Hunyuan-MT-7B is Tencent’s multilingual translation model. Its basic job is to take a source passage and produce that passage in the requested target language. Tencent distinguishes this translator from Hunyuan-MT-Chimera, the family’s ensemble model that refines several candidate translations into one result.
Tencent describes mutual translation across 33 languages and highlights five Chinese ethnic-minority languages or dialects. The published language table includes Chinese, Traditional Chinese, English, French, Portuguese, Spanish, Japanese, Turkish, Russian, Arabic, Korean, Thai, Italian, German, Vietnamese, Malay, Indonesian, Filipino, Hindi, Polish, Czech, Dutch, Khmer, Burmese, Persian, Gujarati, Urdu, Telugu, Marathi, Hebrew, Bengali, Tamil and Ukrainian. It also explicitly lists Tibetan, Kazakh, Mongolian, Uyghur and Cantonese.
State the target language precisely, including the required writing system where relevant. A useful brief can identify whether a document needs Simplified or Traditional Chinese, and name the audience and terminology that should remain consistent. Keep the source passage intact so that the translation can be checked against the exact material supplied.
The manufacturer provides one prompt template for translation involving Chinese and another for language pairs that do not involve Chinese. Both name the target language, place the source text beneath the instruction and ask for the translation without an added explanation. The model has no default system prompt, so put the task instruction in the submitted message rather than relying on an unspecified default role.
For a non-Chinese pair, an original brief can begin: “Translate the following segment into French, without additional explanation.” Follow it with the source passage. When the task involves Chinese, use the corresponding Chinese template and replace its target-language placeholder. The expected artifact is the translated passage, ready for a separate review or an application’s next processing step.
Use coherent sentences or paragraphs instead of breaking text at arbitrary character positions. Keep the surrounding material needed to interpret pronouns, technical terms and idioms. For a product manual, include the product name, defined terms and the actual instruction together; for a support exchange, preserve the question and the answer it refers to.
If a larger document is processed in segments, keep a stable segment ID outside the text being translated and maintain the agreed terminology across the resulting passages. Ask explicitly how to handle names, measurements and placeholders, then inspect that treatment in the output. These preparation steps make the result easier to assemble and review; they do not replace checking the translated meaning.
Hunyuan-MT-7B produces a translation from the source. Chimera’s documented workflow instead takes the original source plus several target-language candidates and produces a single refined translation. A workflow that uses both stages must supply those candidates to the separate ensemble model; selecting MT-7B alone does not perform that additional merge.
The producer also lists FP8 checkpoints separately. Retain the ordinary Hunyuan-MT-7B edition name when saving the request and translation, and distinguish it from an FP8 or Chimera artifact when comparing results. The later HY-MT1.5 models have their own identities and specifications.
Tencent recommends temperature 0.7, top_p 0.6, top_k 20 and repetition_penalty 1.05 in its native inference example. Treat the translated content as the result to review. Check names, numbers, units, negation, dates and the relationship between sentences against the source, especially where a literal translation could lose the intended meaning.
Retain the source, target language, selected model identity and final reviewed translation together. For application text, check that placeholders and formatting still connect to the intended fields; for a document, read the joined paragraphs for consistent terminology and tone. A fluent sentence can still require correction if it changes a factual detail or an instruction.
Through Ailoot, select this exact model ID in /v1/chat/completions and supply the task in messages. Each message carries a role and its content; keep the relevant instruction and source material together. Collect the complete JSON response or all SSE segments when stream is enabled, and retain usage with the written result.
", "aboutText": "Hunyuan-MT-7B is Tencent’s multilingual translation model. Its basic job is to take a source passage and produce that passage in the requested target language. Tencent distinguishes this translator from Hunyuan-MT-Chimera, the family’s ensemble model that refines several candidate translations into one result.\n\n### Choose the language pair and the intended translation\n\nTencent describes mutual translation across 33 languages and highlights five Chinese ethnic-minority languages or dialects. The published language table includes Chinese, Traditional Chinese, English, French, Portuguese, Spanish, Japanese, Turkish, Russian, Arabic, Korean, Thai, Italian, German, Vietnamese, Malay, Indonesian, Filipino, Hindi, Polish, Czech, Dutch, Khmer, Burmese, Persian, Gujarati, Urdu, Telugu, Marathi, Hebrew, Bengali, Tamil and Ukrainian. It also explicitly lists Tibetan, Kazakh, Mongolian, Uyghur and Cantonese.\n\nState the target language precisely, including the required writing system where relevant. A useful brief can identify whether a document needs Simplified or Traditional Chinese, and name the audience and terminology that should remain consistent. Keep the source passage intact so that the translation can be checked against the exact material supplied.\n\n### Follow the producer’s translation prompt\n\nThe manufacturer provides one prompt template for translation involving Chinese and another for language pairs that do not involve Chinese. Both name the target language, place the source text beneath the instruction and ask for the translation without an added explanation. The model has no default system prompt, so put the task instruction in the submitted message rather than relying on an unspecified default role.\n\nFor a non-Chinese pair, an original brief can begin: “Translate the following segment into French, without additional explanation.” Follow it with the source passage. When the task involves Chinese, use the corresponding Chinese template and replace its target-language placeholder. The expected artifact is the translated passage, ready for a separate review or an application’s next processing step.\n\n### Prepare segments that preserve meaning\n\nUse coherent sentences or paragraphs instead of breaking text at arbitrary character positions. Keep the surrounding material needed to interpret pronouns, technical terms and idioms. For a product manual, include the product name, defined terms and the actual instruction together; for a support exchange, preserve the question and the answer it refers to.\n\nIf a larger document is processed in segments, keep a stable segment ID outside the text being translated and maintain the agreed terminology across the resulting passages. Ask explicitly how to handle names, measurements and placeholders, then inspect that treatment in the output. These preparation steps make the result easier to assemble and review; they do not replace checking the translated meaning.\n\n### Keep the translator and the ensemble separate\n\nHunyuan-MT-7B produces a translation from the source. Chimera’s documented workflow instead takes the original source plus several target-language candidates and produces a single refined translation. A workflow that uses both stages must supply those candidates to the separate ensemble model; selecting MT-7B alone does not perform that additional merge.\n\nThe producer also lists FP8 checkpoints separately. Retain the ordinary Hunyuan-MT-7B edition name when saving the request and translation, and distinguish it from an FP8 or Chimera artifact when comparing results. The later HY-MT1.5 models have their own identities and specifications.\n\n### Native inference guidance and result review\n\nTencent recommends temperature 0.7, top_p 0.6, top_k 20 and repetition_penalty 1.05 in its native inference example. Treat the translated content as the result to review. Check names, numbers, units, negation, dates and the relationship between sentences against the source, especially where a literal translation could lose the intended meaning.\n\nRetain the source, target language, selected model identity and final reviewed translation together. For application text, check that placeholders and formatting still connect to the intended fields; for a document, read the joined paragraphs for consistent terminology and tone. A fluent sentence can still require correction if it changes a factual detail or an instruction.\n\nThrough Ailoot, select this exact model ID in /v1/chat/completions and supply the task in messages. Each message carries a role and its content; keep the relevant instruction and source material together. Collect the complete JSON response or all SSE segments when stream is enabled, and retain usage with the written result.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "62caf1339d04262f681eee248622acaa8563cc49b8fbe7d61532ffd645c9e773", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "tencent/Hunyuan-MT-7BTencent’s Hunyuan-MT-7B translates supplied text into a named target language, with multilingual coverage and particular attention to Chinese, minority languages and dialects. It is the translation model in the family; the separately named Chimera model combines multiple translation candidates.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Hunyuan-MT-7B is Tencent’s multilingual translation model. Its basic job is to take a source passage and produce that passage in the requested target language. Tencent distinguishes this translator from Hunyuan-MT-Chimera, the family’s ensemble model that refines several candidate translations into one result.
Tencent describes mutual translation across 33 languages and highlights five Chinese ethnic-minority languages or dialects. The published language table includes Chinese, Traditional Chinese, English, French, Portuguese, Spanish, Japanese, Turkish, Russian, Arabic, Korean, Thai, Italian, German, Vietnamese, Malay, Indonesian, Filipino, Hindi, Polish, Czech, Dutch, Khmer, Burmese, Persian, Gujarati, Urdu, Telugu, Marathi, Hebrew, Bengali, Tamil and Ukrainian. It also explicitly lists Tibetan, Kazakh, Mongolian, Uyghur and Cantonese.
State the target language precisely, including the required writing system where relevant. A useful brief can identify whether a document needs Simplified or Traditional Chinese, and name the audience and terminology that should remain consistent. Keep the source passage intact so that the translation can be checked against the exact material supplied.
The manufacturer provides one prompt template for translation involving Chinese and another for language pairs that do not involve Chinese. Both name the target language, place the source text beneath the instruction and ask for the translation without an added explanation. The model has no default system prompt, so put the task instruction in the submitted message rather than relying on an unspecified default role.
For a non-Chinese pair, an original brief can begin: “Translate the following segment into French, without additional explanation.” Follow it with the source passage. When the task involves Chinese, use the corresponding Chinese template and replace its target-language placeholder. The expected artifact is the translated passage, ready for a separate review or an application’s next processing step.
Use coherent sentences or paragraphs instead of breaking text at arbitrary character positions. Keep the surrounding material needed to interpret pronouns, technical terms and idioms. For a product manual, include the product name, defined terms and the actual instruction together; for a support exchange, preserve the question and the answer it refers to.
If a larger document is processed in segments, keep a stable segment ID outside the text being translated and maintain the agreed terminology across the resulting passages. Ask explicitly how to handle names, measurements and placeholders, then inspect that treatment in the output. These preparation steps make the result easier to assemble and review; they do not replace checking the translated meaning.
Hunyuan-MT-7B produces a translation from the source. Chimera’s documented workflow instead takes the original source plus several target-language candidates and produces a single refined translation. A workflow that uses both stages must supply those candidates to the separate ensemble model; selecting MT-7B alone does not perform that additional merge.
The producer also lists FP8 checkpoints separately. Retain the ordinary Hunyuan-MT-7B edition name when saving the request and translation, and distinguish it from an FP8 or Chimera artifact when comparing results. The later HY-MT1.5 models have their own identities and specifications.
Tencent recommends temperature 0.7, top_p 0.6, top_k 20 and repetition_penalty 1.05 in its native inference example. Treat the translated content as the result to review. Check names, numbers, units, negation, dates and the relationship between sentences against the source, especially where a literal translation could lose the intended meaning.
Retain the source, target language, selected model identity and final reviewed translation together. For application text, check that placeholders and formatting still connect to the intended fields; for a document, read the joined paragraphs for consistent terminology and tone. A fluent sentence can still require correction if it changes a factual detail or an instruction.
Through Ailoot, select this exact model ID in /v1/chat/completions and supply the task in messages. Each message carries a role and its content; keep the relevant instruction and source material together. Collect the complete JSON response or all SSE segments when stream is enabled, and retain usage with the written result.
POST /v1/chat/completionstext, imagetext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits tencent/Hunyuan-MT-7B Conditions: Use this exact Ailoot routing selector. | Default— |
Fieldmessages | Typearray | RequirementRequired | Values & limits Conditions: | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits Conditions: | Defaultfalse |
text_input · Required: messages
image_with_text · Required: messages with actual image content blocks
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parameteroptional | Contractstream |
Parametermaterial_types | Contracttext, image |
Parameterconditions | ContractUse this exact Ailoot routing selector., Image content is carried by this protocol where the exact selected model supports vision. Protocol admission does not establish image capability for every model. |
Method aliases: /chat/completions
Lifecycle: synchronous_or_streamed
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 / 1K tokens Output · Output tokens $0 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${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/Hunyuan-MT-7B", "messages": [{"role": "user", "content": "Explain how a rainbow forms."}]}')\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 SSE
Keep every complete returned response, file and content part.
Retain every content block, tool-call ID, thinking signature when returned, all SSE deltas and complete usage. A first text fragment is not the whole result.
Keep the original X-Client-Request-ID, response and headers. An unknown or result_pending_check outcome does not authorize a second creation.
| Field | Type |
|---|---|
Fieldchoices[] | Typeobject |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionA required field, model selector, type or input representation is invalid. | Next stepInspect the returned validation detail before preparing a separate request. |
Response | ConditionThe original request or result is unknown or requires a check. | Next stepKeep original identifiers and headers; read only supported status/library records. Do not submit creation again. |
Ailoot Ultra tencent/Hunyuan-MT-7B
/chat/completions
tencent/Hunyuan-MT-7BTencent’s Hunyuan-MT-7B translates supplied text into a named target language, with multilingual coverage and particular attention to Chinese, minority languages and dialects. It is the translation model in the family; the separately named Chimera model combines multiple translation candidates.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Hunyuan-MT-7B is Tencent’s multilingual translation model. Its basic job is to take a source passage and produce that passage in the requested target language. Tencent distinguishes this translator from Hunyuan-MT-Chimera, the family’s ensemble model that refines several candidate translations into one result.
Tencent describes mutual translation across 33 languages and highlights five Chinese ethnic-minority languages or dialects. The published language table includes Chinese, Traditional Chinese, English, French, Portuguese, Spanish, Japanese, Turkish, Russian, Arabic, Korean, Thai, Italian, German, Vietnamese, Malay, Indonesian, Filipino, Hindi, Polish, Czech, Dutch, Khmer, Burmese, Persian, Gujarati, Urdu, Telugu, Marathi, Hebrew, Bengali, Tamil and Ukrainian. It also explicitly lists Tibetan, Kazakh, Mongolian, Uyghur and Cantonese.
State the target language precisely, including the required writing system where relevant. A useful brief can identify whether a document needs Simplified or Traditional Chinese, and name the audience and terminology that should remain consistent. Keep the source passage intact so that the translation can be checked against the exact material supplied.
The manufacturer provides one prompt template for translation involving Chinese and another for language pairs that do not involve Chinese. Both name the target language, place the source text beneath the instruction and ask for the translation without an added explanation. The model has no default system prompt, so put the task instruction in the submitted message rather than relying on an unspecified default role.
For a non-Chinese pair, an original brief can begin: “Translate the following segment into French, without additional explanation.” Follow it with the source passage. When the task involves Chinese, use the corresponding Chinese template and replace its target-language placeholder. The expected artifact is the translated passage, ready for a separate review or an application’s next processing step.
Use coherent sentences or paragraphs instead of breaking text at arbitrary character positions. Keep the surrounding material needed to interpret pronouns, technical terms and idioms. For a product manual, include the product name, defined terms and the actual instruction together; for a support exchange, preserve the question and the answer it refers to.
If a larger document is processed in segments, keep a stable segment ID outside the text being translated and maintain the agreed terminology across the resulting passages. Ask explicitly how to handle names, measurements and placeholders, then inspect that treatment in the output. These preparation steps make the result easier to assemble and review; they do not replace checking the translated meaning.
Hunyuan-MT-7B produces a translation from the source. Chimera’s documented workflow instead takes the original source plus several target-language candidates and produces a single refined translation. A workflow that uses both stages must supply those candidates to the separate ensemble model; selecting MT-7B alone does not perform that additional merge.
The producer also lists FP8 checkpoints separately. Retain the ordinary Hunyuan-MT-7B edition name when saving the request and translation, and distinguish it from an FP8 or Chimera artifact when comparing results. The later HY-MT1.5 models have their own identities and specifications.
Tencent recommends temperature 0.7, top_p 0.6, top_k 20 and repetition_penalty 1.05 in its native inference example. Treat the translated content as the result to review. Check names, numbers, units, negation, dates and the relationship between sentences against the source, especially where a literal translation could lose the intended meaning.
Retain the source, target language, selected model identity and final reviewed translation together. For application text, check that placeholders and formatting still connect to the intended fields; for a document, read the joined paragraphs for consistent terminology and tone. A fluent sentence can still require correction if it changes a factual detail or an instruction.
Through Ailoot, select this exact model ID in /v1/chat/completions and supply the task in messages. Each message carries a role and its content; keep the relevant instruction and source material together. Collect the complete JSON response or all SSE segments when stream is enabled, and retain usage with the written result.
POST /v1/messagestext, imagejson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits tencent/Hunyuan-MT-7B Conditions: Use this exact Ailoot routing selector. | Default— |
Fieldmessages | Typearray | RequirementRequired | Values & limits Conditions: | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits Conditions: | Defaultfalse |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits Minimum: 1 Conditions: | Default— |
text_input · Required: messages
image_with_text · Required: messages with actual image content blocks
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional | Contractstream |
Parametermaterial_types | Contracttext, image |
Parameterconditions | ContractUse this exact Ailoot routing selector., Image content is carried by this protocol where the exact selected model supports vision. Protocol admission does not establish image capability for every model. |
Lifecycle: synchronous_or_streamed
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 / 1K tokens Output · Output tokens $0 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${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/Hunyuan-MT-7B", "messages": [{"role": "user", "content": "Explain how a rainbow forms."}], "max_tokens": 256}')\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/messages \\\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 SSE
Keep every complete returned response, file and content part.
Retain every content block, tool-call ID, thinking signature when returned, all SSE deltas and complete usage. A first text fragment is not the whole result.
Keep the original X-Client-Request-ID, response and headers. An unknown or result_pending_check outcome does not authorize a second creation.
| Field | Type |
|---|---|
Fieldcontent[] | Typeobject |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionA required field, model selector, type or input representation is invalid. | Next stepInspect the returned validation detail before preparing a separate request. |
Response | ConditionThe original request or result is unknown or requires a check. | Next stepKeep original identifiers and headers; read only supported status/library records. Do not submit creation again. |
Ailoot Ultra tencent/Hunyuan-MT-7B
/chat/completions