Sync ollama docs from eab97e9f on 2026-10-12

2026-10-12 04:00:05 +00:00
parent f10d4bfbcc
commit a8b97b807a
26 changed files with 1820 additions and 782 deletions
@@ -96,11 +96,7 @@ components:
          type: boolean
          default: true
        think:
-          oneOf:
-            - type: boolean
-            - type: string
-              enum: [high, medium, low, max]
-          description: When true, returns separate thinking output in addition to content. Can be a boolean (true/false) or a string ("high", "medium", "low", "max") for supported models, with "max" requesting the highest thinking level.
+          $ref: "#/components/schemas/ThinkValue"
        raw:
          type: boolean
          description: When true, returns the raw response from the model without any prompt templating
@@ -294,11 +290,7 @@ components:
          type: boolean
          default: true
        think:
-          oneOf:
-            - type: boolean
-            - type: string
-              enum: [high, medium, low, max]
-          description: When true, returns separate thinking output in addition to content. Can be a boolean (true/false) or a string ("high", "medium", "low", "max") for supported models, with "max" requesting the highest thinking level.
+          $ref: "#/components/schemas/ThinkValue"
        keep_alive:
          oneOf:
            - type: string
@@ -410,6 +402,29 @@ components:
        done:
          type: boolean
          description: True for the final event in the stream
+    ThinkValue:
+      description: Controls a model's thinking output. Use `/api/show` to discover the supported values and default for the selected model. `true` requests thinking, `false` requests no thinking output, and `null` uses the model default. String values are model-defined; supported names must match `/api/show` exactly. Numbers are not supported.
+      oneOf:
+        - type: boolean
+        - type: string
+        - type: "null"
+    Thinking:
+      type: object
+      required: [values, default]
+      description: Thinking controls advertised by a model. Models without thinking metadata omit this field.
+      properties:
+        values:
+          type: array
+          description: Values explicitly supported by the model's `think` request field. Booleans represent on/off controls and strings represent model-defined levels. An array containing only `false` identifies a model without thinking support.
+          items:
+            oneOf:
+              - type: boolean
+              - type: string
+        default:
+          description: Value used when `think` is not set. For models that use this metadata for named thinking levels, unsupported names resolve to this default.
+          oneOf:
+            - type: boolean
+            - type: string
    StatusEvent:
      type: object
      properties:
@@ -498,6 +513,16 @@ components:
        parser:
          type: string
          description: Name of the parser for the model
+        files:
+          type: object
+          additionalProperties:
+            type: string
+          description: Source file names mapped to their SHA-256 digests. Split GGUF models must include each shard under its original split filename.
+        draft_files:
+          type: object
+          additionalProperties:
+            type: string
+          description: Draft source file names mapped to their SHA-256 digests
        license:
          oneOf:
            - type: string
@@ -518,7 +543,18 @@ components:
            $ref: "#/components/schemas/ChatMessage"
        quantize:
          type: string
-          description: Quantization level to apply (e.g. `q4_K_M`, `q8_0`)
+          description: Quantization level to apply during import (e.g. `nvfp4`)
+        draft_quantize:
+          type: string
+          description: Quantization level to apply to draft weights during import
+        requires:
+          type: string
+          description: Minimum Ollama version required by the model
+        capabilities:
+          type: array
+          items:
+            type: string
+          description: Capabilities to add without removing inherited or inferred capabilities (e.g. `decision` for compatible decision models)
        stream:
          type: boolean
          default: true
@@ -581,6 +617,8 @@ components:
    ShowResponse:
      type: object
      properties:
+        thinking:
+          $ref: "#/components/schemas/Thinking"
        parameters:
          type: string
          description: Model parameter settings serialized as text
@@ -790,6 +828,324 @@ components:
          items:
            $ref: "#/components/schemas/TokenLogprob"
          description: Most likely tokens and their log probabilities at this position
+    SystemOneContent:
+      description: A nonempty string, or an object or array serialized as JSON text. Not interpreted as chat messages or multimodal input.
+      oneOf:
+        - type: string
+          pattern: '\S'
+        - type: object
+          additionalProperties: true
+        - type: array
+          items: {}
+    SystemOneChoiceQuestion:
+      title: Choice
+      type: object
+      required: [type, instructions, criteria]
+      properties:
+        type:
+          type: string
+          enum: [choice]
+        instructions:
+          $ref: "#/components/schemas/SystemOneContent"
+        criteria:
+          type: object
+          description: Option keys mapped to descriptions, or null for a bare label. Keys must not be blank; ties follow the model's option order. The option limit depends on the model.
+          minProperties: 2
+          maxProperties: 255
+          propertyNames:
+            pattern: '\S'
+          additionalProperties:
+            type: [string, "null"]
+    SystemOneNoulQuestion:
+      title: Noul
+      type: object
+      required: [type, instructions]
+      properties:
+        type:
+          type: string
+          enum: [noul]
+        instructions:
+          $ref: "#/components/schemas/SystemOneContent"
+        criteria:
+          type: object
+          description: Optional descriptions for the two outcomes. Omitted entries use model-specific defaults.
+          properties:
+            "false":
+              type: string
+              default: "No"
+            "true":
+              type: string
+              default: "Yes"
+          additionalProperties: false
+    SystemOneScoreQuestion:
+      title: Score
+      type: object
+      required: [type, instructions, criteria]
+      properties:
+        type:
+          type: string
+          enum: [score]
+        instructions:
+          $ref: "#/components/schemas/SystemOneContent"
+        criteria:
+          type: array
+          description: Descriptions ordered from the lowest score (index 0) to the highest. Defines a scale from 0 to the number of criteria minus 1. The maximum number of levels depends on the model.
+          minItems: 2
+          maxItems: 26
+          items:
+            type: string
+    SystemOneRequest:
+      type: object
+      required: [model, state, questions]
+      properties:
+        model:
+          type: string
+          pattern: '\S'
+          description: Local model trained for System One, such as nimble. Requires compatible GGUF weights and a scoring-capable runner; cloud and MLX/Safetensors models are not supported.
+        state:
+          $ref: "#/components/schemas/SystemOneContent"
+        images:
+          type: array
+          description: Base64-encoded images shared by all questions, in request order. Requires Clef or Clef Flash with vision weights. URLs and data URLs are not supported.
+          items:
+            type: string
+            format: byte
+        questions:
+          type: object
+          description: Named questions about the shared state. Answers are not passed to later questions.
+          minProperties: 1
+          maxProperties: 64
+          propertyNames:
+            pattern: '\S'
+          additionalProperties:
+            oneOf:
+              - $ref: "#/components/schemas/SystemOneChoiceQuestion"
+              - $ref: "#/components/schemas/SystemOneNoulQuestion"
+              - $ref: "#/components/schemas/SystemOneScoreQuestion"
+        keep_alive:
+          oneOf:
+            - type: string
+            - type: number
+          description: How long to keep the model loaded after the request, as a duration string (such as 5m) or seconds. Zero unloads after the request; a negative value keeps it loaded. Defaults to the server's keep-alive setting (5m unless configured otherwise).
+    SystemOneProbabilities:
+      type: object
+      description: Probabilities normalized over the supplied candidates, summing to 1 subject to floating-point precision.
+      additionalProperties:
+        type: number
+        minimum: 0
+        maximum: 1
+    SystemOneConfidence:
+      type: number
+      minimum: 0
+      maximum: 1
+      description: Distribution concentration, calculated as 1 - H(p) / ln(N), where H(p) is entropy and N is the candidate count. Zero means uniform probabilities; values near 1 mean one candidate dominates. Not calibrated correctness.
+    SystemOneChoiceAnswer:
+      title: Choice
+      type: object
+      required: [type, choice, probabilities, confidence]
+      properties:
+        type:
+          type: string
+          enum: [choice]
+        choice:
+          type: string
+          description: Option key with the highest probability. Ties follow the model's option order.
+        probabilities:
+          $ref: "#/components/schemas/SystemOneProbabilities"
+        confidence:
+          $ref: "#/components/schemas/SystemOneConfidence"
+    SystemOneNoulAnswer:
+      title: Noul
+      type: object
+      required: [type, noul]
+      properties:
+        type:
+          type: string
+          enum: [noul]
+        noul:
+          type: number
+          minimum: 0
+          maximum: 1
+          description: Probability of true among the false and true candidates. This is a number, not a Boolean.
+    SystemOneScoreAnswer:
+      title: Score
+      type: object
+      required: [type, score, legend, probabilities, confidence]
+      properties:
+        type:
+          type: string
+          enum: [score]
+        score:
+          type: number
+          minimum: 0
+          maximum: 25
+          description: Probability-weighted average of the zero-based criterion indices, from 0 to the number of criteria minus 1. Not rounded to a level or normalized to 0–1.
+        legend:
+          type: object
+          description: Zero-based indices as string keys mapped to the criterion descriptions.
+          additionalProperties:
+            type: string
+        probabilities:
+          $ref: "#/components/schemas/SystemOneProbabilities"
+          description: Probabilities keyed by zero-based criterion indices as strings.
+        confidence:
+          $ref: "#/components/schemas/SystemOneConfidence"
+    SystemOneResponse:
+      type: object
+      required: [model, answers, usage]
+      properties:
+        model:
+          type: string
+          description: Model name from the request.
+        answers:
+          type: object
+          description: Answers keyed by the question names in the request.
+          additionalProperties:
+            oneOf:
+              - $ref: "#/components/schemas/SystemOneChoiceAnswer"
+              - $ref: "#/components/schemas/SystemOneNoulAnswer"
+              - $ref: "#/components/schemas/SystemOneScoreAnswer"
+        usage:
+          type: object
+          required: [input_tokens, output_tokens]
+          properties:
+            input_tokens:
+              type: integer
+              minimum: 0
+              description: Total evaluated input tokens, including image positions. Shared context is counted again when the model scores questions separately.
+            output_tokens:
+              type: integer
+              minimum: 0
+              description: Tokens generated internally for scoring, including prefix preparation and retries. May exceed the question count; not the length of the JSON response.
+    UsageMetrics:
+      type: object
+      required: [request_count]
+      properties:
+        request_count:
+          type: integer
+          minimum: 0
+          description: Number of recorded requests.
+        usage_usd:
+          type: number
+          description: Total value of the requests in USD, including usage covered by your plan and usage paid from purchased credits.
+        input_tokens:
+          type: integer
+          description: Recorded input tokens, including cached input tokens.
+        cached_input_tokens:
+          type: integer
+          description: Recorded input tokens read from cache, already included in input_tokens.
+        output_tokens:
+          type: integer
+          description: Recorded output tokens.
+    UsageBucket:
+      allOf:
+        - $ref: "#/components/schemas/UsageMetrics"
+        - type: object
+          required: [from, until]
+          properties:
+            from:
+              type: string
+              format: date-time
+              description: Start of the bucket in UTC, inclusive.
+            until:
+              type: string
+              format: date-time
+              description: End of the bucket in UTC, exclusive.
+            partial:
+              type: boolean
+              description: Present and true for the current hour or day, which is still in progress.
+    UsageResponse:
+      type: object
+      required: [range, scope, granularity, from, until, totals, buckets]
+      properties:
+        range:
+          type: string
+          enum: [24h, 7d, 30d]
+          description: Selected time range.
+        scope:
+          type: string
+          enum: [self, team]
+          description: Selected usage scope.
+        granularity:
+          type: string
+          enum: [hour, day]
+          description: "Set automatically: hour for 24h, day for 7d and 30d."
+        from:
+          type: string
+          format: date-time
+          description: Start of the range in UTC, inclusive.
+        until:
+          type: string
+          format: date-time
+          description: End of the range in UTC, exclusive.
+        totals:
+          $ref: "#/components/schemas/UsageMetrics"
+          description: Usage across the entire range.
+        buckets:
+          type: array
+          description: Usage in chronological order, including buckets with no recorded requests.
+          items:
+            $ref: "#/components/schemas/UsageBucket"
+    IncludedBalance:
+      title: Included credits
+      type: object
+      required: [balance_usd, allowance_usd, period]
+      properties:
+        balance_usd:
+          type: number
+          description: Remaining included credits in USD.
+        allowance_usd:
+          type: number
+          description: Included credits available for the full period in USD.
+        period:
+          type: object
+          required: [from, until]
+          properties:
+            from:
+              type: string
+              format: date-time
+              description: Start of the included period in UTC, inclusive.
+            until:
+              type: string
+              format: date-time
+              description: End of the included period in UTC, exclusive.
+    LegacyBalanceLimit:
+      type: object
+      required: [remaining_percent, resets_at]
+      properties:
+        remaining_percent:
+          type: number
+          minimum: 0
+          maximum: 100
+          description: Percentage of the limit remaining.
+        resets_at:
+          type: string
+          format: date-time
+          description: Next reset time in UTC.
+    LegacyIncludedBalance:
+      title: Legacy plan limits
+      type: object
+      required: [session, weekly]
+      properties:
+        session:
+          $ref: "#/components/schemas/LegacyBalanceLimit"
+        weekly:
+          $ref: "#/components/schemas/LegacyBalanceLimit"
+    BalanceResponse:
+      type: object
+      required: [included, purchased]
+      properties:
+        included:
+          oneOf:
+            - $ref: "#/components/schemas/IncludedBalance"
+            - $ref: "#/components/schemas/LegacyIncludedBalance"
+        purchased:
+          type: object
+          required: [balance_usd]
+          properties:
+            balance_usd:
+              type: number
+              description: Remaining unexpired purchased credits in USD.
    ErrorResponse:
      type: object
      properties:
@@ -797,12 +1153,117 @@ components:
          type: string
          description: Error message describing what went wrong
 paths:
+  /v1/systemone:
+    post:
+      summary: Answer typed questions
+      description: |
+        Answer choice, yes/no, and scoring questions with a local System One model. Requires Ollama v0.35.0 or later. See the [decision guide](/capabilities/decision) for examples.
+      operationId: systemone
+      x-mint:
+        href: /api/systemone
+        metadata:
+          title: System One
+          sidebarTitle: /v1/systemone
+        content: |
+          <Note>
+          Currently available locally in Ollama.
+          </Note>
+
+          - Returns one JSON response; streaming, video, tools, and generation controls are not supported.
+          - Requests without images must fit within 64 KiB; requests with images must fit within 32 MiB, including base64 and JSON. The complete input must fit the loaded context window. Nimble and Tev also require two token positions for scoring. Input is never truncated.
+      x-codeSamples:
+        - lang: bash
+          label: Choose a label
+          source: |
+            curl http://localhost:11434/v1/systemone \
+              -H 'Content-Type: application/json' \
+              -d '{
+                "model": "nimble",
+                "state": "Our checkout has returned 500 errors since 9am.",
+                "questions": {
+                  "label": {
+                    "type": "choice",
+                    "instructions": "Which label fits this ticket?",
+                    "criteria": {
+                      "billing": "Payments and refunds",
+                      "bug": "Software errors",
+                      "account": "Login and account access"
+                    }
+                  }
+                }
+              }'
+      requestBody:
+        required: true
+        content:
+          application/json:
+            schema:
+              $ref: "#/components/schemas/SystemOneRequest"
+            example:
+              model: nimble
+              state: Our checkout has returned 500 errors since 9am.
+              questions:
+                label:
+                  type: choice
+                  instructions: Which label fits this ticket?
+                  criteria:
+                    billing: Payments and refunds
+                    bug: Software errors
+                    account: Login and account access
+      responses:
+        "200":
+          description: Answers and token usage for all questions. Example probabilities and confidence are rounded to four decimal places; results and usage can vary with the model and server configuration.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/SystemOneResponse"
+              example:
+                model: nimble
+                answers:
+                  label:
+                    type: choice
+                    choice: bug
+                    probabilities:
+                      billing: 0.0125
+                      bug: 0.9781
+                      account: 0.0093
+                    confidence: 0.8906
+                usage:
+                  input_tokens: 174
+                  output_tokens: 1
+        "400":
+          description: Invalid request, unsupported model or runner, or a rendered prompt that exceeds the loaded context. Cloud models are rejected.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ErrorResponse"
+        "404":
+          description: Local model not found. Download the model before making a request.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ErrorResponse"
+        "413":
+          description: Request body exceeds 64 KiB without images or 32 MiB with images.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ErrorResponse"
+              example:
+                error: request body must not exceed 64 KiB without images
+        "500":
+          description: Model loading, rendering, or scoring failed.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ErrorResponse"
  /api/generate:
    post:
      summary: Generate a response
      description: Generates a response for the provided prompt
      operationId: generate
      x-mint:
+        metadata:
+          sidebarTitle: /api/generate
        href: /api/generate
      x-codeSamples:
        - lang: bash
@@ -820,6 +1281,15 @@ paths:
              "prompt": "Why is the sky blue?",
              "stream": false
            }'
+        - lang: bash
+          label: Thinking
+          source: |
+            curl http://localhost:11434/api/generate -d '{
+              "model": "gpt-oss",
+              "prompt": "What is 1+1?",
+              "think": "low",
+              "stream": false
+            }'
        - lang: bash
          label: With options
          source: |
@@ -915,6 +1385,8 @@ paths:
      description: Generate the next chat message in a conversation between a user and an assistant.
      operationId: chat
      x-mint:
+        metadata:
+          sidebarTitle: /api/chat
        href: /api/chat
      x-codeSamples:
        - lang: bash
@@ -1073,6 +1545,8 @@ paths:
      description: Creates vector embeddings representing the input text
      operationId: embed
      x-mint:
+        metadata:
+          sidebarTitle: /api/embed
        href: /api/embed
      x-codeSamples:
        - lang: bash
@@ -1148,6 +1622,8 @@ paths:
      description: Fetch a list of models and their details
      operationId: list
      x-mint:
+        metadata:
+          sidebarTitle: /api/tags
        href: /api/tags
      x-codeSamples:
        - lang: bash
@@ -1181,6 +1657,8 @@ paths:
      description: Retrieve a list of models that are currently running
      operationId: ps
      x-mint:
+        metadata:
+          sidebarTitle: /api/ps
        href: /api/ps
      x-codeSamples:
        - lang: bash
@@ -1215,6 +1693,9 @@ paths:
    post:
      summary: Show model details
      operationId: show
+      x-mint:
+        metadata:
+          sidebarTitle: /api/show
      x-codeSamples:
        - lang: bash
          label: Default
@@ -1229,6 +1710,18 @@ paths:
              "model": "gemma4",
              "verbose": true
            }'
+        - lang: bash
+          label: Thinking controls
+          source: |
+            curl http://localhost:11434/api/show -d '{
+              "model": "gpt-oss"
+            }'
+        - lang: bash
+          label: Thinking controls
+          source: |
+            curl http://localhost:11434/api/show -d '{
+              "model": "gpt-oss"
+            }'
      requestBody:
        required: true
        content:
@@ -1249,7 +1742,13 @@ paths:
                license: "Gemma Terms of Use \n\nLast modified: February 21, 2024..."
                capabilities:
                  - "completion"
+                  - "thinking"
                  - "vision"
+                thinking:
+                  values:
+                    - false
+                    - true
+                  default: true
                modified_at: "2025-08-14T15:49:43.634137516-07:00"
                details:
                  parent_model: ""
@@ -1321,6 +1820,8 @@ paths:
      summary: Create a model
      operationId: create
      x-mint:
+        metadata:
+          sidebarTitle: /api/create
        href: /api/create
      x-codeSamples:
        - lang: bash
@@ -1340,12 +1841,13 @@ paths:
              "system": "You are Ollama the llama."
            }'
        - lang: bash
-          label: Quantize
+          label: Create from GGUF
          source: |
            curl http://localhost:11434/api/create -d '{
-              "model": "llama3.1:8b-instruct-Q4_K_M",
-              "from": "llama3.1:8b-instruct-fp16",
-              "quantize": "q4_K_M"
+              "model": "my-gguf-model",
+              "files": {
+                "model.gguf": "sha256:432f310a77f4650a88d0fd59ecdd7cebed8d684bafea53cbff0473542964f0c3"
+              }
            }'
      requestBody:
        required: true
@@ -1371,11 +1873,69 @@ paths:
                $ref: "#/components/schemas/StatusEvent"
              example:
                status: "success"
+  /api/blobs/{digest}:
+    head:
+      summary: Check if a blob exists
+      operationId: headBlob
+      parameters:
+        - $ref: "#/components/parameters/DigestParam"
+      responses:
+        "200":
+          description: Blob exists
+        "400":
+          description: Invalid digest
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ErrorResponse"
+        "404":
+          description: Blob not found
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ErrorResponse"
+        "500":
+          description: Failed to inspect blob
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ErrorResponse"
+    post:
+      summary: Push a blob
+      operationId: createBlob
+      parameters:
+        - $ref: "#/components/parameters/DigestParam"
+      requestBody:
+        required: true
+        content:
+          application/octet-stream:
+            schema:
+              type: string
+              format: binary
+      responses:
+        "200":
+          description: Blob already exists
+        "201":
+          description: Blob created
+        "400":
+          description: Invalid digest or blob content
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ErrorResponse"
+        "500":
+          description: Failed to write blob
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ErrorResponse"
  /api/copy:
    post:
      summary: Copy a model
      operationId: copy
      x-mint:
+        metadata:
+          sidebarTitle: /api/copy
        href: /api/copy
      x-codeSamples:
        - lang: bash
@@ -1397,11 +1957,31 @@ paths:
      responses:
        "200":
          description: Model successfully copied
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/StatusResponse"
+              example:
+                status: "success"
+        "400":
+          description: Model could not be copied
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ErrorResponse"
+        "404":
+          description: Source model not found
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ErrorResponse"
  /api/pull:
    post:
      summary: Pull a model
      operationId: pull
      x-mint:
+        metadata:
+          sidebarTitle: /api/pull
        href: /api/pull
      x-codeSamples:
        - lang: bash
@@ -1444,6 +2024,8 @@ paths:
      summary: Push a model
      operationId: push
      x-mint:
+        metadata:
+          sidebarTitle: /api/push
        href: /api/push
      x-codeSamples:
        - lang: bash
@@ -1486,6 +2068,8 @@ paths:
      summary: Delete a model
      operationId: delete
      x-mint:
+        metadata:
+          sidebarTitle: /api/delete
        href: /api/delete
      x-codeSamples:
        - lang: bash
@@ -1510,6 +2094,9 @@ paths:
      summary: Get version
      description: Retrieve the version of the Ollama
      operationId: version
+      x-mint:
+        metadata:
+          sidebarTitle: /api/version
      x-codeSamples:
        - lang: bash
          label: Default
@@ -1524,3 +2111,124 @@ paths:
                $ref: "#/components/schemas/VersionResponse"
              example:
                version: "0.12.6"
+  /api/usage:
+    get:
+      summary: Cloud usage
+      description: Usage statistics for cloud inference, web search, and web fetch.
+      operationId: usage
+      servers:
+        - url: https://ollama.com
+          description: Ollama Cloud
+      security:
+        - bearerAuth: []
+      parameters:
+        - name: range
+          in: query
+          description: Completed UTC hours or days to include, plus the current partial hour or day.
+          schema:
+            type: string
+            enum: [24h, 7d, 30d]
+            default: 7d
+        - name: scope
+          in: query
+          description: Your requests, or your team's requests. Team scope requires being a team admin.
+          schema:
+            type: string
+            enum: [self, team]
+            default: self
+      responses:
+        "200":
+          description: Usage for the selected range and scope.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/UsageResponse"
+        "400":
+          description: Invalid query parameters.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ErrorResponse"
+        "401":
+          description: Invalid credentials.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ErrorResponse"
+        "403":
+          description: Account suspended or team scope requested without team admin access.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ErrorResponse"
+        "429":
+          description: Too many requests.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ErrorResponse"
+          headers:
+            Retry-After:
+              description: Seconds to wait before retrying.
+              schema:
+                type: integer
+                minimum: 1
+        "503":
+          description: Usage reporting is temporarily unavailable.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ErrorResponse"
+  /api/balance:
+    get:
+      summary: Balance
+      description: Check your remaining usage credits.
+      operationId: balance
+      servers:
+        - url: https://ollama.com
+          description: Ollama Cloud
+      security:
+        - bearerAuth: []
+      responses:
+        "200":
+          description: Current included and purchased balances.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/BalanceResponse"
+        "400":
+          description: Invalid query parameters.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ErrorResponse"
+        "401":
+          description: Invalid credentials.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ErrorResponse"
+        "403":
+          description: Account suspended.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ErrorResponse"
+        "429":
+          description: Too many requests.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ErrorResponse"
+          headers:
+            Retry-After:
+              description: Seconds to wait before retrying.
+              schema:
+                type: integer
+                minimum: 1
+        "503":
+          description: Balance reporting is temporarily unavailable.
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ErrorResponse"