DeepSeek V4 Pro 0813 works with text conversations under the exact model ID deepseek/deepseek-v4-pro-0813. Ailoot Ultra also maps ~deepseek/deepseek-pro-latest to this model. Use the explicit ID when the named edition matters to your application or revision record. The published model profile describes text input and text output and lists a context length of 1,048,576 tokens.
Use a request to define a checkable deliverable. For a document comparison, provide the relevant versions and ask for changes grouped by topic, with supporting excerpts. For a technical explanation, include the actual code, configuration or error text and name the question to answer. For a draft, supply the facts that may be used, the intended audience and the desired structure. These are ways to organize the task; evaluate the answer against the supplied source material.
Send POST /v1/chat/completions with model and a nonempty messages array. Each message provides a role and literal text content. Include the previous turns needed to understand the current question. For file-based work, read the actual UTF-8 text and insert the relevant contents into a message. Use clear boundaries between documents, notes and instructions so the answer can refer to the correct material.
The context figure describes the conversation capacity listed in the model profile. It is separate from the size of a completed answer. For long material, provide a short task statement and a map of the sections the model should use, then ask for the specific output you need. A context limit alone is not a reason to request a response as long as the entire input.
The minimal Chat Completions profile exposes stream as an optional boolean, defaulting to false. Use JSON delivery when the next step needs the complete result, or stream:true for SSE delivery to an interface. Retain all returned choices, response fields and usage rather than extracting only the first visible text fragment. When streaming, assemble the returned events before treating the answer as complete. Preserve the original request identity and received response if delivery stops unexpectedly; this text interface does not supply an asynchronous media job to recreate or poll.
", "aboutText": "DeepSeek V4 Pro 0813 works with text conversations under the exact model ID deepseek/deepseek-v4-pro-0813. Ailoot Ultra also maps ~deepseek/deepseek-pro-latest to this model. Use the explicit ID when the named edition matters to your application or revision record. The published model profile describes text input and text output and lists a context length of 1,048,576 tokens.\n\nUse a request to define a checkable deliverable. For a document comparison, provide the relevant versions and ask for changes grouped by topic, with supporting excerpts. For a technical explanation, include the actual code, configuration or error text and name the question to answer. For a draft, supply the facts that may be used, the intended audience and the desired structure. These are ways to organize the task; evaluate the answer against the supplied source material.\n\nSend POST /v1/chat/completions with model and a nonempty messages array. Each message provides a role and literal text content. Include the previous turns needed to understand the current question. For file-based work, read the actual UTF-8 text and insert the relevant contents into a message. Use clear boundaries between documents, notes and instructions so the answer can refer to the correct material.\n\nThe context figure describes the conversation capacity listed in the model profile. It is separate from the size of a completed answer. For long material, provide a short task statement and a map of the sections the model should use, then ask for the specific output you need. A context limit alone is not a reason to request a response as long as the entire input.\n\nThe minimal Chat Completions profile exposes stream as an optional boolean, defaulting to false. Use JSON delivery when the next step needs the complete result, or stream:true for SSE delivery to an interface. Retain all returned choices, response fields and usage rather than extracting only the first visible text fragment. When streaming, assemble the returned events before treating the answer as complete. Preserve the original request identity and received response if delivery stops unexpectedly; this text interface does not supply an asynchronous media job to recreate or poll.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "568a4d8cbc5dcec67079894753ec644826a0197d2bfb16859ac96d6edf269bf1", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "deepseek/deepseek-v4-pro-0813DeepSeek V4 Pro 0813 is a text-input, text-output model available through Chat Completions in Ailoot Ultra. Its published context length is 1,048,576 tokens. Use deepseek/deepseek-v4-pro-0813 for the explicit model identity; the alias ~deepseek/deepseek-pro-latest currently binds to the same model. Supply the material and request a concrete analysis, explanation, summary or draft.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
DeepSeek V4 Pro 0813 works with text conversations under the exact model ID deepseek/deepseek-v4-pro-0813. Ailoot Ultra also maps ~deepseek/deepseek-pro-latest to this model. Use the explicit ID when the named edition matters to your application or revision record. The published model profile describes text input and text output and lists a context length of 1,048,576 tokens.
Use a request to define a checkable deliverable. For a document comparison, provide the relevant versions and ask for changes grouped by topic, with supporting excerpts. For a technical explanation, include the actual code, configuration or error text and name the question to answer. For a draft, supply the facts that may be used, the intended audience and the desired structure. These are ways to organize the task; evaluate the answer against the supplied source material.
Send POST /v1/chat/completions with model and a nonempty messages array. Each message provides a role and literal text content. Include the previous turns needed to understand the current question. For file-based work, read the actual UTF-8 text and insert the relevant contents into a message. Use clear boundaries between documents, notes and instructions so the answer can refer to the correct material.
The context figure describes the conversation capacity listed in the model profile. It is separate from the size of a completed answer. For long material, provide a short task statement and a map of the sections the model should use, then ask for the specific output you need. A context limit alone is not a reason to request a response as long as the entire input.
The minimal Chat Completions profile exposes stream as an optional boolean, defaulting to false. Use JSON delivery when the next step needs the complete result, or stream:true for SSE delivery to an interface. Retain all returned choices, response fields and usage rather than extracting only the first visible text fragment. When streaming, assemble the returned events before treating the answer as complete. Preserve the original request identity and received response if delivery stops unexpectedly; this text interface does not supply an asynchronous media job to recreate or poll.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits deepseek/deepseek-v4-pro-0813 | Default— |
Fieldmessages | Typearray | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldmax_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 | Default— |
Fieldmax_completion_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 | Default— |
Fieldn | Typeinteger | RequirementOptional | Values & limits Minimum: 1 | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits | Default— |
Fieldseed | Typeinteger | RequirementOptional | Values & limits | Default— |
Fieldstop | Type | RequirementOptional | Values & limits | Default— |
Fieldfrequency_penalty | Typenumber | RequirementOptional | Values & limits | Default— |
Fieldpresence_penalty | Typenumber | RequirementOptional | Values & limits | Default— |
Fielduser | Typestring | RequirementOptional | Values & limits | Default— |
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parameteroptional | Contractstream, max_tokens, max_completion_tokens, n, temperature, top_p, seed, stop, frequency_penalty, presence_penalty, user |
Parametermaterial_types | Contracttext |
Parameterconditions | Contract |
Lifecycle: synchronous_json_or_sse
Tariff references do not add request options. Supported parameters are listed for the selected method.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.00132 / 1K tokens Output · Output tokens $0.00396 / 1K tokens Input · Cache read $0.000044 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "deepseek/deepseek-v4-pro-0813", "messages": [{"role": "user", "content": "Summarize the supplied text in three concise points."}], "stream": false}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\n# Submit once. Retain the complete result, original identifiers and every response header.\nJSON or supported SSE
Keep every complete returned response, file and content part.
Retain the complete response, all actual results, original identifiers, usage and response headers.
Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.
Ailoot Ultra deepseek/deepseek-v4-pro-0813, ~deepseek/deepseek-pro-latest
Use the method paths shown above.
deepseek/deepseek-v4-pro-0813, ~deepseek/deepseek-pro-latest
~deepseek/deepseek-pro-latestDeepSeek V4 Pro 0813 is a text-input, text-output model available through Chat Completions in Ailoot Ultra. Its published context length is 1,048,576 tokens. Use deepseek/deepseek-v4-pro-0813 for the explicit model identity; the alias ~deepseek/deepseek-pro-latest currently binds to the same model. Supply the material and request a concrete analysis, explanation, summary or draft.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
DeepSeek V4 Pro 0813 works with text conversations under the exact model ID deepseek/deepseek-v4-pro-0813. Ailoot Ultra also maps ~deepseek/deepseek-pro-latest to this model. Use the explicit ID when the named edition matters to your application or revision record. The published model profile describes text input and text output and lists a context length of 1,048,576 tokens.
Use a request to define a checkable deliverable. For a document comparison, provide the relevant versions and ask for changes grouped by topic, with supporting excerpts. For a technical explanation, include the actual code, configuration or error text and name the question to answer. For a draft, supply the facts that may be used, the intended audience and the desired structure. These are ways to organize the task; evaluate the answer against the supplied source material.
Send POST /v1/chat/completions with model and a nonempty messages array. Each message provides a role and literal text content. Include the previous turns needed to understand the current question. For file-based work, read the actual UTF-8 text and insert the relevant contents into a message. Use clear boundaries between documents, notes and instructions so the answer can refer to the correct material.
The context figure describes the conversation capacity listed in the model profile. It is separate from the size of a completed answer. For long material, provide a short task statement and a map of the sections the model should use, then ask for the specific output you need. A context limit alone is not a reason to request a response as long as the entire input.
The minimal Chat Completions profile exposes stream as an optional boolean, defaulting to false. Use JSON delivery when the next step needs the complete result, or stream:true for SSE delivery to an interface. Retain all returned choices, response fields and usage rather than extracting only the first visible text fragment. When streaming, assemble the returned events before treating the answer as complete. Preserve the original request identity and received response if delivery stops unexpectedly; this text interface does not supply an asynchronous media job to recreate or poll.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits ~deepseek/deepseek-pro-latest | Default— |
Fieldmessages | Typearray | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldmax_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 | Default— |
Fieldmax_completion_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 | Default— |
Fieldn | Typeinteger | RequirementOptional | Values & limits Minimum: 1 | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits | Default— |
Fieldseed | Typeinteger | RequirementOptional | Values & limits | Default— |
Fieldstop | Type | RequirementOptional | Values & limits | Default— |
Fieldfrequency_penalty | Typenumber | RequirementOptional | Values & limits | Default— |
Fieldpresence_penalty | Typenumber | RequirementOptional | Values & limits | Default— |
Fielduser | Typestring | RequirementOptional | Values & limits | Default— |
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parameteroptional | Contractstream, max_tokens, max_completion_tokens, n, temperature, top_p, seed, stop, frequency_penalty, presence_penalty, user |
Parametermaterial_types | Contracttext |
Parameterconditions | Contract |
Lifecycle: synchronous_json_or_sse
Tariff references do not add request options. Supported parameters are listed for the selected method.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.00132 / 1K tokens Output · Output tokens $0.00396 / 1K tokens Input · Cache read $0.000044 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "~deepseek/deepseek-pro-latest", "messages": [{"role": "user", "content": "Summarize the supplied text in three concise points."}], "stream": false}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\n# Submit once. Retain the complete result, original identifiers and every response header.\nJSON or supported SSE
Keep every complete returned response, file and content part.
Retain the complete response, all actual results, original identifiers, usage and response headers.
Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.
Ailoot Ultra deepseek/deepseek-v4-pro-0813, ~deepseek/deepseek-pro-latest
Use the method paths shown above.
deepseek/deepseek-v4-pro-0813, ~deepseek/deepseek-pro-latest