systemprompt-models 0.14.0

Foundation data models for systemprompt.io AI governance infrastructure. Shared DTOs, config, and domain types consumed by every layer of the MCP governance pipeline.
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
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205

# Canonical default provider catalog.
#
# Single source of truth for the out-of-the-box model knowledge (ids, aliases,
# per-million pricing, capabilities, limits) seeded into a fresh profile. The
# setup wizard, cloud-init scaffolding, and the catalog-parity tests all read
# this one file via `ProviderRegistry::default_seed()`. Operators extend or
# override it by editing `profile.providers` directly — nothing here is
# compiled into model behaviour.
#
# Pricing is per *million* tokens (the registry `ModelPricing` unit). The first
# model under each provider is its agent-side default model.
#
# Model sets are reconciled against each vendor's live `/models` endpoint and
# their published rate cards (as of 2026-06-01):
#   - Anthropic: https://platform.claude.com/docs/en/about-claude/pricing
#   - OpenAI:    https://openai.com/api/pricing/
#   - Google:    https://ai.google.dev/gemini-api/docs/pricing
# Every id below is a real model at its provider; retired ids (Claude 3.x,
# o1-mini/o1-preview, dall-e-2/3, Gemini 1.5) have been dropped.

providers:
  - name: anthropic
    protocol: anthropic
    endpoint: https://api.anthropic.com/v1
    api_key_secret: anthropic
    models:
      - id: claude-sonnet-4-6
        pricing: { input_per_million: 3.0, output_per_million: 15.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 200000, max_output_tokens: 64000 }
      - id: claude-opus-4-8
        pricing: { input_per_million: 5.0, output_per_million: 25.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 200000, max_output_tokens: 64000 }
      - id: claude-opus-4-7
        pricing: { input_per_million: 5.0, output_per_million: 25.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 200000, max_output_tokens: 64000 }
      - id: claude-opus-4-6
        pricing: { input_per_million: 5.0, output_per_million: 25.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 200000, max_output_tokens: 64000 }
      - id: claude-opus-4-5-20251101
        pricing: { input_per_million: 5.0, output_per_million: 25.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 200000, max_output_tokens: 64000 }
      - id: claude-sonnet-4-5-20250929
        pricing: { input_per_million: 3.0, output_per_million: 15.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 200000, max_output_tokens: 64000 }
      - id: claude-haiku-4-5-20251001
        pricing: { input_per_million: 1.0, output_per_million: 5.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 200000, max_output_tokens: 64000 }
      - id: claude-opus-4-1-20250805
        pricing: { input_per_million: 15.0, output_per_million: 75.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 200000, max_output_tokens: 32000 }
      - id: claude-sonnet-4-20250514
        pricing: { input_per_million: 3.0, output_per_million: 15.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 200000, max_output_tokens: 64000 }
      - id: claude-opus-4-20250514
        pricing: { input_per_million: 15.0, output_per_million: 75.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 200000, max_output_tokens: 32000 }

  - name: openai
    protocol: openai-chat
    endpoint: https://api.openai.com/v1
    api_key_secret: openai
    models:
      - id: gpt-4.1
        pricing: { input_per_million: 2.0, output_per_million: 8.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 1000000, max_output_tokens: 32768 }
      - id: gpt-4.1-mini
        pricing: { input_per_million: 0.4, output_per_million: 1.6 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 1000000, max_output_tokens: 32768 }
      - id: gpt-4.1-nano
        pricing: { input_per_million: 0.1, output_per_million: 0.4 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 1000000, max_output_tokens: 32768 }
      - id: gpt-5
        pricing: { input_per_million: 1.25, output_per_million: 10.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 400000, max_output_tokens: 128000 }
      - id: gpt-5.1
        pricing: { input_per_million: 1.25, output_per_million: 10.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 400000, max_output_tokens: 128000 }
      - id: gpt-5-mini
        pricing: { input_per_million: 0.25, output_per_million: 2.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 400000, max_output_tokens: 128000 }
      - id: gpt-5-nano
        pricing: { input_per_million: 0.05, output_per_million: 0.4 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 400000, max_output_tokens: 128000 }
      - id: o4-mini
        pricing: { input_per_million: 1.1, output_per_million: 4.4 }
        capabilities: { streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 200000, max_output_tokens: 100000 }
      - id: o3
        pricing: { input_per_million: 10.0, output_per_million: 40.0 }
        capabilities: { streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 200000, max_output_tokens: 100000 }
      - id: o3-mini
        pricing: { input_per_million: 1.1, output_per_million: 4.4 }
        capabilities: { streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 200000, max_output_tokens: 100000 }
      - id: gpt-4o
        pricing: { input_per_million: 2.5, output_per_million: 10.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 128000, max_output_tokens: 16384 }
      - id: gpt-4o-mini
        pricing: { input_per_million: 0.15, output_per_million: 0.6 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 128000, max_output_tokens: 16384 }
      - id: gpt-4-turbo
        pricing: { input_per_million: 10.0, output_per_million: 30.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 128000, max_output_tokens: 4096 }
      - id: gpt-4
        pricing: { input_per_million: 10.0, output_per_million: 30.0 }
        capabilities: { streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 8192, max_output_tokens: 4096 }
      - id: gpt-3.5-turbo
        pricing: { input_per_million: 0.5, output_per_million: 1.5 }
        capabilities: { streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 16385, max_output_tokens: 4096 }
      - id: o1
        pricing: { input_per_million: 15.0, output_per_million: 60.0 }
        capabilities: { streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 200000, max_output_tokens: 100000 }
      - id: gpt-image-1
        pricing: { input_per_million: 0.0, output_per_million: 0.0, per_image_cents: 4.0 }
        capabilities: { image_generation: true }
      - id: gpt-image-1-mini
        pricing: { input_per_million: 0.0, output_per_million: 0.0, per_image_cents: 4.0 }
        capabilities: { image_generation: true }

  - name: gemini
    protocol: gemini
    endpoint: https://generativelanguage.googleapis.com/v1beta
    api_key_secret: gemini
    models:
      - id: gemini-3.1-flash-lite-preview
        pricing: { input_per_million: 0.25, output_per_million: 1.5 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 1000000, max_output_tokens: 65536 }
      - id: gemini-3.1-pro-preview
        pricing: { input_per_million: 2.0, output_per_million: 12.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 1000000, max_output_tokens: 65536 }
      - id: gemini-3.5-flash
        pricing: { input_per_million: 1.5, output_per_million: 9.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 1000000, max_output_tokens: 65536 }
      - id: gemini-3.1-flash-image-preview
        pricing: { input_per_million: 0.5, output_per_million: 3.0, per_image_cents: 4.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true, image_generation: true }
        limits: { context_window: 1000000, max_output_tokens: 65536 }
      - id: gemini-3-flash-preview
        pricing: { input_per_million: 0.5, output_per_million: 3.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 1000000, max_output_tokens: 65536 }
      - id: gemini-3-pro-image-preview
        pricing: { input_per_million: 2.0, output_per_million: 12.0, per_image_cents: 4.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true, image_generation: true }
        limits: { context_window: 1000000, max_output_tokens: 65536 }
      # Rotating aliases — the vendor repoints these at the current pro/flash
      # release; priced to the model each currently resolves to.
      - id: gemini-pro-latest
        pricing: { input_per_million: 2.0, output_per_million: 12.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 1000000, max_output_tokens: 65536 }
      - id: gemini-flash-latest
        pricing: { input_per_million: 1.5, output_per_million: 9.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 1000000, max_output_tokens: 65536 }
      - id: gemini-2.5-flash-lite
        pricing: { input_per_million: 0.1, output_per_million: 0.4 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 1000000, max_output_tokens: 65536 }
      - id: gemini-2.5-flash
        pricing: { input_per_million: 0.3, output_per_million: 2.5 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 1000000, max_output_tokens: 65536 }
      - id: gemini-2.5-pro
        pricing: { input_per_million: 1.25, output_per_million: 10.0 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 1000000, max_output_tokens: 65536 }
      - id: gemini-2.0-flash
        pricing: { input_per_million: 0.1, output_per_million: 0.4 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 1000000, max_output_tokens: 8192 }
      - id: gemini-2.0-flash-lite
        pricing: { input_per_million: 0.1, output_per_million: 0.4 }
        capabilities: { vision: true, streaming: true, tools: true, structured_output: true, system_prompts: true }
        limits: { context_window: 1000000, max_output_tokens: 8192 }
      - id: gemini-2.5-flash-image
        pricing: { input_per_million: 0.0, output_per_million: 0.0, per_image_cents: 4.0 }
        capabilities: { image_generation: true }