mobius 0.15.50

A small, modular Rust framework for building coding agents
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

# Provider-owned model catalog and token prices.
default_model = "gpt-6-sol"

[[models]]
id = "gpt-6-sol"
label = "6 Sol"
description = "Complex coding and agentic workflows"
default_reasoning = "medium"
context_window = 1050000
tool_discovery = "native"

[[models.reasoning]]
id = "none"
label = "None"
description = "Skip reasoning for the lowest latency"

[[models.reasoning]]
id = "low"
label = "Low"
description = "Faster answers for straightforward work"

[[models.reasoning]]
id = "medium"
label = "Medium"
description = "Balanced reasoning and latency"

[[models.reasoning]]
id = "high"
label = "High"
description = "Deeper reasoning for complex work"

[[models.reasoning]]
id = "xhigh"
label = "Extra high"
description = "Extended reasoning for demanding work"

[[models.reasoning]]
id = "max"
label = "Maximum"
description = "Maximum reasoning for the hardest work"

[[models.pricing]]
effective_from = 0
[models.pricing.rates]
input_microusd_per_million = 2000000
cached_input_microusd_per_million = 200000
cache_write_input_microusd_per_million = 2500000
output_microusd_per_million = 10000000
[models.pricing.rates.long_context]
threshold_input_tokens = 272000
input_multiplier_millis = 2000
output_multiplier_millis = 1500

[[models]]
id = "gpt-6-luna"
label = "6 Luna"
description = "Focused, high-volume tasks"
default_reasoning = "medium"
context_window = 1050000
tool_discovery = "native"

[[models.reasoning]]
id = "none"
label = "None"
description = "Skip reasoning for the lowest latency"

[[models.reasoning]]
id = "low"
label = "Low"
description = "Faster answers for straightforward work"

[[models.reasoning]]
id = "medium"
label = "Medium"
description = "Balanced reasoning and latency"

[[models.reasoning]]
id = "high"
label = "High"
description = "Deeper reasoning for complex work"

[[models.reasoning]]
id = "xhigh"
label = "Extra high"
description = "Extended reasoning for demanding work"

[[models.reasoning]]
id = "max"
label = "Maximum"
description = "Maximum reasoning for the hardest work"

[[models.pricing]]
effective_from = 0
[models.pricing.rates]
input_microusd_per_million = 100000
cached_input_microusd_per_million = 10000
cache_write_input_microusd_per_million = 125000
output_microusd_per_million = 500000
[models.pricing.rates.long_context]
threshold_input_tokens = 272000
input_multiplier_millis = 2000
output_multiplier_millis = 1500

[[models]]
id = "gpt-6-astra"
label = "6 Astra"
description = "Advanced reasoning and complex end-to-end work"
default_reasoning = "medium"
context_window = 1050000
tool_discovery = "native"

[[models.reasoning]]
id = "low"
label = "Low"
description = "Faster answers for straightforward work"

[[models.reasoning]]
id = "medium"
label = "Medium"
description = "Balanced reasoning and latency"

[[models.reasoning]]
id = "high"
label = "High"
description = "Deeper reasoning for complex work"

[[models.reasoning]]
id = "xhigh"
label = "Extra high"
description = "Extended reasoning for demanding work"

[[models.reasoning]]
id = "max"
label = "Maximum"
description = "Maximum reasoning for the hardest work"

[[models.pricing]]
effective_from = 0
[models.pricing.rates]
input_microusd_per_million = 10000000
cached_input_microusd_per_million = 1000000
cache_write_input_microusd_per_million = 12500000
output_microusd_per_million = 50000000
[models.pricing.rates.long_context]
threshold_input_tokens = 272000
input_multiplier_millis = 2000
output_multiplier_millis = 1500