / $25.00–27.50
Claude Opus 4.5AnthropicAnthropic×2Bedrock×2Vertex AI200K$5.00–5.50 / $25.00–27.50
Claude Opus 4.1deprecatedAnthropicAnthropic×2BedrockVertex AI200K$15.00 / $75.00
Claude Opus 4deprecatedAnthropicAnthropicVertex AI200K$15.00 / $75.00
Claude Opus 3retiredAnthropicAnthropic200K—
Capabilities:streamingtoolsparallel tool callsstructured outputreasoningprompt cachingGroup guarantees use capability intersection and minimum context. Input and output price envelopes stay separate.
Claude Opus 5.5 expanded: the Baseline panel, its four offerings, and Bedrock Geo opened to its model id and price in each region. Select to enlarge.

Listing models with the API

GET /v1/models lists the chat models the API token's organization can call: models that are active or deprecated and have an offering that is not retired from a provider for which the organization holds an enabled provider key, together with custom endpoint models when the organization holds a Custom endpoint key. The endpoint requires the models:read scope and returns the OpenAI list format, sorted by publisher and slug. In each entry, owned_by is the publisher and created is the publication time of the catalog version in effect, which is the same for every model. The full catalog, with every model's offerings, regions and prices, is read with GET /v1/catalog/models and GET /v1/catalog/models/{publisher}/{model}, with the same scope; see Catalog.

Requestbash
curl https://api.multi-router.ai/v1/models \
  -H "Authorization: Bearer $MR_API_KEY"
Response 200json
{
  "object": "list",
  "data": [
    { "id": "anthropic/claude-haiku-4.5", "object": "model", "created": 1790812800, "owned_by": "anthropic" },
    { "id": "anthropic/claude-sonnet-4.6", "object": "model", "created": 1790812800, "owned_by": "anthropic" }
  ]
}

With an x-mr-router header that names a Claude Proxy, the endpoint returns the models that Claude Proxy serves in the Anthropic format, which Claude Code uses to list its models, sorted by id. Each entry carries the model id the proxy's route uses, the display name, the release date at midnight UTC, and the token limits. A header that names any other kind of router returns 404.

Response with x-mr-router 200json
{
  "data": [
    {
      "type": "model",
      "id": "claude-sonnet-4-6",
      "display_name": "Claude Sonnet 4.6",
      "created_at": "2026-02-17T00:00:00Z",
      "max_input_tokens": 1000000,
      "max_tokens": 128000
    }
  ],
  "has_more": false,
  "first_id": "claude-sonnet-4-6",
  "last_id": "claude-sonnet-4-6"
}

Catalog updates

Multi-Router publishes the catalog as numbered versions at models.multi-router.ai, and a published version never changes. A new version adds models and offerings, updates prices, and records deprecations and retirements. Multi-Router manages catalog updates on the hosted service. On a self-hosted installation, the server administrator controls them on the Catalog tab of the Admin page:

ControlUse
Catalog UpdatesTurns checking the publisher on or off. While it is on, the installation checks every 30 seconds; turning it off keeps the version in effect.
Publisher URLThe address the catalog is fetched from, which can point to a private mirror.
Rollout modeAuto applies each new version as it is fetched. Manual holds it for review, with Review diff, Approve go-live and Discard.
RefreshFetches the latest version immediately.
Recent versionsLists earlier versions, with Roll back. Rolling back sets Rollout mode to Manual.

Every fetched version is validated before use, a version that fails validation is skipped, and automatic updates only move forward. Upgrading the server installs the catalog bundled with the new release when it is newer than the version in effect. While an installation serves a catalog bundled with its release, the Models page shows a banner stating the version and that model data may be out of date. See Self-Hosting.

Errors

Catalog checks on chat requests return HTTP 400 with the following errors (503 for catalog_unavailable), in addition to the capability errors above. In a fallback router, a member that fails a catalog check is skipped and the next member is tried.

ErrorCause
model_not_foundThe model is not in the catalog.
wrong_endpoint_for_modeThe model is not a chat model.
provider_not_offeredThe router's provider does not offer the model.
model_retiredThe model is retired. The message names the successor when there is one.
router_variant_missingThe router names no variant for the model. The message lists the valid variants.
router_variant_not_foundThe router's variant is not offered for the model. The message lists the valid variants.
router_variant_retiredThe router's variant is retired. The message lists the variants still served.
publisher_not_supportedThe router's provider is Google Vertex and the model is not published by Anthropic.
region_not_servedThe model is not offered in the selected region.
catalog_unavailableThe catalog could not be read. Retry the request.
Google VertexModel Group
Was this helpful?