Reference 2026-09-01 01:57 UTC to 2026-09-02 01:58 UTC

84 84 

85 Details about why the response is incomplete.85 Details about why the response is incomplete.

86 86 

87 - `reason: optional "max_output_tokens" or "content_filter"`87 - `reason: optional "max_output_tokens" or "max_messages" or "content_filter"`

88 88 

89 The reason why the response is incomplete.89 The reason why the response is incomplete.

90 90 

91 - `"max_output_tokens"`91 - `"max_output_tokens"`

92 92 

93 - `"max_messages"`

94 

93 - `"content_filter"`95 - `"content_filter"`

94 96 

95 - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more or null`97 - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more or null`

10902 10904 

10903 The total number of tokens used.10905 The total number of tokens used.

10904 10906 

10905 - `compute_units: optional number or null`

10906 

10907 Compute units for the request. Currently null when available.

10908 

10909 - `user: optional string`10907 - `user: optional string`

10910 10908 

10911 This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations.10909 This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations.

11089 "output_tokens_details": {11087 "output_tokens_details": {

11090 "reasoning_tokens": 011088 "reasoning_tokens": 0

11091 },11089 },

11092 "total_tokens": 0,11090 "total_tokens": 0

11093 "compute_units": 0

11094 },11091 },

11095 "user": "user-1234"11092 "user": "user-1234"

11096}11093}

9968 9968 

9969 The total number of tokens used.9969 The total number of tokens used.

9970 9970 

9971 - `compute_units: optional number or null`

9972 

9973 Compute units for the request. Currently null when available.

9974 

9975### Example9971### Example

9976 9972 

9977```http9973```http

10022 "output_tokens_details": {10018 "output_tokens_details": {

10023 "reasoning_tokens": 010019 "reasoning_tokens": 0

10024 },10020 },

10025 "total_tokens": 0,10021 "total_tokens": 0

10026 "compute_units": 0

10027 }10022 }

10028}10023}

10029```10024```

6868 6868 

6869 Details about why the response is incomplete.6869 Details about why the response is incomplete.

6870 6870 

6871 - `reason: optional "max_output_tokens" or "content_filter"`6871 - `reason: optional "max_output_tokens" or "max_messages" or "content_filter"`

6872 6872 

6873 The reason why the response is incomplete.6873 The reason why the response is incomplete.

6874 6874 

6875 - `"max_output_tokens"`6875 - `"max_output_tokens"`

6876 6876 

6877 - `"max_messages"`

6878 

6877 - `"content_filter"`6879 - `"content_filter"`

6878 6880 

6879 - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more or null`6881 - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more or null`

17686 17688 

17687 The total number of tokens used.17689 The total number of tokens used.

17688 17690 

17689 - `compute_units: optional number or null`

17690 

17691 Compute units for the request. Currently null when available.

17692 

17693 - `user: optional string`17691 - `user: optional string`

17694 17692 

17695 This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations.17693 This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations.

17881 "output_tokens_details": {17879 "output_tokens_details": {

17882 "reasoning_tokens": 017880 "reasoning_tokens": 0

17883 },17881 },

17884 "total_tokens": 0,17882 "total_tokens": 0

17885 "compute_units": 0

17886 },17883 },

17887 "user": "user-1234"17884 "user": "user-1234"

17888}17885}

128 128 

129 Details about why the response is incomplete.129 Details about why the response is incomplete.

130 130 

131 - `reason: optional "max_output_tokens" or "content_filter"`131 - `reason: optional "max_output_tokens" or "max_messages" or "content_filter"`

132 132 

133 The reason why the response is incomplete.133 The reason why the response is incomplete.

134 134 

135 - `"max_output_tokens"`135 - `"max_output_tokens"`

136 136 

137 - `"max_messages"`

138 

137 - `"content_filter"`139 - `"content_filter"`

138 140 

139 - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more or null`141 - `instructions: string or array of BetaEasyInputMessage or object { content, role, agent, 2 more } or BetaResponseOutputMessage or 32 more or null`

10946 10948 

10947 The total number of tokens used.10949 The total number of tokens used.

10948 10950 

10949 - `compute_units: optional number or null`

10950 

10951 Compute units for the request. Currently null when available.

10952 

10953 - `user: optional string`10951 - `user: optional string`

10954 10952 

10955 This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations.10953 This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations.

11132 "output_tokens_details": {11130 "output_tokens_details": {

11133 "reasoning_tokens": 011131 "reasoning_tokens": 0

11134 },11132 },

11135 "total_tokens": 0,11133 "total_tokens": 0

11136 "compute_units": 0

11137 },11134 },

11138 "user": "user-1234"11135 "user": "user-1234"

11139}11136}

1868 1868 

1869 Text output tokens generated by the model.1869 Text output tokens generated by the model.

1870 1870 

1871 - `compute_units: optional number or null`

1872 

1873 Compute units for the request. Currently null when available.

1874 

1875 - `prompt_tokens_details: optional object { audio_tokens, cache_write_tokens, cached_tokens, 2 more }`1871 - `prompt_tokens_details: optional object { audio_tokens, cache_write_tokens, cached_tokens, 2 more }`

1876 1872 

1877 Breakdown of tokens used in the prompt.1873 Breakdown of tokens used in the prompt.

2069 "rejected_prediction_tokens": 0,2065 "rejected_prediction_tokens": 0,

2070 "text_tokens": 02066 "text_tokens": 0

2071 },2067 },

2072 "compute_units": 0,

2073 "prompt_tokens_details": {2068 "prompt_tokens_details": {

2074 "audio_tokens": 0,2069 "audio_tokens": 0,

2075 "cache_write_tokens": 0,2070 "cache_write_tokens": 0,

509 509 

510 Text output tokens generated by the model.510 Text output tokens generated by the model.

511 511 

512 - `compute_units: optional number or null`

513 

514 Compute units for the request. Currently null when available.

515 

516 - `prompt_tokens_details: optional object { audio_tokens, cache_write_tokens, cached_tokens, 2 more }`512 - `prompt_tokens_details: optional object { audio_tokens, cache_write_tokens, cached_tokens, 2 more }`

517 513 

518 Breakdown of tokens used in the prompt.514 Breakdown of tokens used in the prompt.

714 "rejected_prediction_tokens": 0,710 "rejected_prediction_tokens": 0,

715 "text_tokens": 0711 "text_tokens": 0

716 },712 },

717 "compute_units": 0,

718 "prompt_tokens_details": {713 "prompt_tokens_details": {

719 "audio_tokens": 0,714 "audio_tokens": 0,

720 "cache_write_tokens": 0,715 "cache_write_tokens": 0,

485 485 

486 Text output tokens generated by the model.486 Text output tokens generated by the model.

487 487 

488 - `compute_units: optional number or null`

489 

490 Compute units for the request. Currently null when available.

491 

492 - `prompt_tokens_details: optional object { audio_tokens, cache_write_tokens, cached_tokens, 2 more }`488 - `prompt_tokens_details: optional object { audio_tokens, cache_write_tokens, cached_tokens, 2 more }`

493 489 

494 Breakdown of tokens used in the prompt.490 Breakdown of tokens used in the prompt.

670 "rejected_prediction_tokens": 0,666 "rejected_prediction_tokens": 0,

671 "text_tokens": 0667 "text_tokens": 0

672 },668 },

673 "compute_units": 0,

674 "prompt_tokens_details": {669 "prompt_tokens_details": {

675 "audio_tokens": 0,670 "audio_tokens": 0,

676 "cache_write_tokens": 0,671 "cache_write_tokens": 0,

497 497 

498 Text output tokens generated by the model.498 Text output tokens generated by the model.

499 499 

500 - `compute_units: optional number or null`

501 

502 Compute units for the request. Currently null when available.

503 

504 - `prompt_tokens_details: optional object { audio_tokens, cache_write_tokens, cached_tokens, 2 more }`500 - `prompt_tokens_details: optional object { audio_tokens, cache_write_tokens, cached_tokens, 2 more }`

505 501 

506 Breakdown of tokens used in the prompt.502 Breakdown of tokens used in the prompt.

688 "rejected_prediction_tokens": 0,684 "rejected_prediction_tokens": 0,

689 "text_tokens": 0685 "text_tokens": 0

690 },686 },

691 "compute_units": 0,

692 "prompt_tokens_details": {687 "prompt_tokens_details": {

693 "audio_tokens": 0,688 "audio_tokens": 0,

694 "cache_write_tokens": 0,689 "cache_write_tokens": 0,

305 "(resource) completions > (model) completion_usage > (schema) > (property) prompt_tokens",305 "(resource) completions > (model) completion_usage > (schema) > (property) prompt_tokens",

306 "(resource) completions > (model) completion_usage > (schema) > (property) total_tokens",306 "(resource) completions > (model) completion_usage > (schema) > (property) total_tokens",

307 "(resource) completions > (model) completion_usage > (schema) > (property) completion_tokens_details",307 "(resource) completions > (model) completion_usage > (schema) > (property) completion_tokens_details",

308 "(resource) completions > (model) completion_usage > (schema) > (property) compute_units",

309 "(resource) completions > (model) completion_usage > (schema) > (property) prompt_tokens_details"308 "(resource) completions > (model) completion_usage > (schema) > (property) prompt_tokens_details"

310 ]309 ]

311 },310 },

661 "(resource) completions > (model) completion_usage > (schema) > (property) completion_tokens_details > (property) text_tokens"660 "(resource) completions > (model) completion_usage > (schema) > (property) completion_tokens_details > (property) text_tokens"

662 ]661 ]

663 },662 },

664 "(resource) completions > (model) completion_usage > (schema) > (property) compute_units": {

665 "kind": "HttpDeclProperty",

666 "oasRef": "#/components/schemas/CompletionUsage/properties/compute_units",

667 "deprecated": false,

668 "key": "compute_units",

669 "docstring": "Compute units for the request. Currently null when available.\n",

670 "type": {

671 "kind": "HttpTypeNumber"

672 },

673 "constraints": {

674 "minimum": 0

675 },

676 "optional": true,

677 "nullable": true,

678 "schemaType": "integer",

679 "children": []

680 },

681 "(resource) completions > (model) completion_usage > (schema) > (property) prompt_tokens_details": {663 "(resource) completions > (model) completion_usage > (schema) > (property) prompt_tokens_details": {

682 "kind": "HttpDeclProperty",664 "kind": "HttpDeclProperty",

683 "oasRef": "#/components/schemas/CompletionUsage/properties/prompt_tokens_details",665 "oasRef": "#/components/schemas/CompletionUsage/properties/prompt_tokens_details",

736 {718 {

737 "ident": "completion_tokens_details"719 "ident": "completion_tokens_details"

738 },720 },

739 {

740 "ident": "compute_units"

741 },

742 {721 {

743 "ident": "prompt_tokens_details"722 "ident": "prompt_tokens_details"

744 }723 }

750 "(resource) completions > (model) completion_usage > (schema) > (property) prompt_tokens",729 "(resource) completions > (model) completion_usage > (schema) > (property) prompt_tokens",

751 "(resource) completions > (model) completion_usage > (schema) > (property) total_tokens",730 "(resource) completions > (model) completion_usage > (schema) > (property) total_tokens",

752 "(resource) completions > (model) completion_usage > (schema) > (property) completion_tokens_details",731 "(resource) completions > (model) completion_usage > (schema) > (property) completion_tokens_details",

753 "(resource) completions > (model) completion_usage > (schema) > (property) compute_units",

754 "(resource) completions > (model) completion_usage > (schema) > (property) prompt_tokens_details"732 "(resource) completions > (model) completion_usage > (schema) > (property) prompt_tokens_details"

755 ]733 ]

756 },734 },

261 261 

262 Text output tokens generated by the model.262 Text output tokens generated by the model.

263 263 

264 - `compute_units: optional number or null`

265 

266 Compute units for the request. Currently null when available.

267 

268 - `prompt_tokens_details: optional object { audio_tokens, cache_write_tokens, cached_tokens, 2 more }`264 - `prompt_tokens_details: optional object { audio_tokens, cache_write_tokens, cached_tokens, 2 more }`

269 265 

270 Breakdown of tokens used in the prompt.266 Breakdown of tokens used in the prompt.

350 "rejected_prediction_tokens": 0,346 "rejected_prediction_tokens": 0,

351 "text_tokens": 0347 "text_tokens": 0

352 },348 },

353 "compute_units": 0,

354 "prompt_tokens_details": {349 "prompt_tokens_details": {

355 "audio_tokens": 0,350 "audio_tokens": 0,

356 "cache_write_tokens": 0,351 "cache_write_tokens": 0,

78 78 

79 Details about why the response is incomplete.79 Details about why the response is incomplete.

80 80 

81 - `reason: optional "max_output_tokens" or "content_filter"`81 - `reason: optional "max_output_tokens" or "max_messages" or "content_filter"`

82 82 

83 The reason why the response is incomplete.83 The reason why the response is incomplete.

84 84 

85 - `"max_output_tokens"`85 - `"max_output_tokens"`

86 86 

87 - `"max_messages"`

88 

87 - `"content_filter"`89 - `"content_filter"`

88 90 

89 - `instructions: string or array of EasyInputMessage or object { content, role, status, type } or ResponseOutputMessage or 29 more or null`91 - `instructions: string or array of EasyInputMessage or object { content, role, status, type } or ResponseOutputMessage or 29 more or null`

9158 9160 

9159 The total number of tokens used.9161 The total number of tokens used.

9160 9162 

9161 - `compute_units: optional number or null`

9162 

9163 Compute units for the request. Currently null when available.

9164 

9165 - `user: optional string`9163 - `user: optional string`

9166 9164 

9167 This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations.9165 This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations.

9342 "output_tokens_details": {9340 "output_tokens_details": {

9343 "reasoning_tokens": 09341 "reasoning_tokens": 0

9344 },9342 },

9345 "total_tokens": 0,9343 "total_tokens": 0

9346 "compute_units": 0

9347 },9344 },

9348 "user": "user-1234"9345 "user": "user-1234"

9349}9346}

8484 8484 

8485 The total number of tokens used.8485 The total number of tokens used.

8486 8486 

8487 - `compute_units: optional number or null`

8488 

8489 Compute units for the request. Currently null when available.

8490 

8491### Example8487### Example

8492 8488 

8493```http8489```http

8535 "output_tokens_details": {8531 "output_tokens_details": {

8536 "reasoning_tokens": 08532 "reasoning_tokens": 0

8537 },8533 },

8538 "total_tokens": 0,8534 "total_tokens": 0

8539 "compute_units": 0

8540 }8535 }

8541}8536}

8542```8537```

5927 5927 

5928 Details about why the response is incomplete.5928 Details about why the response is incomplete.

5929 5929 

5930 - `reason: optional "max_output_tokens" or "content_filter"`5930 - `reason: optional "max_output_tokens" or "max_messages" or "content_filter"`

5931 5931 

5932 The reason why the response is incomplete.5932 The reason why the response is incomplete.

5933 5933 

5934 - `"max_output_tokens"`5934 - `"max_output_tokens"`

5935 5935 

5936 - `"max_messages"`

5937 

5936 - `"content_filter"`5938 - `"content_filter"`

5937 5939 

5938 - `instructions: string or array of EasyInputMessage or object { content, role, status, type } or ResponseOutputMessage or 29 more or null`5940 - `instructions: string or array of EasyInputMessage or object { content, role, status, type } or ResponseOutputMessage or 29 more or null`

15007 15009 

15008 The total number of tokens used.15010 The total number of tokens used.

15009 15011 

15010 - `compute_units: optional number or null`

15011 

15012 Compute units for the request. Currently null when available.

15013 

15014 - `user: optional string`15012 - `user: optional string`

15015 15013 

15016 This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations.15014 This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations.

15199 "output_tokens_details": {15197 "output_tokens_details": {

15200 "reasoning_tokens": 015198 "reasoning_tokens": 0

15201 },15199 },

15202 "total_tokens": 0,15200 "total_tokens": 0

15203 "compute_units": 0

15204 },15201 },

15205 "user": "user-1234"15202 "user": "user-1234"

15206}15203}

122 122 

123 Details about why the response is incomplete.123 Details about why the response is incomplete.

124 124 

125 - `reason: optional "max_output_tokens" or "content_filter"`125 - `reason: optional "max_output_tokens" or "max_messages" or "content_filter"`

126 126 

127 The reason why the response is incomplete.127 The reason why the response is incomplete.

128 128 

129 - `"max_output_tokens"`129 - `"max_output_tokens"`

130 130 

131 - `"max_messages"`

132 

131 - `"content_filter"`133 - `"content_filter"`

132 134 

133 - `instructions: string or array of EasyInputMessage or object { content, role, status, type } or ResponseOutputMessage or 29 more or null`135 - `instructions: string or array of EasyInputMessage or object { content, role, status, type } or ResponseOutputMessage or 29 more or null`

9202 9204 

9203 The total number of tokens used.9205 The total number of tokens used.

9204 9206 

9205 - `compute_units: optional number or null`

9206 

9207 Compute units for the request. Currently null when available.

9208 

9209 - `user: optional string`9207 - `user: optional string`

9210 9208 

9211 This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations.9209 This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations.

9385 "output_tokens_details": {9383 "output_tokens_details": {

9386 "reasoning_tokens": 09384 "reasoning_tokens": 0

9387 },9385 },

9388 "total_tokens": 0,9386 "total_tokens": 0

9389 "compute_units": 0

9390 },9387 },

9391 "user": "user-1234"9388 "user": "user-1234"

9392}9389}