feat(gateway): rate-limit the new /v1/ocr endpoint

Main added a /v1/ocr endpoint not covered by the org rate limiter. Add it
to the per-path config (regular 300, dev 120, chat 30). OCR is available
to dev/chat plans (it consumes their plan credits, no coding-plan block),
so all three plan classes get a limit. Document the env vars and update
the rate-limits docs page accordingly.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

Author: steebchen

.env.example

@@ -81,6 +81,7 @@ TIMEOUT_MS=5000
 # GATEWAY_RATE_LIMIT_EMBEDDINGS_RPM=1200
 # GATEWAY_RATE_LIMIT_MODERATIONS_RPM=1200
 # GATEWAY_RATE_LIMIT_MODELS_RPM=1200
+# GATEWAY_RATE_LIMIT_OCR_RPM=300
 # GATEWAY_RATE_LIMIT_IMAGES_RPM=300
 # GATEWAY_RATE_LIMIT_AUDIO_SPEECH_RPM=300
 # GATEWAY_RATE_LIMIT_VIDEOS_RPM=120
@@ -93,6 +94,7 @@ TIMEOUT_MS=5000
 # GATEWAY_RATE_LIMIT_DEV_EMBEDDINGS_RPM=120
 # GATEWAY_RATE_LIMIT_DEV_MODERATIONS_RPM=120
 # GATEWAY_RATE_LIMIT_DEV_MODELS_RPM=120
+# GATEWAY_RATE_LIMIT_DEV_OCR_RPM=120
 # GATEWAY_RATE_LIMIT_DEV_IMAGES_RPM=120
 # GATEWAY_RATE_LIMIT_DEV_AUDIO_SPEECH_RPM=120
 # GATEWAY_RATE_LIMIT_DEV_VIDEOS_RPM=120
@@ -104,6 +106,7 @@ TIMEOUT_MS=5000
 # GATEWAY_RATE_LIMIT_CHATPLAN_EMBEDDINGS_RPM=120
 # GATEWAY_RATE_LIMIT_CHATPLAN_MODERATIONS_RPM=120
 # GATEWAY_RATE_LIMIT_CHATPLAN_MODELS_RPM=120
+# GATEWAY_RATE_LIMIT_CHATPLAN_OCR_RPM=30
 # GATEWAY_RATE_LIMIT_CHATPLAN_IMAGES_RPM=30
 # GATEWAY_RATE_LIMIT_CHATPLAN_AUDIO_SPEECH_RPM=30
 # GATEWAY_RATE_LIMIT_CHATPLAN_VIDEOS_RPM=12

apps/docs/content/resources/rate-limits.mdx

@@ -28,6 +28,7 @@ The default limits (requests per minute, per organization) are:
 | Embeddings           | `/v1/embeddings`       | 1200           |
 | Moderations          | `/v1/moderations`      | 1200           |
 | Models               | `/v1/models`           | 1200           |
+| OCR                  | `/v1/ocr`              | 300            |
 | Images               | `/v1/images`           | 300            |
 | Speech               | `/v1/audio/speech`     | 300            |
 | Videos               | `/v1/videos`           | 120            |
@@ -53,14 +54,15 @@ For example, an organization that has spent more than $10,000 gets a 4× multipl
 
 Organizations on a **Dev plan** (also called devpass) or a **Chat plan** have their own, tighter per-endpoint limits and do not receive the spend-based multiplier.
 
-Dev plans are inference-only and only cover **chat completions, messages, responses, and the models list**, each at a flat 120 requests-per-minute floor. The other endpoints (embeddings, moderations, images, speech, videos) are **not available** on Dev plans and are marked **—** below.
+Dev plans are inference-only and only cover **chat completions, messages, responses, the models list, and OCR**, each at a flat 120 requests-per-minute floor. The other endpoints (embeddings, moderations, images, speech, videos) are **not available** on Dev plans and are marked **—** below.
 
 | Endpoint             | Dev plan / min | Chat plan / min |
 | -------------------- | -------------- | --------------- |
 | Chat completions     | 120            | 60              |
 | Messages (Anthropic) | 120            | 60              |
 | Responses            | 120            | 60              |
 | Models               | 120            | 120             |
+| OCR                  | 120            | 30              |
 | Embeddings           | —              | 120             |
 | Moderations          | —              | 120             |
 | Images               | —              | 30              |

apps/gateway/src/lib/org-rate-limit.spec.ts

@@ -86,6 +86,7 @@ describe("resolvePathRateLimit", () => {
 		);
 		expect(resolvePathRateLimit("/v1/models")?.key).toBe("models");
 		expect(resolvePathRateLimit("/v1/messages")?.key).toBe("messages");
+		expect(resolvePathRateLimit("/v1/ocr")?.key).toBe("ocr");
 	});
 
 	it("matches sub-paths", () => {

apps/gateway/src/lib/org-rate-limit.ts

@@ -99,6 +99,13 @@ export const PATH_RATE_LIMITS: readonly PathRateLimitConfig[] = [
 		devDefaultRpm: 120,
 		chatDefaultRpm: 120,
 	},
+	{
+		key: "ocr",
+		prefix: "/v1/ocr",
+		defaultRpm: 300,
+		devDefaultRpm: 120,
+		chatDefaultRpm: 30,
+	},
 	{
 		key: "images",
 		prefix: "/v1/images",