xai-openapi 0.1.1

Rust types for the xAI API (Grok models)
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155

//! Token usage tracking types for xAI API responses.

use serde::{Deserialize, Serialize};

#[allow(unused_imports)]
use crate::prelude::*;

/// Token usage information for chat completions.
#[derive(Clone, Debug, Default, PartialEq, Serialize, Deserialize)]
pub struct Usage {
    /// Total prompt token used.
    pub prompt_tokens: i32,

    /// Total completion token used.
    pub completion_tokens: i32,

    /// Total token used, the sum of prompt token and completion token amount.
    pub total_tokens: i32,

    /// Breakdown of prompt token usage of different types.
    pub prompt_tokens_details: PromptUsageDetail,

    /// Breakdown of completion token usage of different types.
    pub completion_tokens_details: CompletionUsageDetail,

    /// Number of individual live search source used.
    pub num_sources_used: i32,
}

/// Details of prompt usage.
#[derive(Clone, Debug, Default, PartialEq, Serialize, Deserialize)]
pub struct PromptUsageDetail {
    /// Text prompt token used.
    pub text_tokens: i32,

    /// Audio prompt token used.
    pub audio_tokens: i32,

    /// Image prompt token used.
    pub image_tokens: i32,

    /// Token cached by xAI from previous requests and reused for this request.
    pub cached_tokens: i32,
}

/// Details of completion usage.
#[derive(Clone, Debug, Default, PartialEq, Serialize, Deserialize)]
pub struct CompletionUsageDetail {
    /// Tokens generated by the model for reasoning.
    pub reasoning_tokens: i32,

    /// Audio input tokens generated by the model.
    pub audio_tokens: i32,

    /// The number of tokens in the prediction that appeared in the completion.
    pub accepted_prediction_tokens: i32,

    /// The number of tokens in the prediction that did not appear in the completion.
    pub rejected_prediction_tokens: i32,
}

/// Token usage information for the Responses API.
#[derive(Clone, Debug, Default, PartialEq, Serialize, Deserialize)]
pub struct ModelUsage {
    /// Number of input tokens used.
    pub input_tokens: i32,

    /// Breakdown of the input tokens.
    pub input_tokens_details: InputTokensDetails,

    /// Number of output tokens used.
    pub output_tokens: i32,

    /// Breakdown of the output tokens.
    pub output_tokens_details: OutputTokensDetails,

    /// Total tokens used.
    pub total_tokens: i32,

    /// Number of sources used (for live search).
    pub num_sources_used: i32,

    /// Number of server side tools used.
    pub num_server_side_tools_used: i32,

    /// Cost in nano US dollars for this request.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub cost_in_nano_usd: Option<i64>,

    /// Details about the server side tool usage.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub server_side_tool_usage_details: Option<ServerSideToolUsageDetails>,
}

/// Input tokens details.
#[derive(Clone, Debug, Default, PartialEq, Serialize, Deserialize)]
pub struct InputTokensDetails {
    /// Token cached by xAI from previous requests and reused for this request.
    pub cached_tokens: i32,
}

/// Output tokens details.
#[derive(Clone, Debug, Default, PartialEq, Serialize, Deserialize)]
pub struct OutputTokensDetails {
    /// Tokens generated by the model for reasoning.
    pub reasoning_tokens: i32,
}

/// Details about the server side tool usage.
#[derive(Clone, Debug, Default, PartialEq, Serialize, Deserialize)]
pub struct ServerSideToolUsageDetails {
    /// Number of web search calls.
    pub web_search_calls: i32,

    /// Number of X search calls.
    pub x_search_calls: i32,

    /// Number of code interpreter calls.
    pub code_interpreter_calls: i32,

    /// Number of file search calls.
    pub file_search_calls: i32,

    /// Number of MCP calls.
    pub mcp_calls: i32,

    /// Number of document search calls.
    pub document_search_calls: i32,
}

/// Token usage information for embeddings.
#[derive(Clone, Debug, Default, PartialEq, Serialize, Deserialize)]
pub struct EmbeddingUsage {
    /// Prompt token used.
    pub prompt_tokens: i32,

    /// Total token used.
    pub total_tokens: i32,
}

/// Token usage information for the Messages API (Anthropic-compatible).
#[derive(Clone, Debug, Default, PartialEq, Serialize, Deserialize)]
pub struct MessageUsage {
    /// Number of input tokens used.
    pub input_tokens: i32,

    /// (Unsupported) Number of tokens written to the cache when creating a new entry.
    pub cache_creation_input_tokens: i32,

    /// Number of tokens retrieved from the cache for this request.
    pub cache_read_input_tokens: i32,

    /// Number of output tokens used.
    pub output_tokens: i32,
}