Basic Parameters
| Parameter | Description |
|---|---|
| Anthropic Format | Select to use an Anthropic model. Note: This parameter is only available for Anthropic models like Claude Sonnet or Claude Opus. It won’t work for other models such as GPT-4o or DeepSeek. |
| Max Tokens | The maximum number of tokens to generate in the completion. |
| Messages | The conversation messages to generate a completion for. For example: |
| Model | The deployment name of the model to use. Note: To use an Anthropic model, you must also use the Anthropic Format parameter. |
| Project Name | The name of the Microsoft Foundry project. |
Advanced Parameters
| Parameter | Description |
|---|---|
| Additional Parameters | A JSON object for additional body parameters. Values specified in this parameter will override equivalent parameters. For example: |
Example Output
{
"choices": [
{
"content_filter_results": {
"hate": {
"filtered": false,
"severity": "safe"
},
"protected_material_code": {
"detected": false,
"filtered": false
},
"protected_material_text": {
"detected": false,
"filtered": false
},
"self_harm": {
"filtered": false,
"severity": "safe"
},
"sexual": {
"filtered": false,
"severity": "safe"
},
"violence": {
"filtered": false,
"severity": "safe"
}
},
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"message": {
"annotations": [],
"content": "The Eiffel Tower is great for a few reasons—beyond just being famous:\n\n- **Views you can't get anywhere else:** From the top (or even the mid-level platforms), you get a sweeping panorama of Paris.\n- **A true \"Paris icon\" moment:** It's one of the most recognizable structures in the world.\n- **Architecture + engineering:** When it was built it was considered a major engineering achievement.\n- **It changes with the light:** The tower looks different at each time of day. At night it's often lit up in a way that makes it feel magical.",
"refusal": null,
"role": "assistant"
}
}
],
"created": 1779624259,
"id": "chatcmpl-Dj1r1Fbkh12OyeQWi0x6PdRwOCsrM",
"model": "gpt-5.4-nano-2026-03-17",
"object": "chat.completion",
"prompt_filter_results": [
{
"prompt_index": 0,
"content_filter_results": {
"hate": {
"filtered": false,
"severity": "safe"
},
"jailbreak": {
"detected": false,
"filtered": false
},
"self_harm": {
"filtered": false,
"severity": "safe"
},
"sexual": {
"filtered": false,
"severity": "safe"
},
"violence": {
"filtered": false,
"severity": "safe"
}
}
}
],
"service_tier": "default",
"system_fingerprint": null,
"usage": {
"completion_tokens": 260,
"prompt_tokens": 203,
"total_tokens": 463
}
}
Workflow Library Example
Chat Completion with Microsoft Foundry and Send Results Via Email