Deploy Claude Desktop on 3P with an LLM gateway changedthird-party/claude-desktop/gateway
Nearest release: v2.1.319, published 20 hours before upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Upstream edited this page at 6 Nov 2026 21:13 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 6 Nov 2026 21:37 UTC.
Upstream edited
Recorded here
Lines+4added
Lines−4removed
From line
9
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits52to this page, all time
The whole hunk
from line 9, old and new numbered
/
from line 9
99* `POST /v1/messages` with [streaming](https://docs.claude.com/en/api/streaming) and [tool use](https://docs.claude.com/en/docs/tool-use) is required.
1010* `GET /v1/models` is optional. If the gateway implements it, Claude Desktop on 3P auto-discovers available models; if not, set `inferenceModels` explicitly.
1111
12The gateway should also preserve [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching). Cowork and Code sessions send `cache_control` breakpoints with each turn so that the provider can reuse the tool definitions, system prompt, and earlier turns of the conversation instead of reprocessing them. A gateway that forwards these fields, or translates them for its upstream provider, keeps that behavior. A gateway that strips `cache_control`, or that changes the system prompt or tool list from one request to the next, makes the provider reprocess the whole conversation on every turn at full input-token cost and higher latency. To verify, check the [usage fields](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#tracking-cache-performance) your gateway returns or logs for Claude Desktop traffic: after the first request of a session, `cache_read_input_tokens` should be well above zero on most requests. If it is zero on every request, review the gateway's request transformation and caching settings for the route that serves Claude models.
12The gateway should also preserve [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching). Chat, Cowork, and Code sessions send `cache_control` breakpoints with each turn so that the provider can reuse the tool definitions, system prompt, and earlier turns of the conversation instead of reprocessing them. A gateway that forwards these fields, or translates them for its upstream provider, keeps that behavior. A gateway that strips `cache_control`, or that changes the system prompt or tool list from one request to the next, makes the provider reprocess the whole conversation on every turn at full input-token cost and higher latency. To verify, check the [usage fields](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#tracking-cache-performance) your gateway returns or logs for Claude Desktop traffic: after the first request of a session, `cache_read_input_tokens` should be well above zero on most requests. If it is zero on every request, review the gateway's request transformation and caching settings for the route that serves Claude models.
1313
14In each response's `usage`, return the provider's `cache_creation` object with its `ephemeral_5m_input_tokens` and `ephemeral_1h_input_tokens` fields. Without that object, the [API request event](https://claude.com/docs/cowork/monitoring.md#api-request-event) in your OpenTelemetry export reports `0` for both `cache_creation_5m_tokens` and `cache_creation_1h_tokens`.
14In Chat and Cowork, the main conversation's breakpoints ask for a one-hour lifetime (`"ttl": "1h"`). In each response's `usage`, return the provider's `cache_creation` object with its `ephemeral_5m_input_tokens` and `ephemeral_1h_input_tokens` fields. Without that object, the [API request event](https://claude.com/docs/cowork/monitoring.md#api-request-event) in your OpenTelemetry export reports `0` for both `cache_creation_5m_tokens` and `cache_creation_1h_tokens`.
1515
1616## Choose an authentication approach
1717
from line 525
525525
526526If your gateway serves Claude models under routing aliases, list each alias in `inferenceModels` and set `behavesAs` on its entry to the ID of the Claude model it routes to, such as `claude-sonnet-5`. For an alias without a model version, users then get that model's **Effort** control, and sessions assume that model's context window. Requires Claude Desktop 4.29.0 or later. For an alias that contains a model version, see [Map an unrecognized model ID to a Claude model](https://claude.com/docs/third-party/claude-desktop/models.md#map-an-unrecognized-model-id-to-a-claude-model).
527527
528Your gateway can mark which Claude tier a model serves by returning an `anthropic_family_tier` field (a tier name such as `sonnet` or `opus`) on that model object in its `/v1/models` response, optionally with `is_family_default: true` when several models map to the same tier. The app uses the marked model when it needs that tier, for example to resolve a bare `sonnet` alias. The app also reads other optional fields on each model object. `display_name` sets the picker label when the app cannot derive one from the model ID. `description` adds a one-line description beneath the label (Claude Desktop 1.49585.0 or later). `supports_1m: true`, or a `max_input_tokens` value of 1,000,000 or more, marks a discovered model as supporting the 1M-token context window, as `supports1m` does on an `inferenceModels` entry.
528Your gateway can mark which Claude tier a model serves by returning an `anthropic_family_tier` field (a tier name such as `sonnet` or `opus`) on that model object in its `/v1/models` response, optionally with `is_family_default: true` when several models map to the same tier. The app and its sessions use the marked model when they need that tier, such as for a sub-agent that asks for `sonnet`, even if the user picked another model. The app also reads other optional fields on each model object. `display_name` sets the picker label when the app cannot derive one from the model ID. `description` adds a one-line description beneath the label (Claude Desktop 1.49585.0 or later). `supports_1m: true`, or a `max_input_tokens` value of 1,000,000 or more, marks a discovered model as supporting the 1M-token context window, as `supports1m` does on an `inferenceModels` entry.
529529
530530If your gateway doesn't implement `GET /v1/models`, give every `inferenceModels` entry the full model ID your gateway accepts. When every entry is a full model ID, the app skips the `/v1/models` call automatically. A bare tier alias such as `sonnet` can't be resolved without discovery, so a list that contains one keeps discovery on. On earlier app versions that don't skip the call automatically, also set [`modelDiscoveryEnabled`](https://claude.com/docs/third-party/claude-desktop/configuration#modeldiscoveryenabled) to `false`. If discovery stays on, a gateway that answers the call with an error makes the app fall back to the `inferenceModels` list immediately. A gateway that accepts the call and hangs delays the model list by up to 10 seconds at launch.
531531
No line in this hunk matches that.