Mistral Saba is Mistral AI's specialized regional text model, created by fine-tuning a Small-family model with curated material from the Middle East and South Asia. The maker describes a 24-billion-parameter model intended to reflect regional language, cultural context and local forms of expression. It receives a written task and source material and returns text.
Regional language and context
The release explicitly identifies Arabic and many Indian-origin languages, with particular strength in South Indian-origin languages such as Tamil. Its focus is more specific than simply changing the final language of a general-purpose answer: the training material is chosen for the regional linguistic and cultural context in which the response will be used.
Specify the audience, region, language and desired register before asking for a result. A formal explanation, a customer-facing message and an educational passage can require different terminology and forms of address. Supply a glossary for product names or specialist terms that must remain consistent, and state whether the result should preserve the source wording or adapt its explanation to the reader.
The maker page gives a 32k context window and identifies the edition as mistral-saba-2502. Use the context for the relevant source passages, conversation and instructions together. A regionally adapted response still needs the actual product conditions, procedure or document content supplied as evidence; cultural familiarity does not supply a company's private information.
Conversational support
The maker highlights Arabic conversational assistants as a central use case. A practical support request can provide the user's message and the approved reference material, then ask for a response in a named register. Request the next action, the condition that makes it applicable and any detail the user still needs to supply. This keeps the answer anchored to the particular issue rather than producing a generic regional greeting.
For a bilingual explanation, identify the language of the source and the language of the final message. Preserve names, amounts or units supplied in the material and describe the audience that should understand the answer. A follow-up can ask for a shorter version or a clarification of one term while retaining the same conditions.
Domain-specific adaptation
The announcement describes fine-tuning Saba for particular domains, including energy and other regional professional contexts. That is an adaptation process rather than a claim that every specialized dataset is already part of the default model. For a domain-oriented text task, supply the terminology, source documents and response rules relevant to the actual application.
A technical explanation can ask the model to restate a procedure using the reader's regional terminology while retaining the original steps and conditions. A document question can identify the clause to explain and request a concise answer with the supporting passage. Distinguish the source fact, the explanation and any unresolved term when preparing the output.
Cultural content creation
The maker also describes culturally relevant writing and educational resources. Give the topic, intended audience, language and the facts or examples that should appear. For an educational passage, specify what the learner should understand at the end and ask for an explanation followed by a practical example. For an organizational message, provide the purpose and the information the reader must act on.
When local idioms or cultural references are part of the task, state the context in which they will be used. Request an alternative wording when a formal or more neutral version would serve another audience. These are practical ways to apply the model's regional specialization while keeping the content and intended use explicit.
Edition and result boundaries
Saba's documented specialization is text-based regional language work with a 32k context. It should not inherit image input, hybrid reasoning controls or tool-format features from later Small or Medium models merely because it is a Small-family fine-tune. The sources read do not state a separate maximum output-token capacity for this edition.
Prepare the complete written task, the relevant source facts and the desired artifact: a support reply, explanation, adapted passage or short educational text. Keep the named Saba edition and the audience's language and register explicit so that the resulting text answers the actual regional communication need.
", "aboutText": "Mistral Saba is Mistral AI's specialized regional text model, created by fine-tuning a Small-family model with curated material from the Middle East and South Asia. The maker describes a 24-billion-parameter model intended to reflect regional language, cultural context and local forms of expression. It receives a written task and source material and returns text.\n\nRegional language and context\n\nThe release explicitly identifies Arabic and many Indian-origin languages, with particular strength in South Indian-origin languages such as Tamil. Its focus is more specific than simply changing the final language of a general-purpose answer: the training material is chosen for the regional linguistic and cultural context in which the response will be used.\n\nSpecify the audience, region, language and desired register before asking for a result. A formal explanation, a customer-facing message and an educational passage can require different terminology and forms of address. Supply a glossary for product names or specialist terms that must remain consistent, and state whether the result should preserve the source wording or adapt its explanation to the reader.\n\nThe maker page gives a 32k context window and identifies the edition as mistral-saba-2502. Use the context for the relevant source passages, conversation and instructions together. A regionally adapted response still needs the actual product conditions, procedure or document content supplied as evidence; cultural familiarity does not supply a company's private information.\n\nConversational support\n\nThe maker highlights Arabic conversational assistants as a central use case. A practical support request can provide the user's message and the approved reference material, then ask for a response in a named register. Request the next action, the condition that makes it applicable and any detail the user still needs to supply. This keeps the answer anchored to the particular issue rather than producing a generic regional greeting.\n\nFor a bilingual explanation, identify the language of the source and the language of the final message. Preserve names, amounts or units supplied in the material and describe the audience that should understand the answer. A follow-up can ask for a shorter version or a clarification of one term while retaining the same conditions.\n\nDomain-specific adaptation\n\nThe announcement describes fine-tuning Saba for particular domains, including energy and other regional professional contexts. That is an adaptation process rather than a claim that every specialized dataset is already part of the default model. For a domain-oriented text task, supply the terminology, source documents and response rules relevant to the actual application.\n\nA technical explanation can ask the model to restate a procedure using the reader's regional terminology while retaining the original steps and conditions. A document question can identify the clause to explain and request a concise answer with the supporting passage. Distinguish the source fact, the explanation and any unresolved term when preparing the output.\n\nCultural content creation\n\nThe maker also describes culturally relevant writing and educational resources. Give the topic, intended audience, language and the facts or examples that should appear. For an educational passage, specify what the learner should understand at the end and ask for an explanation followed by a practical example. For an organizational message, provide the purpose and the information the reader must act on.\n\nWhen local idioms or cultural references are part of the task, state the context in which they will be used. Request an alternative wording when a formal or more neutral version would serve another audience. These are practical ways to apply the model's regional specialization while keeping the content and intended use explicit.\n\nEdition and result boundaries\n\nSaba's documented specialization is text-based regional language work with a 32k context. It should not inherit image input, hybrid reasoning controls or tool-format features from later Small or Medium models merely because it is a Small-family fine-tune. The sources read do not state a separate maximum output-token capacity for this edition.\n\nPrepare the complete written task, the relevant source facts and the desired artifact: a support reply, explanation, adapted passage or short educational text. Keep the named Saba edition and the audience's language and register explicit so that the resulting text answers the actual regional communication need.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Draft an Arabic service reply\n\nWrite a polite Modern Standard Arabic support reply for customers in the Gulf. Approved facts: service desk hours are Sunday through Thursday, 09:00-17:00; ticket T-46 is received; no appointment has been assigned. Confirm receipt and explain the hours in two sentences. Keep T-46 unchanged and do not promise a visit time.A two-sentence Arabic reply retaining the ticket ID, workdays, hours and unassigned appointment status.Review the Arabic for meaning and verify that no appointment or Friday service is promised.mistralai/mistral-sabaMistral Saba is a 24B text model trained with curated Middle Eastern and South Asian material. It focuses on regional language and cultural context, including Arabic and Indian-origin languages such as Tamil, with a 32k maker context for written tasks.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Mistral Saba is Mistral AI's specialized regional text model, created by fine-tuning a Small-family model with curated material from the Middle East and South Asia. The maker describes a 24-billion-parameter model intended to reflect regional language, cultural context and local forms of expression. It receives a written task and source material and returns text.
Regional language and context
The release explicitly identifies Arabic and many Indian-origin languages, with particular strength in South Indian-origin languages such as Tamil. Its focus is more specific than simply changing the final language of a general-purpose answer: the training material is chosen for the regional linguistic and cultural context in which the response will be used.
Specify the audience, region, language and desired register before asking for a result. A formal explanation, a customer-facing message and an educational passage can require different terminology and forms of address. Supply a glossary for product names or specialist terms that must remain consistent, and state whether the result should preserve the source wording or adapt its explanation to the reader.
The maker page gives a 32k context window and identifies the edition as mistral-saba-2502. Use the context for the relevant source passages, conversation and instructions together. A regionally adapted response still needs the actual product conditions, procedure or document content supplied as evidence; cultural familiarity does not supply a company's private information.
Conversational support
The maker highlights Arabic conversational assistants as a central use case. A practical support request can provide the user's message and the approved reference material, then ask for a response in a named register. Request the next action, the condition that makes it applicable and any detail the user still needs to supply. This keeps the answer anchored to the particular issue rather than producing a generic regional greeting.
For a bilingual explanation, identify the language of the source and the language of the final message. Preserve names, amounts or units supplied in the material and describe the audience that should understand the answer. A follow-up can ask for a shorter version or a clarification of one term while retaining the same conditions.
Domain-specific adaptation
The announcement describes fine-tuning Saba for particular domains, including energy and other regional professional contexts. That is an adaptation process rather than a claim that every specialized dataset is already part of the default model. For a domain-oriented text task, supply the terminology, source documents and response rules relevant to the actual application.
A technical explanation can ask the model to restate a procedure using the reader's regional terminology while retaining the original steps and conditions. A document question can identify the clause to explain and request a concise answer with the supporting passage. Distinguish the source fact, the explanation and any unresolved term when preparing the output.
Cultural content creation
The maker also describes culturally relevant writing and educational resources. Give the topic, intended audience, language and the facts or examples that should appear. For an educational passage, specify what the learner should understand at the end and ask for an explanation followed by a practical example. For an organizational message, provide the purpose and the information the reader must act on.
When local idioms or cultural references are part of the task, state the context in which they will be used. Request an alternative wording when a formal or more neutral version would serve another audience. These are practical ways to apply the model's regional specialization while keeping the content and intended use explicit.
Edition and result boundaries
Saba's documented specialization is text-based regional language work with a 32k context. It should not inherit image input, hybrid reasoning controls or tool-format features from later Small or Medium models merely because it is a Small-family fine-tune. The sources read do not state a separate maximum output-token capacity for this edition.
Prepare the complete written task, the relevant source facts and the desired artifact: a support reply, explanation, adapted passage or short educational text. Keep the named Saba edition and the audience's language and register explicit so that the resulting text answers the actual regional communication need.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits mistralai/mistral-saba | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
Fieldmessages[].content | Typestring|content_part[]|null | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_calls | Typetool_call[] | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_call_id | Typestring | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
Fieldmessages[].name | Typestring | RequirementOptional | Values & limits | Default— |
Fieldmessages[].reasoning_content | Typestring | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
Fieldmessages[].reasoning_details | Typeobject|array | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmax_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldmax_completion_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldstream_options.include_usage | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstop | Typestring|string[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools | Typefunction_tool[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].type | Typestring | RequirementOptional | Values & limits function Model-specific | Default— |
Fieldtools[].function.name | Typestring | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
Fieldtools[].function.description | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools[].function.parameters | TypeJSON_schema | RequirementOptional | Values & limits | Default— |
Fieldtool_choice | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldparallel_tool_calls | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldresponse_format | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning_effort | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldservice_tier | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldinstructions | Typestring | RequirementOptional | Values & limits Compatibility field | Default— |
Fieldfunctions | Typefunction[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldfunction_call | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldprompt_cache_options | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmodalities | Typestring[] | RequirementOptional | Values & limits text | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— |
Fieldcache_control.ttl | Typestring | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice |
Parametercontrol_scope | Contractmodel-specific; user function tools differ from hosted tools |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0004 / 1K tokens Output · Output tokens $0.0012 / 1K tokens Input · Cache read $0.00004 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0004 / 1K tokens Output · Output tokens $0.0012 / 1K tokens Input · Cache read $0.00004 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "mistralai/mistral-saba", "messages": [{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}]}')\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\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("choices",[]):\n if x.get("message",{}).get("content"): print(x["message"]["content"])\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.chat.completions.create(model='mistralai/mistral-saba',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}])\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(result.to_dict(mode="json"))\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.chat.completions.stream(model='mistralai/mistral-saba',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_completion()\n save_result(final.to_dict(mode="json"),"stream-result")\njson or SSE
Keep every complete returned response, file and content part.
Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldchoices[].index | Typeinteger |
Fieldchoices[].message.content | Typestring|null |
Fieldchoices[].message.tool_calls | Typetool_call[] |
Fieldchoices[].message.reasoning_content | Typestring |
Fieldchoices[].message.reasoning_details | Typeobject|array |
Fieldchoices[].finish_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra mistralai/mistral-saba
Use the method paths shown above.
mistralai/mistral-sabaMistral Saba is a 24B text model trained with curated Middle Eastern and South Asian material. It focuses on regional language and cultural context, including Arabic and Indian-origin languages such as Tamil, with a 32k maker context for written tasks.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Mistral Saba is Mistral AI's specialized regional text model, created by fine-tuning a Small-family model with curated material from the Middle East and South Asia. The maker describes a 24-billion-parameter model intended to reflect regional language, cultural context and local forms of expression. It receives a written task and source material and returns text.
Regional language and context
The release explicitly identifies Arabic and many Indian-origin languages, with particular strength in South Indian-origin languages such as Tamil. Its focus is more specific than simply changing the final language of a general-purpose answer: the training material is chosen for the regional linguistic and cultural context in which the response will be used.
Specify the audience, region, language and desired register before asking for a result. A formal explanation, a customer-facing message and an educational passage can require different terminology and forms of address. Supply a glossary for product names or specialist terms that must remain consistent, and state whether the result should preserve the source wording or adapt its explanation to the reader.
The maker page gives a 32k context window and identifies the edition as mistral-saba-2502. Use the context for the relevant source passages, conversation and instructions together. A regionally adapted response still needs the actual product conditions, procedure or document content supplied as evidence; cultural familiarity does not supply a company's private information.
Conversational support
The maker highlights Arabic conversational assistants as a central use case. A practical support request can provide the user's message and the approved reference material, then ask for a response in a named register. Request the next action, the condition that makes it applicable and any detail the user still needs to supply. This keeps the answer anchored to the particular issue rather than producing a generic regional greeting.
For a bilingual explanation, identify the language of the source and the language of the final message. Preserve names, amounts or units supplied in the material and describe the audience that should understand the answer. A follow-up can ask for a shorter version or a clarification of one term while retaining the same conditions.
Domain-specific adaptation
The announcement describes fine-tuning Saba for particular domains, including energy and other regional professional contexts. That is an adaptation process rather than a claim that every specialized dataset is already part of the default model. For a domain-oriented text task, supply the terminology, source documents and response rules relevant to the actual application.
A technical explanation can ask the model to restate a procedure using the reader's regional terminology while retaining the original steps and conditions. A document question can identify the clause to explain and request a concise answer with the supporting passage. Distinguish the source fact, the explanation and any unresolved term when preparing the output.
Cultural content creation
The maker also describes culturally relevant writing and educational resources. Give the topic, intended audience, language and the facts or examples that should appear. For an educational passage, specify what the learner should understand at the end and ask for an explanation followed by a practical example. For an organizational message, provide the purpose and the information the reader must act on.
When local idioms or cultural references are part of the task, state the context in which they will be used. Request an alternative wording when a formal or more neutral version would serve another audience. These are practical ways to apply the model's regional specialization while keeping the content and intended use explicit.
Edition and result boundaries
Saba's documented specialization is text-based regional language work with a 32k context. It should not inherit image input, hybrid reasoning controls or tool-format features from later Small or Medium models merely because it is a Small-family fine-tune. The sources read do not state a separate maximum output-token capacity for this edition.
Prepare the complete written task, the relevant source facts and the desired artifact: a support reply, explanation, adapted passage or short educational text. Keep the named Saba edition and the audience's language and register explicit so that the resulting text answers the actual regional communication need.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits mistralai/mistral-saba | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring | RequirementRequired | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF-8 text
messages[].content string
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractstream |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_or_streamed
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0004 / 1K tokens Output · Output tokens $0.0012 / 1K tokens Input · Cache read $0.00004 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0004 / 1K tokens Output · Output tokens $0.0012 / 1K tokens Input · Cache read $0.00004 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "mistralai/mistral-saba",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'mistralai/mistral-saba', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'mistralai/mistral-saba', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n with urlopen(request, timeout=120) as response:\n raw = response.read()\n Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n Path('result.json').write_bytes(error.read())\n Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nJSON or SSE
Keep every complete returned response, file and content part.
Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldmodel | Typestring |
Fieldcontent[] | Typetext|thinking|tool_use|other content block |
Fieldstop_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra mistralai/mistral-saba
Use the method paths shown above.
Technical example in English
Draft an Arabic service reply\n\nWrite a polite Modern Standard Arabic support reply for customers in the Gulf. Approved facts: service desk hours are Sunday through Thursday, 09:00-17:00; ticket T-46 is received; no appointment has been assigned. Confirm receipt and explain the hours in two sentences. Keep T-46 unchanged and do not promise a visit time.A two-sentence Arabic reply retaining the ticket ID, workdays, hours and unassigned appointment status.Review the Arabic for meaning and verify that no appointment or Friday service is promised.