Qwen2.5-Coder-7B-Instruct is the instruction-tuned 7B-size release of Qwen's code-focused family, previously known as CodeQwen. Its central tasks are code generation, reasoning about program behavior and code repair. It receives text, including requirements and source code, and returns text that can contain an implementation, explanation or proposed change.
Coding capabilities and training
The maker describes 5.5 trillion training tokens, including source code, material that connects text with code, and synthetic examples. The family retains mathematical and general language abilities alongside its programming specialization. The release announcement distinguishes generating a program, reasoning about how a program runs, and repairing an existing implementation; these call for different inputs and different final artifacts.
For generation, provide the programming language, the function signature, input types and the expected return value. Include constraints such as whether the function may mutate its input or use an external dependency. Ask for the implementation and a short explanation of how it meets each requirement. For example, a sorting request can specify that duplicate values must be retained and the original list left unchanged, then request a function plus example calls for an empty list and a list containing repeated values.
For code reasoning, supply the exact fragment and the particular input to trace. Ask which branches execute, how the intermediate values change and what the function returns. This is more useful than an undirected request to explain a whole file: the answer connects a concrete input to a concrete path through the program. Keep any called helper functions or relevant type definitions with the fragment.
For repair, provide the failing behavior, the expected behavior and the code that determines the difference. An error message alone may leave the important condition unspecified. Request a proposed correction, an explanation of the cause and examples that distinguish the old and intended behavior. The returned patch is a text artifact; compiling it, executing it or applying it to a repository requires the surrounding development environment.
The named 7B edition
The released model has 7.61 billion parameters, including 6.53 billion non-embedding parameters, and 28 Transformer layers. It uses rotary positional embeddings, SwiGLU, RMSNorm and attention QKV bias. Its grouped-query attention has 28 query heads and 4 key/value heads. These details describe this release rather than a larger Coder edition.
The family provides separate Base and Instruct models. Instruct is aligned for conversational requests; Base is a foundation for completion and further tuning. This entry concerns the instruction-tuned 7B model. The release's examples and headline results for other sizes do not define this edition's capabilities or resource requirements.
Preparing the instruction
The model card demonstrates a conversation with separate system and user messages and the matching chat template. Place durable response rules, such as how to present the implementation and explanation, separately from the code and task. Mark which fragment is existing source, which text is a requirement and which output must be returned. This helps preserve identifiers, interfaces and behavior that the requested change must keep.
A useful developer-assistant input can contain a short module, its caller and the intended change. Request a revised function, a list of assumptions and example inputs with the expected outputs. For a generated visual artifact, specify the data and interactions to implement and ask for the resulting source text; the code-focused family also illustrates code assistants and visual artifacts. Rendering the artifact remains a separate step from generating its source.
Long-text processing
The model card lists a full context of 131,072 tokens, while the released configuration is initially set for 32,768 tokens. Processing inputs beyond that setting requires the documented YaRN extension. The example specifies a scaling factor of 4.0 and an original maximum-position setting of 32,768. The maker notes that static scaling can affect shorter-text behavior and recommends adding the extension when long contexts are needed.
Use the larger context to keep related code and requirements together, but identify the actual question: locate an incompatible call, explain a data path or propose a change within a specified interface. Include the portions that determine the behavior rather than unrelated project material. The quick-start's 512 generated tokens are an example setting; the card does not establish a separate maximum output capacity from that value.
The model's documented result is text. Its role in a code agent depends on the application supplying repository access, execution and feedback. Keep those operations separate from the model's ability to propose code and explain its behavior, and keep the exact 7B-Instruct edition and long-context settings explicit when planning a repeatable task.
", "aboutText": "Qwen2.5-Coder-7B-Instruct is the instruction-tuned 7B-size release of Qwen's code-focused family, previously known as CodeQwen. Its central tasks are code generation, reasoning about program behavior and code repair. It receives text, including requirements and source code, and returns text that can contain an implementation, explanation or proposed change.\n\nCoding capabilities and training\n\nThe maker describes 5.5 trillion training tokens, including source code, material that connects text with code, and synthetic examples. The family retains mathematical and general language abilities alongside its programming specialization. The release announcement distinguishes generating a program, reasoning about how a program runs, and repairing an existing implementation; these call for different inputs and different final artifacts.\n\nFor generation, provide the programming language, the function signature, input types and the expected return value. Include constraints such as whether the function may mutate its input or use an external dependency. Ask for the implementation and a short explanation of how it meets each requirement. For example, a sorting request can specify that duplicate values must be retained and the original list left unchanged, then request a function plus example calls for an empty list and a list containing repeated values.\n\nFor code reasoning, supply the exact fragment and the particular input to trace. Ask which branches execute, how the intermediate values change and what the function returns. This is more useful than an undirected request to explain a whole file: the answer connects a concrete input to a concrete path through the program. Keep any called helper functions or relevant type definitions with the fragment.\n\nFor repair, provide the failing behavior, the expected behavior and the code that determines the difference. An error message alone may leave the important condition unspecified. Request a proposed correction, an explanation of the cause and examples that distinguish the old and intended behavior. The returned patch is a text artifact; compiling it, executing it or applying it to a repository requires the surrounding development environment.\n\nThe named 7B edition\n\nThe released model has 7.61 billion parameters, including 6.53 billion non-embedding parameters, and 28 Transformer layers. It uses rotary positional embeddings, SwiGLU, RMSNorm and attention QKV bias. Its grouped-query attention has 28 query heads and 4 key/value heads. These details describe this release rather than a larger Coder edition.\n\nThe family provides separate Base and Instruct models. Instruct is aligned for conversational requests; Base is a foundation for completion and further tuning. This entry concerns the instruction-tuned 7B model. The release's examples and headline results for other sizes do not define this edition's capabilities or resource requirements.\n\nPreparing the instruction\n\nThe model card demonstrates a conversation with separate system and user messages and the matching chat template. Place durable response rules, such as how to present the implementation and explanation, separately from the code and task. Mark which fragment is existing source, which text is a requirement and which output must be returned. This helps preserve identifiers, interfaces and behavior that the requested change must keep.\n\nA useful developer-assistant input can contain a short module, its caller and the intended change. Request a revised function, a list of assumptions and example inputs with the expected outputs. For a generated visual artifact, specify the data and interactions to implement and ask for the resulting source text; the code-focused family also illustrates code assistants and visual artifacts. Rendering the artifact remains a separate step from generating its source.\n\nLong-text processing\n\nThe model card lists a full context of 131,072 tokens, while the released configuration is initially set for 32,768 tokens. Processing inputs beyond that setting requires the documented YaRN extension. The example specifies a scaling factor of 4.0 and an original maximum-position setting of 32,768. The maker notes that static scaling can affect shorter-text behavior and recommends adding the extension when long contexts are needed.\n\nUse the larger context to keep related code and requirements together, but identify the actual question: locate an incompatible call, explain a data path or propose a change within a specified interface. Include the portions that determine the behavior rather than unrelated project material. The quick-start's 512 generated tokens are an example setting; the card does not establish a separate maximum output capacity from that value.\n\nThe model's documented result is text. Its role in a code agent depends on the application supplying repository access, execution and feedback. Keep those operations separate from the model's ability to propose code and explain its behavior, and keep the exact 7B-Instruct edition and long-context settings explicit when planning a repeatable task.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Repair integer averaging\n\nFix this Python function: def mean(values): return sum(values) // len(values). Requirement: return the arithmetic mean as a float, preserve fractional results and raise ValueError for empty input. Provide the corrected function and tests for [1, 2], [-2, 2] and []. Explain the two distinct defects.A corrected function, three tests and separate explanations for floor division and empty-input behavior.Check that [1, 2] keeps its fractional mean and that empty input raises the specified exception.qwen2.5-coder-7b-instructQwen2.5-Coder-7B-Instruct is a text model for generating, explaining and repairing code from instructions. Its 7.61-billion-parameter release supports extended contexts up to 131,072 tokens with the documented long-context configuration.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen2.5-Coder-7B-Instruct is the instruction-tuned 7B-size release of Qwen's code-focused family, previously known as CodeQwen. Its central tasks are code generation, reasoning about program behavior and code repair. It receives text, including requirements and source code, and returns text that can contain an implementation, explanation or proposed change.
Coding capabilities and training
The maker describes 5.5 trillion training tokens, including source code, material that connects text with code, and synthetic examples. The family retains mathematical and general language abilities alongside its programming specialization. The release announcement distinguishes generating a program, reasoning about how a program runs, and repairing an existing implementation; these call for different inputs and different final artifacts.
For generation, provide the programming language, the function signature, input types and the expected return value. Include constraints such as whether the function may mutate its input or use an external dependency. Ask for the implementation and a short explanation of how it meets each requirement. For example, a sorting request can specify that duplicate values must be retained and the original list left unchanged, then request a function plus example calls for an empty list and a list containing repeated values.
For code reasoning, supply the exact fragment and the particular input to trace. Ask which branches execute, how the intermediate values change and what the function returns. This is more useful than an undirected request to explain a whole file: the answer connects a concrete input to a concrete path through the program. Keep any called helper functions or relevant type definitions with the fragment.
For repair, provide the failing behavior, the expected behavior and the code that determines the difference. An error message alone may leave the important condition unspecified. Request a proposed correction, an explanation of the cause and examples that distinguish the old and intended behavior. The returned patch is a text artifact; compiling it, executing it or applying it to a repository requires the surrounding development environment.
The named 7B edition
The released model has 7.61 billion parameters, including 6.53 billion non-embedding parameters, and 28 Transformer layers. It uses rotary positional embeddings, SwiGLU, RMSNorm and attention QKV bias. Its grouped-query attention has 28 query heads and 4 key/value heads. These details describe this release rather than a larger Coder edition.
The family provides separate Base and Instruct models. Instruct is aligned for conversational requests; Base is a foundation for completion and further tuning. This entry concerns the instruction-tuned 7B model. The release's examples and headline results for other sizes do not define this edition's capabilities or resource requirements.
Preparing the instruction
The model card demonstrates a conversation with separate system and user messages and the matching chat template. Place durable response rules, such as how to present the implementation and explanation, separately from the code and task. Mark which fragment is existing source, which text is a requirement and which output must be returned. This helps preserve identifiers, interfaces and behavior that the requested change must keep.
A useful developer-assistant input can contain a short module, its caller and the intended change. Request a revised function, a list of assumptions and example inputs with the expected outputs. For a generated visual artifact, specify the data and interactions to implement and ask for the resulting source text; the code-focused family also illustrates code assistants and visual artifacts. Rendering the artifact remains a separate step from generating its source.
Long-text processing
The model card lists a full context of 131,072 tokens, while the released configuration is initially set for 32,768 tokens. Processing inputs beyond that setting requires the documented YaRN extension. The example specifies a scaling factor of 4.0 and an original maximum-position setting of 32,768. The maker notes that static scaling can affect shorter-text behavior and recommends adding the extension when long contexts are needed.
Use the larger context to keep related code and requirements together, but identify the actual question: locate an incompatible call, explain a data path or propose a change within a specified interface. Include the portions that determine the behavior rather than unrelated project material. The quick-start's 512 generated tokens are an example setting; the card does not establish a separate maximum output capacity from that value.
The model's documented result is text. Its role in a code agent depends on the application supplying repository access, execution and feedback. Keep those operations separate from the model's ability to propose code and explain its behavior, and keep the exact 7B-Instruct edition and long-context settings explicit when planning a repeatable task.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen2.5-coder-7b-instruct | 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.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.0001 / 1K tokens Output · Output tokens $0.0001 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "qwen2.5-coder-7b-instruct", "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='qwen2.5-coder-7b-instruct',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='qwen2.5-coder-7b-instruct',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 qwen2.5-coder-7b-instruct
Use the method paths shown above.
qwen2.5-coder-7b-instructQwen2.5-Coder-7B-Instruct is a text model for generating, explaining and repairing code from instructions. Its 7.61-billion-parameter release supports extended contexts up to 131,072 tokens with the documented long-context configuration.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Qwen2.5-Coder-7B-Instruct is the instruction-tuned 7B-size release of Qwen's code-focused family, previously known as CodeQwen. Its central tasks are code generation, reasoning about program behavior and code repair. It receives text, including requirements and source code, and returns text that can contain an implementation, explanation or proposed change.
Coding capabilities and training
The maker describes 5.5 trillion training tokens, including source code, material that connects text with code, and synthetic examples. The family retains mathematical and general language abilities alongside its programming specialization. The release announcement distinguishes generating a program, reasoning about how a program runs, and repairing an existing implementation; these call for different inputs and different final artifacts.
For generation, provide the programming language, the function signature, input types and the expected return value. Include constraints such as whether the function may mutate its input or use an external dependency. Ask for the implementation and a short explanation of how it meets each requirement. For example, a sorting request can specify that duplicate values must be retained and the original list left unchanged, then request a function plus example calls for an empty list and a list containing repeated values.
For code reasoning, supply the exact fragment and the particular input to trace. Ask which branches execute, how the intermediate values change and what the function returns. This is more useful than an undirected request to explain a whole file: the answer connects a concrete input to a concrete path through the program. Keep any called helper functions or relevant type definitions with the fragment.
For repair, provide the failing behavior, the expected behavior and the code that determines the difference. An error message alone may leave the important condition unspecified. Request a proposed correction, an explanation of the cause and examples that distinguish the old and intended behavior. The returned patch is a text artifact; compiling it, executing it or applying it to a repository requires the surrounding development environment.
The named 7B edition
The released model has 7.61 billion parameters, including 6.53 billion non-embedding parameters, and 28 Transformer layers. It uses rotary positional embeddings, SwiGLU, RMSNorm and attention QKV bias. Its grouped-query attention has 28 query heads and 4 key/value heads. These details describe this release rather than a larger Coder edition.
The family provides separate Base and Instruct models. Instruct is aligned for conversational requests; Base is a foundation for completion and further tuning. This entry concerns the instruction-tuned 7B model. The release's examples and headline results for other sizes do not define this edition's capabilities or resource requirements.
Preparing the instruction
The model card demonstrates a conversation with separate system and user messages and the matching chat template. Place durable response rules, such as how to present the implementation and explanation, separately from the code and task. Mark which fragment is existing source, which text is a requirement and which output must be returned. This helps preserve identifiers, interfaces and behavior that the requested change must keep.
A useful developer-assistant input can contain a short module, its caller and the intended change. Request a revised function, a list of assumptions and example inputs with the expected outputs. For a generated visual artifact, specify the data and interactions to implement and ask for the resulting source text; the code-focused family also illustrates code assistants and visual artifacts. Rendering the artifact remains a separate step from generating its source.
Long-text processing
The model card lists a full context of 131,072 tokens, while the released configuration is initially set for 32,768 tokens. Processing inputs beyond that setting requires the documented YaRN extension. The example specifies a scaling factor of 4.0 and an original maximum-position setting of 32,768. The maker notes that static scaling can affect shorter-text behavior and recommends adding the extension when long contexts are needed.
Use the larger context to keep related code and requirements together, but identify the actual question: locate an incompatible call, explain a data path or propose a change within a specified interface. Include the portions that determine the behavior rather than unrelated project material. The quick-start's 512 generated tokens are an example setting; the card does not establish a separate maximum output capacity from that value.
The model's documented result is text. Its role in a code agent depends on the application supplying repository access, execution and feedback. Keep those operations separate from the model's ability to propose code and explain its behavior, and keep the exact 7B-Instruct edition and long-context settings explicit when planning a repeatable task.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits qwen2.5-coder-7b-instruct | 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.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.0001 / 1K tokens Output · Output tokens $0.0001 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "qwen2.5-coder-7b-instruct",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'qwen2.5-coder-7b-instruct', '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': 'qwen2.5-coder-7b-instruct', '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 qwen2.5-coder-7b-instruct
Use the method paths shown above.
Technical example in English
Repair integer averaging\n\nFix this Python function: def mean(values): return sum(values) // len(values). Requirement: return the arithmetic mean as a float, preserve fractional results and raise ValueError for empty input. Provide the corrected function and tests for [1, 2], [-2, 2] and []. Explain the two distinct defects.A corrected function, three tests and separate explanations for floor division and empty-input behavior.Check that [1, 2] keeps its fractional mean and that empty input raises the specified exception.