Gemini 2.5 Pro Preview 06-05 is the June preview edition of Google’s Gemini 2.5 Pro reasoning model. The release builds on the preceding preview and highlights coding, mathematics, science, knowledge and reasoning tasks. Google also identifies an improvement in response style and structure, including more creative and better-formatted answers. Retaining 06-05 matters when a task refers to this particular preview rather than a later stable or differently dated model.
The working result is text: a code proposal, explanation, analytical conclusion or prepared document. The documented Pro family works with text, images, audio and PDF as source material. A written task can connect information from those inputs to a specific question. For a technical document, identify the relevant definitions, table or diagram and explain what the answer should establish. For a recording, distinguish a requested transcript, summary and interpretation instead of treating them as one operation.
Reasoning is central to the Pro line’s purpose. The June announcement adds thinking budgets to give developers more control over the amount of analysis, and the official release notes explicitly identify expanded thinking support for gemini-2.5-pro-preview-06-05. Choose the depth needed for the actual problem and specify a final result that can be checked. A budget for reasoning and a requested answer length are different controls; a short final response can still require substantial analysis before it is produced.
For programming, include the relevant files or function, the language, expected behavior and a concrete input that demonstrates the problem. Name the interfaces and surrounding behavior that must remain unchanged. A useful final artifact is a proposed implementation with an explanation of the chosen condition and examples showing what needs to be verified. If comparing approaches, give the same input cases and decision criteria to each one so the answer addresses the real trade-off rather than a general discussion of algorithms.
For mathematics or scientific material, provide the full statement, definitions, permitted assumptions and the result to establish. Preserve numerical notation and units. Ask the model to explain why the chosen transformations follow from the supplied conditions and to separate the final result from alternatives it considered. When reviewing a proposed solution, provide both the original problem and the disputed step. Check the resulting calculation or claim with the actual source evidence instead of relying on how confidently it is phrased.
The maker describes the Pro family for long-context analysis of datasets, codebases and documents. Prepare that context with source labels, relevant excerpts and a clear priority rule when documents conflict. Set the task’s completion criterion: a requirement comparison, a source-based answer, a revised function or an explanation for a particular audience. Leave room for the answer instead of filling the entire request with unrelated history. Preserve the same input version and exact preview name when revisiting a case so a change in the result can be interpreted meaningfully.
The Gemini 2.5 Pro family documentation includes structured outputs, function calling, code execution, search grounding and caching. These are producer-family capabilities rather than an automatic set of actions in every surrounding application. Supply a schema when machine-readable output is needed, validate its fields and distinguish the facts provided by a tool from a proposed operation. An application defines and executes custom tools, then returns their results for the model’s next step. A generated code snippet or function request is not evidence that it was run successfully.
The June release’s improved style and structure are useful when an explanation becomes a report or editorial draft. State the audience, terminology, headings and length, and identify what must be retained from the original. Ask for uncertain or missing information to be identified rather than filled with invented details. Inspect factual claims against the supplied material, validate structured records and test code in the intended environment. The useful outcome is a reviewed text artifact with its source context and 06-05 identity retained, while later model names, service settings and media-generation capabilities remain separate choices.
", "aboutText": "Gemini 2.5 Pro Preview 06-05 is the June preview edition of Google’s Gemini 2.5 Pro reasoning model. The release builds on the preceding preview and highlights coding, mathematics, science, knowledge and reasoning tasks. Google also identifies an improvement in response style and structure, including more creative and better-formatted answers. Retaining 06-05 matters when a task refers to this particular preview rather than a later stable or differently dated model.\n\nThe working result is text: a code proposal, explanation, analytical conclusion or prepared document. The documented Pro family works with text, images, audio and PDF as source material. A written task can connect information from those inputs to a specific question. For a technical document, identify the relevant definitions, table or diagram and explain what the answer should establish. For a recording, distinguish a requested transcript, summary and interpretation instead of treating them as one operation.\n\nReasoning is central to the Pro line’s purpose. The June announcement adds thinking budgets to give developers more control over the amount of analysis, and the official release notes explicitly identify expanded thinking support for gemini-2.5-pro-preview-06-05. Choose the depth needed for the actual problem and specify a final result that can be checked. A budget for reasoning and a requested answer length are different controls; a short final response can still require substantial analysis before it is produced.\n\nFor programming, include the relevant files or function, the language, expected behavior and a concrete input that demonstrates the problem. Name the interfaces and surrounding behavior that must remain unchanged. A useful final artifact is a proposed implementation with an explanation of the chosen condition and examples showing what needs to be verified. If comparing approaches, give the same input cases and decision criteria to each one so the answer addresses the real trade-off rather than a general discussion of algorithms.\n\nFor mathematics or scientific material, provide the full statement, definitions, permitted assumptions and the result to establish. Preserve numerical notation and units. Ask the model to explain why the chosen transformations follow from the supplied conditions and to separate the final result from alternatives it considered. When reviewing a proposed solution, provide both the original problem and the disputed step. Check the resulting calculation or claim with the actual source evidence instead of relying on how confidently it is phrased.\n\nThe maker describes the Pro family for long-context analysis of datasets, codebases and documents. Prepare that context with source labels, relevant excerpts and a clear priority rule when documents conflict. Set the task’s completion criterion: a requirement comparison, a source-based answer, a revised function or an explanation for a particular audience. Leave room for the answer instead of filling the entire request with unrelated history. Preserve the same input version and exact preview name when revisiting a case so a change in the result can be interpreted meaningfully.\n\nThe Gemini 2.5 Pro family documentation includes structured outputs, function calling, code execution, search grounding and caching. These are producer-family capabilities rather than an automatic set of actions in every surrounding application. Supply a schema when machine-readable output is needed, validate its fields and distinguish the facts provided by a tool from a proposed operation. An application defines and executes custom tools, then returns their results for the model’s next step. A generated code snippet or function request is not evidence that it was run successfully.\n\nThe June release’s improved style and structure are useful when an explanation becomes a report or editorial draft. State the audience, terminology, headings and length, and identify what must be retained from the original. Ask for uncertain or missing information to be identified rather than filled with invented details. Inspect factual claims against the supplied material, validate structured records and test code in the intended environment. The useful outcome is a reviewed text artifact with its source context and 06-05 identity retained, while later model names, service settings and media-generation capabilities remain separate choices.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Check a unit-sensitive calculation\n\nA pump transfers 18 litres per minute into an empty tank. The tank holds 2.7 cubic metres. Ignore losses and assume a constant rate. Calculate the fill time in minutes and hours, show the unit conversion and explain how the result changes if the actual rate is 15 litres per minute.A unit conversion, both fill-time calculations and a concise comparison.Check that cubic metres are converted to litres before dividing and that a lower flow rate produces a longer fill time.google/gemini-2.5-pro-previewGemini 2.5 Pro Preview 06-05 is the June preview for reasoning-intensive code, mathematics, science and document tasks. Google’s release highlights expanded thinking control and improved response style and structure, while the exact 06-05 identity remains distinct.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 2.5 Pro Preview 06-05 is the June preview edition of Google’s Gemini 2.5 Pro reasoning model. The release builds on the preceding preview and highlights coding, mathematics, science, knowledge and reasoning tasks. Google also identifies an improvement in response style and structure, including more creative and better-formatted answers. Retaining 06-05 matters when a task refers to this particular preview rather than a later stable or differently dated model.
The working result is text: a code proposal, explanation, analytical conclusion or prepared document. The documented Pro family works with text, images, audio and PDF as source material. A written task can connect information from those inputs to a specific question. For a technical document, identify the relevant definitions, table or diagram and explain what the answer should establish. For a recording, distinguish a requested transcript, summary and interpretation instead of treating them as one operation.
Reasoning is central to the Pro line’s purpose. The June announcement adds thinking budgets to give developers more control over the amount of analysis, and the official release notes explicitly identify expanded thinking support for gemini-2.5-pro-preview-06-05. Choose the depth needed for the actual problem and specify a final result that can be checked. A budget for reasoning and a requested answer length are different controls; a short final response can still require substantial analysis before it is produced.
For programming, include the relevant files or function, the language, expected behavior and a concrete input that demonstrates the problem. Name the interfaces and surrounding behavior that must remain unchanged. A useful final artifact is a proposed implementation with an explanation of the chosen condition and examples showing what needs to be verified. If comparing approaches, give the same input cases and decision criteria to each one so the answer addresses the real trade-off rather than a general discussion of algorithms.
For mathematics or scientific material, provide the full statement, definitions, permitted assumptions and the result to establish. Preserve numerical notation and units. Ask the model to explain why the chosen transformations follow from the supplied conditions and to separate the final result from alternatives it considered. When reviewing a proposed solution, provide both the original problem and the disputed step. Check the resulting calculation or claim with the actual source evidence instead of relying on how confidently it is phrased.
The maker describes the Pro family for long-context analysis of datasets, codebases and documents. Prepare that context with source labels, relevant excerpts and a clear priority rule when documents conflict. Set the task’s completion criterion: a requirement comparison, a source-based answer, a revised function or an explanation for a particular audience. Leave room for the answer instead of filling the entire request with unrelated history. Preserve the same input version and exact preview name when revisiting a case so a change in the result can be interpreted meaningfully.
The Gemini 2.5 Pro family documentation includes structured outputs, function calling, code execution, search grounding and caching. These are producer-family capabilities rather than an automatic set of actions in every surrounding application. Supply a schema when machine-readable output is needed, validate its fields and distinguish the facts provided by a tool from a proposed operation. An application defines and executes custom tools, then returns their results for the model’s next step. A generated code snippet or function request is not evidence that it was run successfully.
The June release’s improved style and structure are useful when an explanation becomes a report or editorial draft. State the audience, terminology, headings and length, and identify what must be retained from the original. Ask for uncertain or missing information to be identified rather than filled with invented details. Inspect factual claims against the supplied material, validate structured records and test code in the intended environment. The useful outcome is a reviewed text artifact with its source context and 06-05 identity retained, while later model names, service settings and media-generation capabilities remain separate choices.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits google/gemini-2.5-pro-preview | 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 $0.0025 / 1K tokens Output · Output tokens $0.02 / 1K tokens Input · Cache read $0.00025 / 1K tokens Input · Cache write $0.00075 / 1K tokens Input · Cache write, 1 hour — / 1K tokens Output · Reasoning output tokens $0.02 / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and including200,000 | Charge Input · Input tokens $0.0025 / 1K tokens Output · Output tokens $0.02 / 1K tokens Input · Cache read $0.00025 / 1K tokens Input · Cache write $0.00075 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 2 | Rate schedule— | Context tokens, more than200,000 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.005 / 1K tokens Output · Output tokens $0.03 / 1K tokens Input · Cache read $0.0005 / 1K tokens Input · Cache write $0.00075 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "google/gemini-2.5-pro-preview", "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='google/gemini-2.5-pro-preview',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='google/gemini-2.5-pro-preview',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 google/gemini-2.5-pro-preview
Use the method paths shown above.
google/gemini-2.5-pro-previewGemini 2.5 Pro Preview 06-05 is the June preview for reasoning-intensive code, mathematics, science and document tasks. Google’s release highlights expanded thinking control and improved response style and structure, while the exact 06-05 identity remains distinct.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Gemini 2.5 Pro Preview 06-05 is the June preview edition of Google’s Gemini 2.5 Pro reasoning model. The release builds on the preceding preview and highlights coding, mathematics, science, knowledge and reasoning tasks. Google also identifies an improvement in response style and structure, including more creative and better-formatted answers. Retaining 06-05 matters when a task refers to this particular preview rather than a later stable or differently dated model.
The working result is text: a code proposal, explanation, analytical conclusion or prepared document. The documented Pro family works with text, images, audio and PDF as source material. A written task can connect information from those inputs to a specific question. For a technical document, identify the relevant definitions, table or diagram and explain what the answer should establish. For a recording, distinguish a requested transcript, summary and interpretation instead of treating them as one operation.
Reasoning is central to the Pro line’s purpose. The June announcement adds thinking budgets to give developers more control over the amount of analysis, and the official release notes explicitly identify expanded thinking support for gemini-2.5-pro-preview-06-05. Choose the depth needed for the actual problem and specify a final result that can be checked. A budget for reasoning and a requested answer length are different controls; a short final response can still require substantial analysis before it is produced.
For programming, include the relevant files or function, the language, expected behavior and a concrete input that demonstrates the problem. Name the interfaces and surrounding behavior that must remain unchanged. A useful final artifact is a proposed implementation with an explanation of the chosen condition and examples showing what needs to be verified. If comparing approaches, give the same input cases and decision criteria to each one so the answer addresses the real trade-off rather than a general discussion of algorithms.
For mathematics or scientific material, provide the full statement, definitions, permitted assumptions and the result to establish. Preserve numerical notation and units. Ask the model to explain why the chosen transformations follow from the supplied conditions and to separate the final result from alternatives it considered. When reviewing a proposed solution, provide both the original problem and the disputed step. Check the resulting calculation or claim with the actual source evidence instead of relying on how confidently it is phrased.
The maker describes the Pro family for long-context analysis of datasets, codebases and documents. Prepare that context with source labels, relevant excerpts and a clear priority rule when documents conflict. Set the task’s completion criterion: a requirement comparison, a source-based answer, a revised function or an explanation for a particular audience. Leave room for the answer instead of filling the entire request with unrelated history. Preserve the same input version and exact preview name when revisiting a case so a change in the result can be interpreted meaningfully.
The Gemini 2.5 Pro family documentation includes structured outputs, function calling, code execution, search grounding and caching. These are producer-family capabilities rather than an automatic set of actions in every surrounding application. Supply a schema when machine-readable output is needed, validate its fields and distinguish the facts provided by a tool from a proposed operation. An application defines and executes custom tools, then returns their results for the model’s next step. A generated code snippet or function request is not evidence that it was run successfully.
The June release’s improved style and structure are useful when an explanation becomes a report or editorial draft. State the audience, terminology, headings and length, and identify what must be retained from the original. Ask for uncertain or missing information to be identified rather than filled with invented details. Inspect factual claims against the supplied material, validate structured records and test code in the intended environment. The useful outcome is a reviewed text artifact with its source context and 06-05 identity retained, while later model names, service settings and media-generation capabilities remain separate choices.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits google/gemini-2.5-pro-preview | 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 $0.0025 / 1K tokens Output · Output tokens $0.02 / 1K tokens Input · Cache read $0.00025 / 1K tokens Input · Cache write $0.00075 / 1K tokens Input · Cache write, 1 hour — / 1K tokens Output · Reasoning output tokens $0.02 / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and including200,000 | Charge Input · Input tokens $0.0025 / 1K tokens Output · Output tokens $0.02 / 1K tokens Input · Cache read $0.00025 / 1K tokens Input · Cache write $0.00075 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 2 | Rate schedule— | Context tokens, more than200,000 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.005 / 1K tokens Output · Output tokens $0.03 / 1K tokens Input · Cache read $0.0005 / 1K tokens Input · Cache write $0.00075 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "google/gemini-2.5-pro-preview",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'google/gemini-2.5-pro-preview', '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': 'google/gemini-2.5-pro-preview', '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 google/gemini-2.5-pro-preview
Use the method paths shown above.
Technical example in English
Check a unit-sensitive calculation\n\nA pump transfers 18 litres per minute into an empty tank. The tank holds 2.7 cubic metres. Ignore losses and assume a constant rate. Calculate the fill time in minutes and hours, show the unit conversion and explain how the result changes if the actual rate is 15 litres per minute.A unit conversion, both fill-time calculations and a concise comparison.Check that cubic metres are converted to litres before dividing and that a lower flow rate produces a longer fill time.