mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
473 lines
17 KiB
JSON
473 lines
17 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "https://api.openai.com/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "gpt-4o",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "How many experts does the Llama 4 Maverick model have?"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "",
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": "call_nDPo5gVrtB8KHxfXpmWGvOfh",
|
|
"type": "function",
|
|
"function": {
|
|
"name": "web_search",
|
|
"arguments": "{\"query\":\"Llama 4 Maverick model number of experts\"}"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"role": "tool",
|
|
"tool_call_id": "call_nDPo5gVrtB8KHxfXpmWGvOfh",
|
|
"content": "{\"query\": \"Llama 4 Maverick model number of experts\", \"top_k\": [{\"title\": \"Llama 4 Maverick - API, Providers, Stats\", \"url\": \"https://openrouter.ai/meta-llama/llama-4-maverick\", \"content\": \"Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). Specifically, it combines features from previous Llama Guard models, providing content moderation for English and multiple supported languages, along with enhanced capabilities to handle mixed text-and-image prompts, including multiple images. The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization.\", \"score\": 0.9165366, \"raw_content\": null}, {\"title\": \"meta-llama/Llama-4-Maverick-17B-128E\", \"url\": \"https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E\", \"content\": \"5 Apr 2025 \\u2014 ... model with 16 experts, and Llama 4 Maverick, a 17 billion parameter model with 128 experts . Model developer: Meta. Model Architecture: The\", \"score\": 0.9154545, \"raw_content\": null}, {\"title\": \"Inside Llama 4: How Meta's New Open-Source AI Crushes ...\", \"url\": \"https://machine-learning-made-simple.medium.com/inside-llama-4-how-metas-new-open-source-ai-crushes-gpt-4o-and-gemini-e3265f914599\", \"content\": \"Llama 4 Maverick, a 17 billion active parameter model with 128 experts , is the best multimodal model in its class, beating GPT-4o and Gemini 2.0 Flash.\", \"score\": 0.9134376, \"raw_content\": null}, {\"title\": \"The Llama 4 herd: The beginning of a new era of natively ...\", \"url\": \"https://ai.meta.com/blog/llama-4-multimodal-intelligence/\", \"content\": \"* Llama 4 Scout, a 17 billion active parameter model with 16 experts, is the best multimodal model in the world in its class and is more powerful than all previous generation Llama models, while fitting in a single NVIDIA H100 GPU. * Llama 4 Maverick, a 17 billion active parameter model with 128 experts, is the best multimodal model in its class, beating GPT-4o and Gemini 2.0 Flash across a broad range of widely reported benchmarks, while achieving comparable results to the new DeepSeek v3 on reasoning and coding\\u2014at less than half the active parameters. We\\u2019re introducing Llama 4 Scout and Llama 4 Maverick, the first open-weight natively multimodal models with unprecedented context length support and our first built using a mixture-of-experts (MoE) architecture.\", \"score\": 0.91156644, \"raw_content\": null}, {\"title\": \"Llama (language model)\", \"url\": \"https://en.wikipedia.org/wiki/Llama_(language_model)\", \"content\": \"Llama 4 \\u00b7 Scout: 17 billion active parameter model with 16 experts , context window of 10M, with 109B parameters in total. \\u00b7 Maverick: 17 billion active parameter\", \"score\": 0.89166987, \"raw_content\": null}]}"
|
|
}
|
|
],
|
|
"response_format": {
|
|
"type": "text"
|
|
},
|
|
"stream": true,
|
|
"tools": [
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "web_search",
|
|
"description": "Search the web for information",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"query": {
|
|
"type": "string",
|
|
"description": "The query to search for"
|
|
}
|
|
},
|
|
"required": [
|
|
"query"
|
|
]
|
|
}
|
|
}
|
|
}
|
|
]
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "gpt-4o"
|
|
},
|
|
"response": {
|
|
"body": [
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "chatcmpl-CEJFVQSe4g0BQEfunL3nWjA3Uenlb",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 1757526621,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_1827dd0c55",
|
|
"usage": null,
|
|
"obfuscation": "nT1qN3AiklK"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "chatcmpl-CEJFVQSe4g0BQEfunL3nWjA3Uenlb",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "The",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 1757526621,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_1827dd0c55",
|
|
"usage": null,
|
|
"obfuscation": "Gq5tUvNkna"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "chatcmpl-CEJFVQSe4g0BQEfunL3nWjA3Uenlb",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " L",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 1757526621,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_1827dd0c55",
|
|
"usage": null,
|
|
"obfuscation": "yfrAHu0mRGC"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "chatcmpl-CEJFVQSe4g0BQEfunL3nWjA3Uenlb",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "lama",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 1757526621,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_1827dd0c55",
|
|
"usage": null,
|
|
"obfuscation": "U0lvRQHwj"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "chatcmpl-CEJFVQSe4g0BQEfunL3nWjA3Uenlb",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " ",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 1757526621,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_1827dd0c55",
|
|
"usage": null,
|
|
"obfuscation": "DAawgtWIf5PZ"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "chatcmpl-CEJFVQSe4g0BQEfunL3nWjA3Uenlb",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "4",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 1757526621,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_1827dd0c55",
|
|
"usage": null,
|
|
"obfuscation": "4pinp4GLbSNG"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "chatcmpl-CEJFVQSe4g0BQEfunL3nWjA3Uenlb",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " Maver",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 1757526621,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_1827dd0c55",
|
|
"usage": null,
|
|
"obfuscation": "Oc7F8h5"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "chatcmpl-CEJFVQSe4g0BQEfunL3nWjA3Uenlb",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "ick",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 1757526621,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_1827dd0c55",
|
|
"usage": null,
|
|
"obfuscation": "H1uCX2bRG5"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "chatcmpl-CEJFVQSe4g0BQEfunL3nWjA3Uenlb",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " model",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 1757526621,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_1827dd0c55",
|
|
"usage": null,
|
|
"obfuscation": "vot8eYp"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "chatcmpl-CEJFVQSe4g0BQEfunL3nWjA3Uenlb",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " has",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 1757526621,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_1827dd0c55",
|
|
"usage": null,
|
|
"obfuscation": "3I6RHzAfY"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "chatcmpl-CEJFVQSe4g0BQEfunL3nWjA3Uenlb",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " ",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 1757526621,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_1827dd0c55",
|
|
"usage": null,
|
|
"obfuscation": "hHB5yLVAXCd2"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "chatcmpl-CEJFVQSe4g0BQEfunL3nWjA3Uenlb",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "128",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 1757526621,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_1827dd0c55",
|
|
"usage": null,
|
|
"obfuscation": "Gsn8ukZFoE"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "chatcmpl-CEJFVQSe4g0BQEfunL3nWjA3Uenlb",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " experts",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 1757526621,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_1827dd0c55",
|
|
"usage": null,
|
|
"obfuscation": "m8uLf"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "chatcmpl-CEJFVQSe4g0BQEfunL3nWjA3Uenlb",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": ".",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 1757526621,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_1827dd0c55",
|
|
"usage": null,
|
|
"obfuscation": "gSsC01woUk29"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "chatcmpl-CEJFVQSe4g0BQEfunL3nWjA3Uenlb",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 1757526621,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_1827dd0c55",
|
|
"usage": null,
|
|
"obfuscation": "WAsLXnB"
|
|
}
|
|
}
|
|
],
|
|
"is_streaming": true
|
|
}
|
|
}
|