orch-cli 0.88.4

Orch, the agent orchestration engine: runs coding agents on tasks and cron jobs
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

/// Token usage for an agent run.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Default)]
pub struct TokenUsage {
    pub input_tokens: u64,
    pub output_tokens: u64,
}

impl TokenUsage {
    pub fn total_tokens(self) -> u64 {
        self.input_tokens.saturating_add(self.output_tokens)
    }
}

/// Per-1M token pricing in USD.
#[derive(Debug, Clone, Copy, PartialEq)]
pub struct ModelPricing {
    pub input_per_million_usd: f64,
    pub output_per_million_usd: f64,
}

impl ModelPricing {
    pub fn estimate_cost_usd(self, usage: TokenUsage) -> CostEstimate {
        let input_cost = (usage.input_tokens as f64 / 1_000_000.0) * self.input_per_million_usd;
        let output_cost = (usage.output_tokens as f64 / 1_000_000.0) * self.output_per_million_usd;
        CostEstimate {
            input_cost_usd: input_cost,
            output_cost_usd: output_cost,
            total_cost_usd: input_cost + output_cost,
        }
    }
}

/// Cost estimate in USD.
#[derive(Debug, Clone, Copy, PartialEq, Default)]
pub struct CostEstimate {
    pub input_cost_usd: f64,
    pub output_cost_usd: f64,
    pub total_cost_usd: f64,
}
/// Zero-cost pricing (subscription-based or free-tier models).
const FREE: ModelPricing = ModelPricing {
    input_per_million_usd: 0.0,
    output_per_million_usd: 0.0,
};

/// Resolve model pricing using a built-in table and normalized model aliases.
pub fn pricing_for_model(model: &str) -> ModelPricing {
    let normalized = model.trim().to_lowercase();

    // GitHub Copilot subscription models — billed to Copilot account, not per-token.
    if normalized.starts_with("github-copilot/") {
        return FREE;
    }

    // Free-tier models (e.g. minimax-m2.5-free, nemotron-3-super-free).
    if normalized.contains("-free") || normalized.ends_with("free") {
        return FREE;
    }

    // DeepSeek models (e.g. deepseek-r1, deepseek-v3).
    if normalized.starts_with("deepseek") {
        return ModelPricing {
            input_per_million_usd: 0.55,
            output_per_million_usd: 2.19,
        };
    }

    // OpenAI models
    if normalized == "o3" {
        return ModelPricing {
            input_per_million_usd: 2.0,
            output_per_million_usd: 8.0,
        };
    }
    if normalized == "o4-mini" || normalized.contains("gpt-4.1-mini") {
        return ModelPricing {
            input_per_million_usd: 0.15,
            output_per_million_usd: 0.6,
        };
    }
    if normalized.contains("gpt-4.1") && !normalized.contains("mini") {
        return ModelPricing {
            input_per_million_usd: 2.0,
            output_per_million_usd: 8.0,
        };
    }
    // Codex v5 mini variants (gpt-5.1-codex-mini, gpt-5.4-mini, etc.).
    if normalized.starts_with("gpt-5") && normalized.contains("mini") {
        return ModelPricing {
            input_per_million_usd: 0.15,
            output_per_million_usd: 0.6,
        };
    }
    // Codex v5 full variants (gpt-5.2-codex, gpt-5.3-codex, etc.).
    if normalized.starts_with("gpt-5") {
        return ModelPricing {
            input_per_million_usd: 2.0,
            output_per_million_usd: 8.0,
        };
    }

    // Claude models matched by family substring.
    if normalized.contains("opus") {
        return ModelPricing {
            input_per_million_usd: 15.0,
            output_per_million_usd: 75.0,
        };
    }
    if normalized.contains("sonnet") {
        return ModelPricing {
            input_per_million_usd: 3.0,
            output_per_million_usd: 15.0,
        };
    }
    if normalized.contains("haiku") {
        return ModelPricing {
            input_per_million_usd: 0.8,
            output_per_million_usd: 4.0,
        };
    }

    // Fallback baseline when model is unknown.
    ModelPricing {
        input_per_million_usd: 1.0,
        output_per_million_usd: 4.0,
    }
}