Ling-3.0-flash-VL is inclusionAI’s native multimodal extension of Ling-3.0-flash. It combines the base model’s language, reasoning and long-context capabilities with image and video understanding. The manufacturer organizes its visual task scope into understanding, reasoning and acting: reading complex visual information, using it as evidence, and translating observations into actions in a supporting application. The model’s response is text or the tool-call representation used by that application.
The published architecture has 124B total parameters and 5.5B activated parameters per token. A vision transformer extracts image and video features, and a two-layer projector aligns them with the language representation. VideoRoPE carries both spatial positions and temporal order. The 42-layer hybrid backbone alternates Kimi Delta Attention and gated Multi-head Latent Attention in a 5:1 pattern, with sparse expert routing. The maker describes up to 256K tokens of context and publishes a 262,144-token extended-context recipe.
For visual understanding, supply a readable image and identify the required observation. The maker lists object counting, complex layouts, charts and document content among the tasks. A useful document request can ask for a field table with the supporting page or visible region, while a chart request can ask which series supports a stated comparison. Preserve the original visual material so numbers, labels and small details can be checked. An unclear region should remain unclear in the result rather than becoming a guessed value.
For reasoning with visual evidence, provide the question, relevant assumptions and the precision needed in the final answer. The model can connect a chart, diagram or screenshot to calculation and multi-step reasoning. Ask for the conclusion to identify the observations on which it depends. If the workflow includes calculation or information-retrieval tools, retain their actual results and separate them from the model’s interpretation. A visual relationship and a calibrated measurement are different kinds of evidence.
For video, preserve the order of the material and focus the question on an event, change or interval. The maker identifies event localization, long-video questions and clip-editing workflows as applications of its temporal representation. A practical editorial result can be a proposed cut list explaining which moments to retain and why. Keep that proposal connected to the source timeline; the surrounding editing application performs the changes and produces the edited media. Video understanding does not itself make the model’s text answer a new video file.
For interface tasks, include the current screenshot, the goal and the actions available to the application. Ling-3.0-flash-VL can interpret web or software interfaces and propose sequences of actions from visual information. Feed back the observed state after each operation when the next step depends on it. A useful completion record shows what changed in the interface and whether the requested result is visible, rather than treating a proposed click as an executed action.
Thinking is enabled by default in the maker’s chat template and can be disabled per request in its documented implementation with enable_thinking set to false. The client and generation recipe recommends temperature 1.0, top_p 0.95 and top_k 20; separate evaluation notes use their own settings. Choose the final answer’s form explicitly and leave space for both relevant media context and generated text. These producer settings describe the released model recipe, not a promise about controls exposed by every application.
Retain the VL identity when recording a result: its image and video inputs distinguish it from the text-focused Ling-3.0-flash and the finance-specialized Fin edition. Review extracted wording, counts, temporal locations and proposed interface actions against the source material. The useful final artifact is a visual analysis or action proposal that keeps its evidence and unresolved details inspectable.
", "aboutText": "Ling-3.0-flash-VL is inclusionAI’s native multimodal extension of Ling-3.0-flash. It combines the base model’s language, reasoning and long-context capabilities with image and video understanding. The manufacturer organizes its visual task scope into understanding, reasoning and acting: reading complex visual information, using it as evidence, and translating observations into actions in a supporting application. The model’s response is text or the tool-call representation used by that application.\n\nThe published architecture has 124B total parameters and 5.5B activated parameters per token. A vision transformer extracts image and video features, and a two-layer projector aligns them with the language representation. VideoRoPE carries both spatial positions and temporal order. The 42-layer hybrid backbone alternates Kimi Delta Attention and gated Multi-head Latent Attention in a 5:1 pattern, with sparse expert routing. The maker describes up to 256K tokens of context and publishes a 262,144-token extended-context recipe.\n\nFor visual understanding, supply a readable image and identify the required observation. The maker lists object counting, complex layouts, charts and document content among the tasks. A useful document request can ask for a field table with the supporting page or visible region, while a chart request can ask which series supports a stated comparison. Preserve the original visual material so numbers, labels and small details can be checked. An unclear region should remain unclear in the result rather than becoming a guessed value.\n\nFor reasoning with visual evidence, provide the question, relevant assumptions and the precision needed in the final answer. The model can connect a chart, diagram or screenshot to calculation and multi-step reasoning. Ask for the conclusion to identify the observations on which it depends. If the workflow includes calculation or information-retrieval tools, retain their actual results and separate them from the model’s interpretation. A visual relationship and a calibrated measurement are different kinds of evidence.\n\nFor video, preserve the order of the material and focus the question on an event, change or interval. The maker identifies event localization, long-video questions and clip-editing workflows as applications of its temporal representation. A practical editorial result can be a proposed cut list explaining which moments to retain and why. Keep that proposal connected to the source timeline; the surrounding editing application performs the changes and produces the edited media. Video understanding does not itself make the model’s text answer a new video file.\n\nFor interface tasks, include the current screenshot, the goal and the actions available to the application. Ling-3.0-flash-VL can interpret web or software interfaces and propose sequences of actions from visual information. Feed back the observed state after each operation when the next step depends on it. A useful completion record shows what changed in the interface and whether the requested result is visible, rather than treating a proposed click as an executed action.\n\nThinking is enabled by default in the maker’s chat template and can be disabled per request in its documented implementation with enable_thinking set to false. The client and generation recipe recommends temperature 1.0, top_p 0.95 and top_k 20; separate evaluation notes use their own settings. Choose the final answer’s form explicitly and leave space for both relevant media context and generated text. These producer settings describe the released model recipe, not a promise about controls exposed by every application.\n\nRetain the VL identity when recording a result: its image and video inputs distinguish it from the text-focused Ling-3.0-flash and the finance-specialized Fin edition. Review extracted wording, counts, temporal locations and proposed interface actions against the source material. The useful final artifact is a visual analysis or action proposal that keeps its evidence and unresolved details inspectable.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Create a cut list from scene notes\n\nUse these transcribed scene notes: 00:00–00:06 unopened package; 00:06–00:18 hands assemble the stand; 00:18–00:25 stand holds a tablet; 00:25–00:35 repeated assembly close-up. Propose a 15-second instructional cut using only these intervals. Preserve the assembly-to-use order and explain any shortened or omitted segment.An ordered cut list with source intervals, chosen durations and a short editorial rationale.Check that selected durations total 15 seconds and that tablet use follows the retained assembly step.inclusionai/ling-3.0-flash-vlLing-3.0-flash-VL adds image and video understanding to inclusionAI’s hybrid reasoning model. It supports visual analysis, evidence-based reasoning and interface workflows, with 124B total parameters, 5.5B active parameters and up to 256K tokens of context.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Ling-3.0-flash-VL is inclusionAI’s native multimodal extension of Ling-3.0-flash. It combines the base model’s language, reasoning and long-context capabilities with image and video understanding. The manufacturer organizes its visual task scope into understanding, reasoning and acting: reading complex visual information, using it as evidence, and translating observations into actions in a supporting application. The model’s response is text or the tool-call representation used by that application.
The published architecture has 124B total parameters and 5.5B activated parameters per token. A vision transformer extracts image and video features, and a two-layer projector aligns them with the language representation. VideoRoPE carries both spatial positions and temporal order. The 42-layer hybrid backbone alternates Kimi Delta Attention and gated Multi-head Latent Attention in a 5:1 pattern, with sparse expert routing. The maker describes up to 256K tokens of context and publishes a 262,144-token extended-context recipe.
For visual understanding, supply a readable image and identify the required observation. The maker lists object counting, complex layouts, charts and document content among the tasks. A useful document request can ask for a field table with the supporting page or visible region, while a chart request can ask which series supports a stated comparison. Preserve the original visual material so numbers, labels and small details can be checked. An unclear region should remain unclear in the result rather than becoming a guessed value.
For reasoning with visual evidence, provide the question, relevant assumptions and the precision needed in the final answer. The model can connect a chart, diagram or screenshot to calculation and multi-step reasoning. Ask for the conclusion to identify the observations on which it depends. If the workflow includes calculation or information-retrieval tools, retain their actual results and separate them from the model’s interpretation. A visual relationship and a calibrated measurement are different kinds of evidence.
For video, preserve the order of the material and focus the question on an event, change or interval. The maker identifies event localization, long-video questions and clip-editing workflows as applications of its temporal representation. A practical editorial result can be a proposed cut list explaining which moments to retain and why. Keep that proposal connected to the source timeline; the surrounding editing application performs the changes and produces the edited media. Video understanding does not itself make the model’s text answer a new video file.
For interface tasks, include the current screenshot, the goal and the actions available to the application. Ling-3.0-flash-VL can interpret web or software interfaces and propose sequences of actions from visual information. Feed back the observed state after each operation when the next step depends on it. A useful completion record shows what changed in the interface and whether the requested result is visible, rather than treating a proposed click as an executed action.
Thinking is enabled by default in the maker’s chat template and can be disabled per request in its documented implementation with enable_thinking set to false. The client and generation recipe recommends temperature 1.0, top_p 0.95 and top_k 20; separate evaluation notes use their own settings. Choose the final answer’s form explicitly and leave space for both relevant media context and generated text. These producer settings describe the released model recipe, not a promise about controls exposed by every application.
Retain the VL identity when recording a result: its image and video inputs distinguish it from the text-focused Ling-3.0-flash and the finance-specialized Fin edition. Review extracted wording, counts, temporal locations and proposed interface actions against the source material. The useful final artifact is a visual analysis or action proposal that keeps its evidence and unresolved details inspectable.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits inclusionai/ling-3.0-flash-vl | 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 $0.00012 / 1K tokens Output · Output tokens $0.00036 / 1K tokens Input · Cache read $0.000024 / 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 $0.00012 / 1K tokens Output · Output tokens $0.00036 / 1K tokens Input · Cache read $0.000024 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "inclusionai/ling-3.0-flash-vl", "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='inclusionai/ling-3.0-flash-vl',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='inclusionai/ling-3.0-flash-vl',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 inclusionai/ling-3.0-flash-vl
Use the method paths shown above.
inclusionai/ling-3.0-flash-vlLing-3.0-flash-VL adds image and video understanding to inclusionAI’s hybrid reasoning model. It supports visual analysis, evidence-based reasoning and interface workflows, with 124B total parameters, 5.5B active parameters and up to 256K tokens of context.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Ling-3.0-flash-VL is inclusionAI’s native multimodal extension of Ling-3.0-flash. It combines the base model’s language, reasoning and long-context capabilities with image and video understanding. The manufacturer organizes its visual task scope into understanding, reasoning and acting: reading complex visual information, using it as evidence, and translating observations into actions in a supporting application. The model’s response is text or the tool-call representation used by that application.
The published architecture has 124B total parameters and 5.5B activated parameters per token. A vision transformer extracts image and video features, and a two-layer projector aligns them with the language representation. VideoRoPE carries both spatial positions and temporal order. The 42-layer hybrid backbone alternates Kimi Delta Attention and gated Multi-head Latent Attention in a 5:1 pattern, with sparse expert routing. The maker describes up to 256K tokens of context and publishes a 262,144-token extended-context recipe.
For visual understanding, supply a readable image and identify the required observation. The maker lists object counting, complex layouts, charts and document content among the tasks. A useful document request can ask for a field table with the supporting page or visible region, while a chart request can ask which series supports a stated comparison. Preserve the original visual material so numbers, labels and small details can be checked. An unclear region should remain unclear in the result rather than becoming a guessed value.
For reasoning with visual evidence, provide the question, relevant assumptions and the precision needed in the final answer. The model can connect a chart, diagram or screenshot to calculation and multi-step reasoning. Ask for the conclusion to identify the observations on which it depends. If the workflow includes calculation or information-retrieval tools, retain their actual results and separate them from the model’s interpretation. A visual relationship and a calibrated measurement are different kinds of evidence.
For video, preserve the order of the material and focus the question on an event, change or interval. The maker identifies event localization, long-video questions and clip-editing workflows as applications of its temporal representation. A practical editorial result can be a proposed cut list explaining which moments to retain and why. Keep that proposal connected to the source timeline; the surrounding editing application performs the changes and produces the edited media. Video understanding does not itself make the model’s text answer a new video file.
For interface tasks, include the current screenshot, the goal and the actions available to the application. Ling-3.0-flash-VL can interpret web or software interfaces and propose sequences of actions from visual information. Feed back the observed state after each operation when the next step depends on it. A useful completion record shows what changed in the interface and whether the requested result is visible, rather than treating a proposed click as an executed action.
Thinking is enabled by default in the maker’s chat template and can be disabled per request in its documented implementation with enable_thinking set to false. The client and generation recipe recommends temperature 1.0, top_p 0.95 and top_k 20; separate evaluation notes use their own settings. Choose the final answer’s form explicitly and leave space for both relevant media context and generated text. These producer settings describe the released model recipe, not a promise about controls exposed by every application.
Retain the VL identity when recording a result: its image and video inputs distinguish it from the text-focused Ling-3.0-flash and the finance-specialized Fin edition. Review extracted wording, counts, temporal locations and proposed interface actions against the source material. The useful final artifact is a visual analysis or action proposal that keeps its evidence and unresolved details inspectable.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits inclusionai/ling-3.0-flash-vl | 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 $0.00012 / 1K tokens Output · Output tokens $0.00036 / 1K tokens Input · Cache read $0.000024 / 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 $0.00012 / 1K tokens Output · Output tokens $0.00036 / 1K tokens Input · Cache read $0.000024 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "inclusionai/ling-3.0-flash-vl",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'inclusionai/ling-3.0-flash-vl', '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': 'inclusionai/ling-3.0-flash-vl', '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 inclusionai/ling-3.0-flash-vl
Use the method paths shown above.
Technical example in English
Create a cut list from scene notes\n\nUse these transcribed scene notes: 00:00–00:06 unopened package; 00:06–00:18 hands assemble the stand; 00:18–00:25 stand holds a tablet; 00:25–00:35 repeated assembly close-up. Propose a 15-second instructional cut using only these intervals. Preserve the assembly-to-use order and explain any shortened or omitted segment.An ordered cut list with source intervals, chosen durations and a short editorial rationale.Check that selected durations total 15 seconds and that tablet use follows the retained assembly step.