Tencent Hy3 is a text-input, text-output model selected with the exact ID tencent/hy3. Its published context length is 262,144 tokens. Use the available context to organise substantial source material with the question it must answer: labelled document sections, a relevant conversation or code excerpts. Define the requested result, such as a decision summary, a comparison against named criteria or a draft grounded in the supplied policy text.
Call POST /v1/chat/completions with model and a nonempty messages array. Put the actual source material in message text and preserve the turns needed for a continuing conversation. For several documents, give each one a stable label and ask the answer to identify the passages supporting its conclusions. For a code task, include the relevant definitions and the observed behaviour, then state whether the deliverable is an explanation, review or proposed change.
The published controls include max_tokens and max_completion_tokens for the requested answer budget, temperature and stop for generation, and reasoning, reasoning_effort and include_reasoning for reasoning-related requests. The declared default temperature is 0.9. Select controls deliberately for the task and retain the actual values with the request so a comparison between answers uses a known configuration. Allocate context to instructions, source material, history and the reply you request.
For an application that consumes a particular response shape, the model profile includes response_format. It also exposes tools and tool_choice for function-tool workflows. Supply the function definitions the application actually implements, retain any returned tool-call identifiers and arguments, and perform the indicated application action before supplying its result in the conversation. Keep the tool schema and the expected output fields explicit so the application can inspect the generated response before continuing.
Use stream:false for a complete JSON reply or stream:true to deliver response events to an interactive interface. Preserve every returned choice, content block, tool call, reasoning field and usage field that the response supplies. When streaming, assemble deltas by their choice and tool-call indices and retain the final finish information. Keep the original request and response identifiers if delivery becomes uncertain so the original exchange can be checked before another submission.
", "aboutText": "Tencent Hy3 is a text-input, text-output model selected with the exact ID tencent/hy3. Its published context length is 262,144 tokens. Use the available context to organise substantial source material with the question it must answer: labelled document sections, a relevant conversation or code excerpts. Define the requested result, such as a decision summary, a comparison against named criteria or a draft grounded in the supplied policy text.\n\nCall POST /v1/chat/completions with model and a nonempty messages array. Put the actual source material in message text and preserve the turns needed for a continuing conversation. For several documents, give each one a stable label and ask the answer to identify the passages supporting its conclusions. For a code task, include the relevant definitions and the observed behaviour, then state whether the deliverable is an explanation, review or proposed change.\n\nThe published controls include max_tokens and max_completion_tokens for the requested answer budget, temperature and stop for generation, and reasoning, reasoning_effort and include_reasoning for reasoning-related requests. The declared default temperature is 0.9. Select controls deliberately for the task and retain the actual values with the request so a comparison between answers uses a known configuration. Allocate context to instructions, source material, history and the reply you request.\n\nFor an application that consumes a particular response shape, the model profile includes response_format. It also exposes tools and tool_choice for function-tool workflows. Supply the function definitions the application actually implements, retain any returned tool-call identifiers and arguments, and perform the indicated application action before supplying its result in the conversation. Keep the tool schema and the expected output fields explicit so the application can inspect the generated response before continuing.\n\nUse stream:false for a complete JSON reply or stream:true to deliver response events to an interactive interface. Preserve every returned choice, content block, tool call, reasoning field and usage field that the response supplies. When streaming, assemble deltas by their choice and tool-call indices and retain the final finish information. Keep the original request and response identifiers if delivery becomes uncertain so the original exchange can be checked before another submission.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "537fa5401be823a1a98867fe1fc991ccf11da11a368b734e22ad91a76a7f8d19", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "tencent/hy3Tencent Hy3 is a text model with a published 262,144-token context and Chat Completions access under tencent/hy3. Use it with supplied documents, conversation history or code text, and define a concrete deliverable such as a structured summary, comparison or proposed response. The profile includes reasoning, response-format and function-tool controls.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Tencent Hy3 is a text-input, text-output model selected with the exact ID tencent/hy3. Its published context length is 262,144 tokens. Use the available context to organise substantial source material with the question it must answer: labelled document sections, a relevant conversation or code excerpts. Define the requested result, such as a decision summary, a comparison against named criteria or a draft grounded in the supplied policy text.
Call POST /v1/chat/completions with model and a nonempty messages array. Put the actual source material in message text and preserve the turns needed for a continuing conversation. For several documents, give each one a stable label and ask the answer to identify the passages supporting its conclusions. For a code task, include the relevant definitions and the observed behaviour, then state whether the deliverable is an explanation, review or proposed change.
The published controls include max_tokens and max_completion_tokens for the requested answer budget, temperature and stop for generation, and reasoning, reasoning_effort and include_reasoning for reasoning-related requests. The declared default temperature is 0.9. Select controls deliberately for the task and retain the actual values with the request so a comparison between answers uses a known configuration. Allocate context to instructions, source material, history and the reply you request.
For an application that consumes a particular response shape, the model profile includes response_format. It also exposes tools and tool_choice for function-tool workflows. Supply the function definitions the application actually implements, retain any returned tool-call identifiers and arguments, and perform the indicated application action before supplying its result in the conversation. Keep the tool schema and the expected output fields explicit so the application can inspect the generated response before continuing.
Use stream:false for a complete JSON reply or stream:true to deliver response events to an interactive interface. Preserve every returned choice, content block, tool call, reasoning field and usage field that the response supplies. When streaming, assemble deltas by their choice and tool-call indices and retain the final finish information. Keep the original request and response identifiers if delivery becomes uncertain so the original exchange can be checked before another submission.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits tencent/hy3 | 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 $0.000165 / 1K tokens Output · Output tokens $0.00066 / 1K tokens Input · Cache read $0.00004125 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${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": "tencent/hy3", "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 tencent/hy3
Use the method paths shown above.