segreant 0.1.0 → 0.2.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (142) hide show
  1. package/LICENSING.md +5 -3
  2. package/README.md +57 -19
  3. package/bin/segreant-statusline.mjs +20 -0
  4. package/bin/segreant.mjs +19 -8
  5. package/dist/alerts/detect.js +13 -0
  6. package/dist/billing/epistemic.js +4 -0
  7. package/dist/billing/importer.js +29 -10
  8. package/dist/billing/reconcile.js +122 -32
  9. package/dist/billing/scope.js +7 -0
  10. package/dist/budget/guard.js +33 -4
  11. package/dist/cli/allocCmd.js +73 -4
  12. package/dist/cli/askModelPrices.js +59 -0
  13. package/dist/cli/backupCmd.js +2 -1
  14. package/dist/cli/basisLines.js +45 -0
  15. package/dist/cli/billingCmd.js +68 -9
  16. package/dist/cli/capitalCmd.js +2 -1
  17. package/dist/cli/connectCmd.js +50 -9
  18. package/dist/cli/egressCmd.js +15 -3
  19. package/dist/cli/evidenceCmd.js +6 -3
  20. package/dist/cli/flags.js +68 -0
  21. package/dist/cli/homeCmd.js +117 -0
  22. package/dist/cli/importCmd.js +210 -54
  23. package/dist/cli/launchCmd.js +2 -1
  24. package/dist/cli/opsCmd.js +49 -2
  25. package/dist/cli/planCmd.js +181 -0
  26. package/dist/cli/pricingDeclareCmd.js +178 -0
  27. package/dist/cli/quotaCmd.js +190 -0
  28. package/dist/cli/runCmd.js +203 -51
  29. package/dist/cli/showCmd.js +37 -11
  30. package/dist/cli/teamCmd.js +5 -5
  31. package/dist/cli/ui.js +24 -8
  32. package/dist/cli/valueCmd.js +189 -14
  33. package/dist/cli.js +102 -21
  34. package/dist/config.js +95 -6
  35. package/dist/connect/antigravity.js +310 -0
  36. package/dist/connect/claudeCode.js +43 -3
  37. package/dist/connect/codex.js +38 -1
  38. package/dist/connect/importShared.js +58 -5
  39. package/dist/connect/opencode.js +37 -9
  40. package/dist/connect/protobuf.js +126 -0
  41. package/dist/connect/registry.js +46 -0
  42. package/dist/connect/repoRoot.js +112 -0
  43. package/dist/cost/basis.js +168 -0
  44. package/dist/cost/declarations.js +37 -0
  45. package/dist/cost/exactPricing.js +4 -1
  46. package/dist/cost/firstSight.js +98 -0
  47. package/dist/cost/overrides.js +230 -0
  48. package/dist/cost/pricing.js +228 -15
  49. package/dist/cost/reprice.js +130 -0
  50. package/dist/dashboard/claim-support.js +11 -8
  51. package/dist/dashboard/contracts.js +23 -3
  52. package/dist/dashboard/routes.js +980 -112
  53. package/dist/dashboard/sessions.js +345 -0
  54. package/dist/dashboard/settings.js +2 -1
  55. package/dist/dashboard/value-cache.js +105 -0
  56. package/dist/dashboard/web/app/components/claimInspector.js +6 -5
  57. package/dist/dashboard/web/app/components/drawer.js +105 -35
  58. package/dist/dashboard/web/app/components/ruleFields.js +144 -0
  59. package/dist/dashboard/web/app/components/spine.js +54 -24
  60. package/dist/dashboard/web/app/components/workflow.js +82 -0
  61. package/dist/dashboard/web/app/core/actions.js +734 -23
  62. package/dist/dashboard/web/app/core/api.js +37 -1
  63. package/dist/dashboard/web/app/core/chain.js +11 -4
  64. package/dist/dashboard/web/app/core/claimLayers.js +179 -51
  65. package/dist/dashboard/web/app/core/claimTypes.js +30 -0
  66. package/dist/dashboard/web/app/core/fmt.js +19 -2
  67. package/dist/dashboard/web/app/core/generated-contract.js +23 -3
  68. package/dist/dashboard/web/app/core/generated-payload-contract.js +1944 -465
  69. package/dist/dashboard/web/app/core/generated-types.js +1 -1
  70. package/dist/dashboard/web/app/core/griffin.js +10 -0
  71. package/dist/dashboard/web/app/core/jobs.js +12 -0
  72. package/dist/dashboard/web/app/core/period.js +35 -0
  73. package/dist/dashboard/web/app/core/periodWords.js +10 -0
  74. package/dist/dashboard/web/app/core/periods.js +32 -0
  75. package/dist/dashboard/web/app/core/pricingActions.js +264 -0
  76. package/dist/dashboard/web/app/core/privacyText.js +78 -0
  77. package/dist/dashboard/web/app/core/reconcileWords.js +63 -0
  78. package/dist/dashboard/web/app/core/registry.js +79 -46
  79. package/dist/dashboard/web/app/core/slug.js +9 -0
  80. package/dist/dashboard/web/app/core/theme.js +48 -0
  81. package/dist/dashboard/web/app/core/view.js +69 -0
  82. package/dist/dashboard/web/app/main.js +197 -15
  83. package/dist/dashboard/web/app/views/allocation.js +249 -61
  84. package/dist/dashboard/web/app/views/control.js +57 -16
  85. package/dist/dashboard/web/app/views/data.js +4 -4
  86. package/dist/dashboard/web/app/views/evidence.js +336 -87
  87. package/dist/dashboard/web/app/views/privacy.js +13 -0
  88. package/dist/dashboard/web/app/views/spend.js +30 -15
  89. package/dist/dashboard/web/app/views/statement.js +189 -0
  90. package/dist/dashboard/web/app/views/system.js +44 -4
  91. package/dist/dashboard/web/app/views/value.js +105 -59
  92. package/dist/dashboard/web/app/views/workbench.js +312 -0
  93. package/dist/dashboard/web/classic.html +16 -4
  94. package/dist/dashboard/web/index.html +1 -1
  95. package/dist/dashboard/web/styles/app.css +536 -23
  96. package/dist/demo/seed.js +153 -14
  97. package/dist/economics/ledger.js +1 -1
  98. package/dist/egress/policy.js +129 -5
  99. package/dist/export/allocationCsv.js +70 -0
  100. package/dist/export/billingCsv.js +6 -2
  101. package/dist/export/csv.js +10 -2
  102. package/dist/export/economic.js +6 -2
  103. package/dist/export/statementCsv.js +104 -0
  104. package/dist/git/correlate.js +86 -9
  105. package/dist/git/quality.js +107 -24
  106. package/dist/git/repoScope.js +207 -0
  107. package/dist/git/survivalStore.js +186 -0
  108. package/dist/guide.js +9 -4
  109. package/dist/plans/detect.js +147 -0
  110. package/dist/proxy/server.js +134 -14
  111. package/dist/proxy/usage.js +9 -4
  112. package/dist/quota/limits.js +138 -0
  113. package/dist/quota/statusline.js +68 -0
  114. package/dist/quota/view.js +122 -0
  115. package/dist/scan/knownApps.js +6 -2
  116. package/dist/scan/scan.js +9 -0
  117. package/dist/store/allocation.js +14 -0
  118. package/dist/store/db.js +259 -34
  119. package/dist/store/realization.js +78 -14
  120. package/dist/store/schema.js +59 -1
  121. package/dist/store/scopeEvidence.js +67 -0
  122. package/dist/util/pool.js +19 -0
  123. package/dist/util/time.js +7 -0
  124. package/dist/value/realization.js +321 -30
  125. package/dist/value/report.js +28 -8
  126. package/dist/value/selfReported.js +10 -9
  127. package/docs/ARCHITECTURE.md +8 -4
  128. package/docs/CAPABILITY-EVIDENCE-CONTRACT.md +33 -11
  129. package/docs/CLI-JSON-CONTRACT.md +38 -0
  130. package/docs/DATA-BOUNDARIES.md +66 -6
  131. package/docs/FAQ.md +43 -9
  132. package/docs/GETTING-STARTED.md +19 -12
  133. package/docs/GUIDE.md +81 -18
  134. package/docs/INTEGRATIONS.md +9 -9
  135. package/docs/METHODOLOGY.md +3 -2
  136. package/docs/NEUTRALITY.md +1 -1
  137. package/docs/PRIVACY.md +51 -0
  138. package/docs/README.md +1 -0
  139. package/docs/RELEASE-GATE.md +52 -7
  140. package/docs/THREAT-MODEL.md +2 -1
  141. package/package.json +3 -2
  142. package/pricing/models.json +1366 -60
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "schema_version": 1,
3
- "updated": "2026-09-29",
3
+ "updated": "2026-10-17",
4
4
  "currency": "USD",
5
5
  "unit": "per_million_tokens",
6
6
  "notes": [
@@ -8,87 +8,1393 @@
8
8
  "cache_write_5m / cache_write_1h: cost to WRITE tokens into the prompt cache (Anthropic charges 1.25x input for 5-min TTL, 2x for 1-hour TTL).",
9
9
  "cache_read: cost to READ tokens already in cache (Anthropic ~0.1x input; OpenAI ~0.5x input).",
10
10
  "Anthropic bills extended-thinking ('reasoning') tokens as ordinary OUTPUT tokens. OpenAI bills o-series reasoning tokens inside completion_tokens. There is NO separate reasoning multiplier in current provider pricing.",
11
- "Anthropic and OpenAI values verified against each provider's own pricing page on 2026-09-29 (see each provider's source). They are list prices: negotiated discounts, credits and taxes are not in this card.",
12
- "Google/Gemini values verified against ai.google.dev/gemini-api/docs/pricing (2026-06). Gemini 2.5 Pro lists the <=200k-token base rate; prompts over 200k bill at input 2.50 / output 15.0 / cache_read 0.25.",
11
+ "Anthropic and OpenAI values verified against each provider's own pricing page on 2026-09-29 (see each provider's source), except gpt-6.1-sol, read from its OpenAI model page on 2026-10-10. They are list prices: negotiated discounts, credits and taxes are not in this card.",
12
+ "Models marked with their own \"source\" were added on 2026-10-17 from the public price list (LiteLLM), not from the provider’s pricing page; the provider-level \"verified\" and \"source\" fields describe the other entries only. They are still list prices, with the same exclusions as the rest of the card.",
13
+ "Google/Gemini values verified against ai.google.dev/gemini-api/docs/pricing: the 2.5 models were read in 2026-06, and the 3.x models on 2026-10-09 from the same page (updated 2026-10-07). Gemini 2.5 Pro lists the <=200k-token base rate; prompts over 200k bill at input 2.50 / output 15.0 / cache_read 0.25.",
13
14
  "Gemini is metered through Segreant's OpenAI-compatible path (Google's .../v1beta/openai/ base URL). The cost engine resolves a rate by model family ACROSS providers, so the price follows the model id regardless of which wire protocol carried it.",
14
15
  "Not modelled. These make a request cost MORE than this card shows: OpenAI long-context rates (the page's 'Long context' column), OpenAI cache-write rates, Fast mode on either provider, and the 1.1x data-residency uplift (Anthropic inference_geo, OpenAI regional processing). Batch and Flex discounts make it cost LESS.",
15
- "Google's Gemini 3.x models are not listed: their published rates are promotional through 2026-12-31 and double on 2027-01-01, and this card cannot express a rate that expires. They fall back to a flagged family or unknown estimate."
16
+ "Gemini 3.6, 3.7 and 3.8 Flash carry Google's rates through 2026-12-31; the page lists higher rates from 2027-01-01. This card cannot express a rate that expires, so it keeps the current rates, and those rows read low from 2027-01-01 until the card is updated. Gemini models not listed here fall back to a flagged family or unknown estimate."
16
17
  ],
17
18
  "providers": {
18
19
  "anthropic": {
19
20
  "verified": true,
20
21
  "source": "platform.claude.com/docs/en/about-claude/pricing (read 2026-09-29)",
21
22
  "models": {
22
- "claude-fable-5-1": {"input": 10, "output": 50, "cache_write_5m": 12.5, "cache_write_1h": 20, "cache_read": 0.25, "exact": {"input": "10", "output": "50", "cache_write_5m": "12.5", "cache_write_1h": "20", "cache_read": "0.25"}},
23
- "claude-mythos-5-1": {"input": 10, "output": 50, "cache_write_5m": 12.5, "cache_write_1h": 20, "cache_read": 0.25, "exact": {"input": "10", "output": "50", "cache_write_5m": "12.5", "cache_write_1h": "20", "cache_read": "0.25"}},
24
- "claude-opus-5-5": {"input": 4, "output": 20, "cache_write_5m": 5, "cache_write_1h": 8, "cache_read": 0.2, "exact": {"input": "4", "output": "20", "cache_write_5m": "5", "cache_write_1h": "8", "cache_read": "0.2"}},
25
- "claude-sonnet-5-5": {"input": 2, "output": 10, "cache_write_5m": 2.5, "cache_write_1h": 4, "cache_read": 0.2, "exact": {"input": "2", "output": "10", "cache_write_5m": "2.5", "cache_write_1h": "4", "cache_read": "0.2"}},
26
- "claude-fable-5": {"input": 10, "output": 50, "cache_write_5m": 12.5, "cache_write_1h": 20, "cache_read": 1, "exact": {"input": "10", "output": "50", "cache_write_5m": "12.5", "cache_write_1h": "20", "cache_read": "1"}},
27
- "claude-mythos-5": {"input": 10, "output": 50, "cache_write_5m": 12.5, "cache_write_1h": 20, "cache_read": 1, "exact": {"input": "10", "output": "50", "cache_write_5m": "12.5", "cache_write_1h": "20", "cache_read": "1"}},
28
- "claude-opus-5": {"input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5, "exact": {"input": "5", "output": "25", "cache_write_5m": "6.25", "cache_write_1h": "10", "cache_read": "0.5"}},
29
- "claude-sonnet-5": {"input": 2, "output": 10, "cache_write_5m": 2.5, "cache_write_1h": 4, "cache_read": 0.2, "exact": {"input": "2", "output": "10", "cache_write_5m": "2.5", "cache_write_1h": "4", "cache_read": "0.2"}},
30
- "claude-opus-4-8": {"input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5, "exact": {"input": "5", "output": "25", "cache_write_5m": "6.25", "cache_write_1h": "10", "cache_read": "0.5"}},
31
- "claude-opus-4-7": {"input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5, "exact": {"input": "5", "output": "25", "cache_write_5m": "6.25", "cache_write_1h": "10", "cache_read": "0.5"}},
32
- "claude-opus-4-6": {"input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5, "exact": {"input": "5", "output": "25", "cache_write_5m": "6.25", "cache_write_1h": "10", "cache_read": "0.5"}},
33
- "claude-opus-4-5": {"input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5, "exact": {"input": "5", "output": "25", "cache_write_5m": "6.25", "cache_write_1h": "10", "cache_read": "0.5"}},
34
- "claude-opus-4-1": {"input": 15, "output": 75, "cache_write_5m": 18.75, "cache_write_1h": 30, "cache_read": 1.5, "exact": {"input": "15", "output": "75", "cache_write_5m": "18.75", "cache_write_1h": "30", "cache_read": "1.5"}},
35
- "claude-opus-4": {"input": 15, "output": 75, "cache_write_5m": 18.75, "cache_write_1h": 30, "cache_read": 1.5, "exact": {"input": "15", "output": "75", "cache_write_5m": "18.75", "cache_write_1h": "30", "cache_read": "1.5"}},
36
- "claude-sonnet-4-6": {"input": 3, "output": 15, "cache_write_5m": 3.75, "cache_write_1h": 6, "cache_read": 0.3, "exact": {"input": "3", "output": "15", "cache_write_5m": "3.75", "cache_write_1h": "6", "cache_read": "0.3"}},
37
- "claude-sonnet-4-5": {"input": 3, "output": 15, "cache_write_5m": 3.75, "cache_write_1h": 6, "cache_read": 0.3, "exact": {"input": "3", "output": "15", "cache_write_5m": "3.75", "cache_write_1h": "6", "cache_read": "0.3"}},
38
- "claude-sonnet-4": {"input": 3, "output": 15, "cache_write_5m": 3.75, "cache_write_1h": 6, "cache_read": 0.3, "exact": {"input": "3", "output": "15", "cache_write_5m": "3.75", "cache_write_1h": "6", "cache_read": "0.3"}},
39
- "claude-haiku-4-5": {"input": 1, "output": 5, "cache_write_5m": 1.25, "cache_write_1h": 2, "cache_read": 0.1, "exact": {"input": "1", "output": "5", "cache_write_5m": "1.25", "cache_write_1h": "2", "cache_read": "0.1"}},
40
- "claude-3-5-haiku": {"input": 0.8, "output": 4, "cache_write_5m": 1, "cache_write_1h": 1.6, "cache_read": 0.08, "exact": {"input": "0.8", "output": "4", "cache_write_5m": "1", "cache_write_1h": "1.6", "cache_read": "0.08"}}
23
+ "claude-fable-5-1": {
24
+ "input": 10,
25
+ "output": 50,
26
+ "cache_write_5m": 12.5,
27
+ "cache_write_1h": 20,
28
+ "cache_read": 0.25,
29
+ "exact": {
30
+ "input": "10",
31
+ "output": "50",
32
+ "cache_write_5m": "12.5",
33
+ "cache_write_1h": "20",
34
+ "cache_read": "0.25"
35
+ }
36
+ },
37
+ "claude-mythos-5-1": {
38
+ "input": 10,
39
+ "output": 50,
40
+ "cache_write_5m": 12.5,
41
+ "cache_write_1h": 20,
42
+ "cache_read": 0.25,
43
+ "exact": {
44
+ "input": "10",
45
+ "output": "50",
46
+ "cache_write_5m": "12.5",
47
+ "cache_write_1h": "20",
48
+ "cache_read": "0.25"
49
+ }
50
+ },
51
+ "claude-opus-5-5": {
52
+ "input": 4,
53
+ "output": 20,
54
+ "cache_write_5m": 5,
55
+ "cache_write_1h": 8,
56
+ "cache_read": 0.2,
57
+ "exact": {
58
+ "input": "4",
59
+ "output": "20",
60
+ "cache_write_5m": "5",
61
+ "cache_write_1h": "8",
62
+ "cache_read": "0.2"
63
+ }
64
+ },
65
+ "claude-sonnet-5-5": {
66
+ "input": 2,
67
+ "output": 10,
68
+ "cache_write_5m": 2.5,
69
+ "cache_write_1h": 4,
70
+ "cache_read": 0.2,
71
+ "exact": {
72
+ "input": "2",
73
+ "output": "10",
74
+ "cache_write_5m": "2.5",
75
+ "cache_write_1h": "4",
76
+ "cache_read": "0.2"
77
+ }
78
+ },
79
+ "claude-fable-5": {
80
+ "input": 10,
81
+ "output": 50,
82
+ "cache_write_5m": 12.5,
83
+ "cache_write_1h": 20,
84
+ "cache_read": 1,
85
+ "exact": {
86
+ "input": "10",
87
+ "output": "50",
88
+ "cache_write_5m": "12.5",
89
+ "cache_write_1h": "20",
90
+ "cache_read": "1"
91
+ }
92
+ },
93
+ "claude-mythos-5": {
94
+ "input": 10,
95
+ "output": 50,
96
+ "cache_write_5m": 12.5,
97
+ "cache_write_1h": 20,
98
+ "cache_read": 1,
99
+ "exact": {
100
+ "input": "10",
101
+ "output": "50",
102
+ "cache_write_5m": "12.5",
103
+ "cache_write_1h": "20",
104
+ "cache_read": "1"
105
+ }
106
+ },
107
+ "claude-opus-5": {
108
+ "input": 5,
109
+ "output": 25,
110
+ "cache_write_5m": 6.25,
111
+ "cache_write_1h": 10,
112
+ "cache_read": 0.5,
113
+ "exact": {
114
+ "input": "5",
115
+ "output": "25",
116
+ "cache_write_5m": "6.25",
117
+ "cache_write_1h": "10",
118
+ "cache_read": "0.5"
119
+ }
120
+ },
121
+ "claude-sonnet-5": {
122
+ "input": 2,
123
+ "output": 10,
124
+ "cache_write_5m": 2.5,
125
+ "cache_write_1h": 4,
126
+ "cache_read": 0.2,
127
+ "exact": {
128
+ "input": "2",
129
+ "output": "10",
130
+ "cache_write_5m": "2.5",
131
+ "cache_write_1h": "4",
132
+ "cache_read": "0.2"
133
+ }
134
+ },
135
+ "claude-opus-4-8": {
136
+ "input": 5,
137
+ "output": 25,
138
+ "cache_write_5m": 6.25,
139
+ "cache_write_1h": 10,
140
+ "cache_read": 0.5,
141
+ "exact": {
142
+ "input": "5",
143
+ "output": "25",
144
+ "cache_write_5m": "6.25",
145
+ "cache_write_1h": "10",
146
+ "cache_read": "0.5"
147
+ }
148
+ },
149
+ "claude-opus-4-7": {
150
+ "input": 5,
151
+ "output": 25,
152
+ "cache_write_5m": 6.25,
153
+ "cache_write_1h": 10,
154
+ "cache_read": 0.5,
155
+ "exact": {
156
+ "input": "5",
157
+ "output": "25",
158
+ "cache_write_5m": "6.25",
159
+ "cache_write_1h": "10",
160
+ "cache_read": "0.5"
161
+ }
162
+ },
163
+ "claude-opus-4-6": {
164
+ "input": 5,
165
+ "output": 25,
166
+ "cache_write_5m": 6.25,
167
+ "cache_write_1h": 10,
168
+ "cache_read": 0.5,
169
+ "exact": {
170
+ "input": "5",
171
+ "output": "25",
172
+ "cache_write_5m": "6.25",
173
+ "cache_write_1h": "10",
174
+ "cache_read": "0.5"
175
+ }
176
+ },
177
+ "claude-opus-4-5": {
178
+ "input": 5,
179
+ "output": 25,
180
+ "cache_write_5m": 6.25,
181
+ "cache_write_1h": 10,
182
+ "cache_read": 0.5,
183
+ "exact": {
184
+ "input": "5",
185
+ "output": "25",
186
+ "cache_write_5m": "6.25",
187
+ "cache_write_1h": "10",
188
+ "cache_read": "0.5"
189
+ }
190
+ },
191
+ "claude-opus-4-1": {
192
+ "input": 15,
193
+ "output": 75,
194
+ "cache_write_5m": 18.75,
195
+ "cache_write_1h": 30,
196
+ "cache_read": 1.5,
197
+ "exact": {
198
+ "input": "15",
199
+ "output": "75",
200
+ "cache_write_5m": "18.75",
201
+ "cache_write_1h": "30",
202
+ "cache_read": "1.5"
203
+ }
204
+ },
205
+ "claude-opus-4": {
206
+ "input": 15,
207
+ "output": 75,
208
+ "cache_write_5m": 18.75,
209
+ "cache_write_1h": 30,
210
+ "cache_read": 1.5,
211
+ "exact": {
212
+ "input": "15",
213
+ "output": "75",
214
+ "cache_write_5m": "18.75",
215
+ "cache_write_1h": "30",
216
+ "cache_read": "1.5"
217
+ }
218
+ },
219
+ "claude-sonnet-4-6": {
220
+ "input": 3,
221
+ "output": 15,
222
+ "cache_write_5m": 3.75,
223
+ "cache_write_1h": 6,
224
+ "cache_read": 0.3,
225
+ "exact": {
226
+ "input": "3",
227
+ "output": "15",
228
+ "cache_write_5m": "3.75",
229
+ "cache_write_1h": "6",
230
+ "cache_read": "0.3"
231
+ }
232
+ },
233
+ "claude-sonnet-4-5": {
234
+ "input": 3,
235
+ "output": 15,
236
+ "cache_write_5m": 3.75,
237
+ "cache_write_1h": 6,
238
+ "cache_read": 0.3,
239
+ "exact": {
240
+ "input": "3",
241
+ "output": "15",
242
+ "cache_write_5m": "3.75",
243
+ "cache_write_1h": "6",
244
+ "cache_read": "0.3"
245
+ }
246
+ },
247
+ "claude-sonnet-4": {
248
+ "input": 3,
249
+ "output": 15,
250
+ "cache_write_5m": 3.75,
251
+ "cache_write_1h": 6,
252
+ "cache_read": 0.3,
253
+ "exact": {
254
+ "input": "3",
255
+ "output": "15",
256
+ "cache_write_5m": "3.75",
257
+ "cache_write_1h": "6",
258
+ "cache_read": "0.3"
259
+ }
260
+ },
261
+ "claude-haiku-4-5": {
262
+ "input": 1,
263
+ "output": 5,
264
+ "cache_write_5m": 1.25,
265
+ "cache_write_1h": 2,
266
+ "cache_read": 0.1,
267
+ "exact": {
268
+ "input": "1",
269
+ "output": "5",
270
+ "cache_write_5m": "1.25",
271
+ "cache_write_1h": "2",
272
+ "cache_read": "0.1"
273
+ }
274
+ },
275
+ "claude-3-5-haiku": {
276
+ "input": 0.8,
277
+ "output": 4,
278
+ "cache_write_5m": 1,
279
+ "cache_write_1h": 1.6,
280
+ "cache_read": 0.08,
281
+ "exact": {
282
+ "input": "0.8",
283
+ "output": "4",
284
+ "cache_write_5m": "1",
285
+ "cache_write_1h": "1.6",
286
+ "cache_read": "0.08"
287
+ }
288
+ },
289
+ "claude-mythos-preview": {
290
+ "input": 10,
291
+ "output": 50,
292
+ "cache_read": 1,
293
+ "cache_write_5m": 12.5,
294
+ "exact": {
295
+ "input": "10",
296
+ "output": "50",
297
+ "cache_read": "1",
298
+ "cache_write_5m": "12.5"
299
+ },
300
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
301
+ },
302
+ "claude-haiku-5-5": {
303
+ "input": 0.1,
304
+ "output": 0.5,
305
+ "cache_read": 0.01,
306
+ "cache_write_5m": 0.125,
307
+ "exact": {
308
+ "input": "0.1",
309
+ "output": "0.5",
310
+ "cache_read": "0.01",
311
+ "cache_write_5m": "0.125"
312
+ },
313
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
314
+ }
41
315
  }
42
316
  },
43
317
  "openai": {
44
318
  "verified": true,
45
- "source": "developers.openai.com/api/docs/pricing, Standard tier, short-context rates (read 2026-09-29)",
319
+ "source": "developers.openai.com/api/docs/pricing, Standard tier, short-context rates (read 2026-09-29); gpt-6.1-sol from developers.openai.com/api/docs/models/gpt-6.1-sol (read 2026-10-10: prompts over 272K input tokens bill 2x input and cache and 1.5x output, Fast 2x, Batch and Flex 0.5x, regional processing +10%; none of these modifiers is applied here)",
46
320
  "models": {
47
- "gpt-6-astra": {"input": 10, "output": 50, "cache_read": 1, "exact": {"input": "10", "output": "50", "cache_read": "1"}},
48
- "gpt-6-sol": {"input": 2, "output": 10, "cache_read": 0.2, "exact": {"input": "2", "output": "10", "cache_read": "0.2"}},
49
- "gpt-6-luna": {"input": 0.1, "output": 0.5, "cache_read": 0.01, "exact": {"input": "0.1", "output": "0.5", "cache_read": "0.01"}},
50
- "gpt-5.6-sol": {"input": 4, "output": 20, "cache_read": 0.4, "exact": {"input": "4", "output": "20", "cache_read": "0.4"}},
51
- "gpt-5.6-terra": {"input": 2, "output": 12, "cache_read": 0.2, "exact": {"input": "2", "output": "12", "cache_read": "0.2"}},
52
- "gpt-5.6-luna": {"input": 0.2, "output": 1.2, "cache_read": 0.02, "exact": {"input": "0.2", "output": "1.2", "cache_read": "0.02"}},
53
- "gpt-5.6-cyber": {"input": 12.5, "output": 75, "cache_read": 1.25, "exact": {"input": "12.5", "output": "75", "cache_read": "1.25"}},
54
- "gpt-5.5": {"input": 5, "output": 30, "cache_read": 0.5, "exact": {"input": "5", "output": "30", "cache_read": "0.5"}},
55
- "gpt-5.5-pro": {"input": 30, "output": 180, "exact": {"input": "30", "output": "180"}},
56
- "gpt-5.4": {"input": 2.5, "output": 15, "cache_read": 0.25, "exact": {"input": "2.5", "output": "15", "cache_read": "0.25"}},
57
- "gpt-5.4-pro": {"input": 30, "output": 180, "exact": {"input": "30", "output": "180"}},
58
- "gpt-5.4-mini": {"input": 0.75, "output": 4.5, "cache_read": 0.075, "exact": {"input": "0.75", "output": "4.5", "cache_read": "0.075"}},
59
- "gpt-5.4-nano": {"input": 0.2, "output": 1.25, "cache_read": 0.02, "exact": {"input": "0.2", "output": "1.25", "cache_read": "0.02"}},
60
- "gpt-5.3-codex": {"input": 1.75, "output": 14, "cache_read": 0.175, "exact": {"input": "1.75", "output": "14", "cache_read": "0.175"}},
61
- "gpt-5.2": {"input": 1.75, "output": 14, "cache_read": 0.175, "exact": {"input": "1.75", "output": "14", "cache_read": "0.175"}},
62
- "gpt-5.2-pro": {"input": 21, "output": 168, "exact": {"input": "21", "output": "168"}},
63
- "gpt-5.1": {"input": 1.25, "output": 10, "cache_read": 0.125, "exact": {"input": "1.25", "output": "10", "cache_read": "0.125"}},
64
- "gpt-5": {"input": 1.25, "output": 10, "cache_read": 0.125, "exact": {"input": "1.25", "output": "10", "cache_read": "0.125"}},
65
- "gpt-5-mini": {"input": 0.25, "output": 2, "cache_read": 0.025, "exact": {"input": "0.25", "output": "2", "cache_read": "0.025"}},
66
- "gpt-5-nano": {"input": 0.05, "output": 0.4, "cache_read": 0.005, "exact": {"input": "0.05", "output": "0.4", "cache_read": "0.005"}},
67
- "gpt-5-pro": {"input": 15, "output": 120, "exact": {"input": "15", "output": "120"}},
68
- "chat-latest": {"input": 5, "output": 30, "cache_read": 0.5, "exact": {"input": "5", "output": "30", "cache_read": "0.5"}},
69
- "gpt-4.1": {"input": 2, "output": 8, "cache_read": 0.5, "exact": {"input": "2", "output": "8", "cache_read": "0.5"}},
70
- "gpt-4.1-mini": {"input": 0.4, "output": 1.6, "cache_read": 0.1, "exact": {"input": "0.4", "output": "1.6", "cache_read": "0.1"}},
71
- "gpt-4.1-nano": {"input": 0.1, "output": 0.4, "cache_read": 0.025, "exact": {"input": "0.1", "output": "0.4", "cache_read": "0.025"}},
72
- "gpt-4o": {"input": 2.5, "output": 10, "cache_read": 1.25, "exact": {"input": "2.5", "output": "10", "cache_read": "1.25"}},
73
- "gpt-4o-mini": {"input": 0.15, "output": 0.6, "cache_read": 0.075, "exact": {"input": "0.15", "output": "0.6", "cache_read": "0.075"}},
74
- "o4-mini": {"input": 1.1, "output": 4.4, "cache_read": 0.275, "exact": {"input": "1.1", "output": "4.4", "cache_read": "0.275"}},
75
- "o3": {"input": 2, "output": 8, "cache_read": 0.5, "exact": {"input": "2", "output": "8", "cache_read": "0.5"}},
76
- "o3-mini": {"input": 1.1, "output": 4.4, "cache_read": 0.55, "exact": {"input": "1.1", "output": "4.4", "cache_read": "0.55"}},
77
- "o3-pro": {"input": 20, "output": 80, "exact": {"input": "20", "output": "80"}}
321
+ "gpt-6-astra": {
322
+ "input": 10,
323
+ "output": 50,
324
+ "cache_read": 1,
325
+ "exact": {
326
+ "input": "10",
327
+ "output": "50",
328
+ "cache_read": "1"
329
+ }
330
+ },
331
+ "gpt-6.1-sol": {
332
+ "input": 2,
333
+ "output": 10,
334
+ "cache_read": 0.1,
335
+ "exact": {
336
+ "input": "2",
337
+ "output": "10",
338
+ "cache_read": "0.1"
339
+ }
340
+ },
341
+ "gpt-6-sol": {
342
+ "input": 2,
343
+ "output": 10,
344
+ "cache_read": 0.2,
345
+ "exact": {
346
+ "input": "2",
347
+ "output": "10",
348
+ "cache_read": "0.2"
349
+ }
350
+ },
351
+ "gpt-6-luna": {
352
+ "input": 0.1,
353
+ "output": 0.5,
354
+ "cache_read": 0.01,
355
+ "exact": {
356
+ "input": "0.1",
357
+ "output": "0.5",
358
+ "cache_read": "0.01"
359
+ }
360
+ },
361
+ "gpt-5.6-sol": {
362
+ "input": 4,
363
+ "output": 20,
364
+ "cache_read": 0.4,
365
+ "exact": {
366
+ "input": "4",
367
+ "output": "20",
368
+ "cache_read": "0.4"
369
+ }
370
+ },
371
+ "gpt-5.6-terra": {
372
+ "input": 2,
373
+ "output": 12,
374
+ "cache_read": 0.2,
375
+ "exact": {
376
+ "input": "2",
377
+ "output": "12",
378
+ "cache_read": "0.2"
379
+ }
380
+ },
381
+ "gpt-5.6-luna": {
382
+ "input": 0.2,
383
+ "output": 1.2,
384
+ "cache_read": 0.02,
385
+ "exact": {
386
+ "input": "0.2",
387
+ "output": "1.2",
388
+ "cache_read": "0.02"
389
+ }
390
+ },
391
+ "gpt-5.6-cyber": {
392
+ "input": 12.5,
393
+ "output": 75,
394
+ "cache_read": 1.25,
395
+ "exact": {
396
+ "input": "12.5",
397
+ "output": "75",
398
+ "cache_read": "1.25"
399
+ }
400
+ },
401
+ "gpt-5.5": {
402
+ "input": 5,
403
+ "output": 30,
404
+ "cache_read": 0.5,
405
+ "exact": {
406
+ "input": "5",
407
+ "output": "30",
408
+ "cache_read": "0.5"
409
+ }
410
+ },
411
+ "gpt-5.5-pro": {
412
+ "input": 30,
413
+ "output": 180,
414
+ "exact": {
415
+ "input": "30",
416
+ "output": "180"
417
+ }
418
+ },
419
+ "gpt-5.4": {
420
+ "input": 2.5,
421
+ "output": 15,
422
+ "cache_read": 0.25,
423
+ "exact": {
424
+ "input": "2.5",
425
+ "output": "15",
426
+ "cache_read": "0.25"
427
+ }
428
+ },
429
+ "gpt-5.4-pro": {
430
+ "input": 30,
431
+ "output": 180,
432
+ "exact": {
433
+ "input": "30",
434
+ "output": "180"
435
+ }
436
+ },
437
+ "gpt-5.4-mini": {
438
+ "input": 0.75,
439
+ "output": 4.5,
440
+ "cache_read": 0.075,
441
+ "exact": {
442
+ "input": "0.75",
443
+ "output": "4.5",
444
+ "cache_read": "0.075"
445
+ }
446
+ },
447
+ "gpt-5.4-nano": {
448
+ "input": 0.2,
449
+ "output": 1.25,
450
+ "cache_read": 0.02,
451
+ "exact": {
452
+ "input": "0.2",
453
+ "output": "1.25",
454
+ "cache_read": "0.02"
455
+ }
456
+ },
457
+ "gpt-5.3-codex": {
458
+ "input": 1.75,
459
+ "output": 14,
460
+ "cache_read": 0.175,
461
+ "exact": {
462
+ "input": "1.75",
463
+ "output": "14",
464
+ "cache_read": "0.175"
465
+ }
466
+ },
467
+ "gpt-5.2": {
468
+ "input": 1.75,
469
+ "output": 14,
470
+ "cache_read": 0.175,
471
+ "exact": {
472
+ "input": "1.75",
473
+ "output": "14",
474
+ "cache_read": "0.175"
475
+ }
476
+ },
477
+ "gpt-5.2-pro": {
478
+ "input": 21,
479
+ "output": 168,
480
+ "exact": {
481
+ "input": "21",
482
+ "output": "168"
483
+ }
484
+ },
485
+ "gpt-5.1": {
486
+ "input": 1.25,
487
+ "output": 10,
488
+ "cache_read": 0.125,
489
+ "exact": {
490
+ "input": "1.25",
491
+ "output": "10",
492
+ "cache_read": "0.125"
493
+ }
494
+ },
495
+ "gpt-5": {
496
+ "input": 1.25,
497
+ "output": 10,
498
+ "cache_read": 0.125,
499
+ "exact": {
500
+ "input": "1.25",
501
+ "output": "10",
502
+ "cache_read": "0.125"
503
+ }
504
+ },
505
+ "gpt-5-mini": {
506
+ "input": 0.25,
507
+ "output": 2,
508
+ "cache_read": 0.025,
509
+ "exact": {
510
+ "input": "0.25",
511
+ "output": "2",
512
+ "cache_read": "0.025"
513
+ }
514
+ },
515
+ "gpt-5-nano": {
516
+ "input": 0.05,
517
+ "output": 0.4,
518
+ "cache_read": 0.005,
519
+ "exact": {
520
+ "input": "0.05",
521
+ "output": "0.4",
522
+ "cache_read": "0.005"
523
+ }
524
+ },
525
+ "gpt-5-pro": {
526
+ "input": 15,
527
+ "output": 120,
528
+ "exact": {
529
+ "input": "15",
530
+ "output": "120"
531
+ }
532
+ },
533
+ "chat-latest": {
534
+ "input": 5,
535
+ "output": 30,
536
+ "cache_read": 0.5,
537
+ "exact": {
538
+ "input": "5",
539
+ "output": "30",
540
+ "cache_read": "0.5"
541
+ }
542
+ },
543
+ "gpt-4.1": {
544
+ "input": 2,
545
+ "output": 8,
546
+ "cache_read": 0.5,
547
+ "exact": {
548
+ "input": "2",
549
+ "output": "8",
550
+ "cache_read": "0.5"
551
+ }
552
+ },
553
+ "gpt-4.1-mini": {
554
+ "input": 0.4,
555
+ "output": 1.6,
556
+ "cache_read": 0.1,
557
+ "exact": {
558
+ "input": "0.4",
559
+ "output": "1.6",
560
+ "cache_read": "0.1"
561
+ }
562
+ },
563
+ "gpt-4.1-nano": {
564
+ "input": 0.1,
565
+ "output": 0.4,
566
+ "cache_read": 0.025,
567
+ "exact": {
568
+ "input": "0.1",
569
+ "output": "0.4",
570
+ "cache_read": "0.025"
571
+ }
572
+ },
573
+ "gpt-4o": {
574
+ "input": 2.5,
575
+ "output": 10,
576
+ "cache_read": 1.25,
577
+ "exact": {
578
+ "input": "2.5",
579
+ "output": "10",
580
+ "cache_read": "1.25"
581
+ }
582
+ },
583
+ "gpt-4o-mini": {
584
+ "input": 0.15,
585
+ "output": 0.6,
586
+ "cache_read": 0.075,
587
+ "exact": {
588
+ "input": "0.15",
589
+ "output": "0.6",
590
+ "cache_read": "0.075"
591
+ }
592
+ },
593
+ "o4-mini": {
594
+ "input": 1.1,
595
+ "output": 4.4,
596
+ "cache_read": 0.275,
597
+ "exact": {
598
+ "input": "1.1",
599
+ "output": "4.4",
600
+ "cache_read": "0.275"
601
+ }
602
+ },
603
+ "o3": {
604
+ "input": 2,
605
+ "output": 8,
606
+ "cache_read": 0.5,
607
+ "exact": {
608
+ "input": "2",
609
+ "output": "8",
610
+ "cache_read": "0.5"
611
+ }
612
+ },
613
+ "o3-mini": {
614
+ "input": 1.1,
615
+ "output": 4.4,
616
+ "cache_read": 0.55,
617
+ "exact": {
618
+ "input": "1.1",
619
+ "output": "4.4",
620
+ "cache_read": "0.55"
621
+ }
622
+ },
623
+ "o3-pro": {
624
+ "input": 20,
625
+ "output": 80,
626
+ "exact": {
627
+ "input": "20",
628
+ "output": "80"
629
+ }
630
+ },
631
+ "computer-use-preview": {
632
+ "input": 3,
633
+ "output": 12,
634
+ "exact": {
635
+ "input": "3",
636
+ "output": "12"
637
+ },
638
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
639
+ },
640
+ "ft:gpt-3.5-turbo": {
641
+ "input": 3,
642
+ "output": 6,
643
+ "exact": {
644
+ "input": "3",
645
+ "output": "6"
646
+ },
647
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
648
+ },
649
+ "ft:gpt-3.5-turbo-0125": {
650
+ "input": 3,
651
+ "output": 6,
652
+ "exact": {
653
+ "input": "3",
654
+ "output": "6"
655
+ },
656
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
657
+ },
658
+ "ft:gpt-3.5-turbo-0613": {
659
+ "input": 3,
660
+ "output": 6,
661
+ "exact": {
662
+ "input": "3",
663
+ "output": "6"
664
+ },
665
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
666
+ },
667
+ "ft:gpt-3.5-turbo-1106": {
668
+ "input": 3,
669
+ "output": 6,
670
+ "exact": {
671
+ "input": "3",
672
+ "output": "6"
673
+ },
674
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
675
+ },
676
+ "ft:gpt-4-0613": {
677
+ "input": 30,
678
+ "output": 60,
679
+ "exact": {
680
+ "input": "30",
681
+ "output": "60"
682
+ },
683
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
684
+ },
685
+ "gpt-3.5-turbo": {
686
+ "input": 0.5,
687
+ "output": 1.5,
688
+ "exact": {
689
+ "input": "0.5",
690
+ "output": "1.5"
691
+ },
692
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
693
+ },
694
+ "gpt-3.5-turbo-0125": {
695
+ "input": 0.5,
696
+ "output": 1.5,
697
+ "exact": {
698
+ "input": "0.5",
699
+ "output": "1.5"
700
+ },
701
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
702
+ },
703
+ "gpt-3.5-turbo-1106": {
704
+ "input": 1,
705
+ "output": 2,
706
+ "exact": {
707
+ "input": "1",
708
+ "output": "2"
709
+ },
710
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
711
+ },
712
+ "gpt-3.5-turbo-16k": {
713
+ "input": 3,
714
+ "output": 4,
715
+ "exact": {
716
+ "input": "3",
717
+ "output": "4"
718
+ },
719
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
720
+ },
721
+ "gpt-4": {
722
+ "input": 30,
723
+ "output": 60,
724
+ "exact": {
725
+ "input": "30",
726
+ "output": "60"
727
+ },
728
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
729
+ },
730
+ "gpt-4-0613": {
731
+ "input": 30,
732
+ "output": 60,
733
+ "exact": {
734
+ "input": "30",
735
+ "output": "60"
736
+ },
737
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
738
+ },
739
+ "gpt-4-1106-preview": {
740
+ "input": 10,
741
+ "output": 30,
742
+ "exact": {
743
+ "input": "10",
744
+ "output": "30"
745
+ },
746
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
747
+ },
748
+ "gpt-4-turbo": {
749
+ "input": 10,
750
+ "output": 30,
751
+ "exact": {
752
+ "input": "10",
753
+ "output": "30"
754
+ },
755
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
756
+ },
757
+ "gpt-audio": {
758
+ "input": 2.5,
759
+ "output": 10,
760
+ "exact": {
761
+ "input": "2.5",
762
+ "output": "10"
763
+ },
764
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
765
+ },
766
+ "gpt-audio-1.5": {
767
+ "input": 2.5,
768
+ "output": 10,
769
+ "exact": {
770
+ "input": "2.5",
771
+ "output": "10"
772
+ },
773
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
774
+ },
775
+ "gpt-audio-mini": {
776
+ "input": 0.6,
777
+ "output": 2.4,
778
+ "exact": {
779
+ "input": "0.6",
780
+ "output": "2.4"
781
+ },
782
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
783
+ },
784
+ "gpt-4o-mini-search-preview": {
785
+ "input": 0.15,
786
+ "output": 0.6,
787
+ "cache_read": 0.075,
788
+ "exact": {
789
+ "input": "0.15",
790
+ "output": "0.6",
791
+ "cache_read": "0.075"
792
+ },
793
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
794
+ },
795
+ "gpt-4o-search-preview": {
796
+ "input": 2.5,
797
+ "output": 10,
798
+ "cache_read": 1.25,
799
+ "exact": {
800
+ "input": "2.5",
801
+ "output": "10",
802
+ "cache_read": "1.25"
803
+ },
804
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
805
+ },
806
+ "gpt-5-codex": {
807
+ "input": 1.25,
808
+ "output": 10,
809
+ "cache_read": 0.125,
810
+ "exact": {
811
+ "input": "1.25",
812
+ "output": "10",
813
+ "cache_read": "0.125"
814
+ },
815
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
816
+ },
817
+ "gpt-5.1-codex-mini": {
818
+ "input": 0.25,
819
+ "output": 2,
820
+ "cache_read": 0.025,
821
+ "exact": {
822
+ "input": "0.25",
823
+ "output": "2",
824
+ "cache_read": "0.025"
825
+ },
826
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
827
+ },
828
+ "gpt-5.1-codex-max": {
829
+ "input": 1.25,
830
+ "output": 10,
831
+ "cache_read": 0.125,
832
+ "exact": {
833
+ "input": "1.25",
834
+ "output": "10",
835
+ "cache_read": "0.125"
836
+ },
837
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
838
+ },
839
+ "gpt-5.1-codex": {
840
+ "input": 1.25,
841
+ "output": 10,
842
+ "cache_read": 0.125,
843
+ "exact": {
844
+ "input": "1.25",
845
+ "output": "10",
846
+ "cache_read": "0.125"
847
+ },
848
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
849
+ },
850
+ "gpt-5.1-chat-latest": {
851
+ "input": 1.25,
852
+ "output": 10,
853
+ "cache_read": 0.125,
854
+ "exact": {
855
+ "input": "1.25",
856
+ "output": "10",
857
+ "cache_read": "0.125"
858
+ },
859
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
860
+ },
861
+ "gpt-5.2-codex": {
862
+ "input": 1.75,
863
+ "output": 14,
864
+ "cache_read": 0.175,
865
+ "exact": {
866
+ "input": "1.75",
867
+ "output": "14",
868
+ "cache_read": "0.175"
869
+ },
870
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
871
+ },
872
+ "gpt-5.2-chat-latest": {
873
+ "input": 1.75,
874
+ "output": 14,
875
+ "cache_read": 0.175,
876
+ "exact": {
877
+ "input": "1.75",
878
+ "output": "14",
879
+ "cache_read": "0.175"
880
+ },
881
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
882
+ },
883
+ "gpt-5.6": {
884
+ "input": 4,
885
+ "output": 20,
886
+ "cache_read": 0.4,
887
+ "cache_write_5m": 5,
888
+ "exact": {
889
+ "input": "4",
890
+ "output": "20",
891
+ "cache_read": "0.4",
892
+ "cache_write_5m": "5"
893
+ },
894
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
895
+ },
896
+ "daybreak-red-latest": {
897
+ "input": 12.5,
898
+ "output": 75,
899
+ "cache_read": 1.25,
900
+ "cache_write_5m": 15.625,
901
+ "exact": {
902
+ "input": "12.5",
903
+ "output": "75",
904
+ "cache_read": "1.25",
905
+ "cache_write_5m": "15.625"
906
+ },
907
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
908
+ },
909
+ "gpt-daybreak-red-latest": {
910
+ "input": 12.5,
911
+ "output": 75,
912
+ "cache_read": 1.25,
913
+ "cache_write_5m": 15.625,
914
+ "exact": {
915
+ "input": "12.5",
916
+ "output": "75",
917
+ "cache_read": "1.25",
918
+ "cache_write_5m": "15.625"
919
+ },
920
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
921
+ },
922
+ "daybreak-blue-latest": {
923
+ "input": 4,
924
+ "output": 20,
925
+ "cache_read": 0.4,
926
+ "cache_write_5m": 5,
927
+ "exact": {
928
+ "input": "4",
929
+ "output": "20",
930
+ "cache_read": "0.4",
931
+ "cache_write_5m": "5"
932
+ },
933
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
934
+ },
935
+ "gpt-daybreak-blue-latest": {
936
+ "input": 4,
937
+ "output": 20,
938
+ "cache_read": 0.4,
939
+ "cache_write_5m": 5,
940
+ "exact": {
941
+ "input": "4",
942
+ "output": "20",
943
+ "cache_read": "0.4",
944
+ "cache_write_5m": "5"
945
+ },
946
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
947
+ },
948
+ "gpt-5-chat": {
949
+ "input": 1.25,
950
+ "output": 10,
951
+ "cache_read": 0.125,
952
+ "exact": {
953
+ "input": "1.25",
954
+ "output": "10",
955
+ "cache_read": "0.125"
956
+ },
957
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
958
+ },
959
+ "gpt-5-chat-latest": {
960
+ "input": 1.25,
961
+ "output": 10,
962
+ "cache_read": 0.125,
963
+ "exact": {
964
+ "input": "1.25",
965
+ "output": "10",
966
+ "cache_read": "0.125"
967
+ },
968
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
969
+ },
970
+ "gpt-5.3-chat-latest": {
971
+ "input": 1.75,
972
+ "output": 14,
973
+ "cache_read": 0.175,
974
+ "exact": {
975
+ "input": "1.75",
976
+ "output": "14",
977
+ "cache_read": "0.175"
978
+ },
979
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
980
+ },
981
+ "o1": {
982
+ "input": 15,
983
+ "output": 60,
984
+ "cache_read": 7.5,
985
+ "exact": {
986
+ "input": "15",
987
+ "output": "60",
988
+ "cache_read": "7.5"
989
+ },
990
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
991
+ },
992
+ "o1-pro": {
993
+ "input": 150,
994
+ "output": 600,
995
+ "exact": {
996
+ "input": "150",
997
+ "output": "600"
998
+ },
999
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1000
+ },
1001
+ "o3-deep-research": {
1002
+ "input": 10,
1003
+ "output": 40,
1004
+ "cache_read": 2.5,
1005
+ "exact": {
1006
+ "input": "10",
1007
+ "output": "40",
1008
+ "cache_read": "2.5"
1009
+ },
1010
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1011
+ },
1012
+ "o4-mini-deep-research": {
1013
+ "input": 2,
1014
+ "output": 8,
1015
+ "cache_read": 0.5,
1016
+ "exact": {
1017
+ "input": "2",
1018
+ "output": "8",
1019
+ "cache_read": "0.5"
1020
+ },
1021
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1022
+ },
1023
+ "gpt-5-search-api": {
1024
+ "input": 1.25,
1025
+ "output": 10,
1026
+ "cache_read": 0.125,
1027
+ "exact": {
1028
+ "input": "1.25",
1029
+ "output": "10",
1030
+ "cache_read": "0.125"
1031
+ },
1032
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1033
+ },
1034
+ "gpt-5.5-cyber": {
1035
+ "input": 12.5,
1036
+ "output": 75,
1037
+ "cache_read": 1.25,
1038
+ "exact": {
1039
+ "input": "12.5",
1040
+ "output": "75",
1041
+ "cache_read": "1.25"
1042
+ },
1043
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1044
+ },
1045
+ "gpt-5.5-cyber-preview": {
1046
+ "input": 12.5,
1047
+ "output": 75,
1048
+ "cache_read": 1.25,
1049
+ "exact": {
1050
+ "input": "12.5",
1051
+ "output": "75",
1052
+ "cache_read": "1.25"
1053
+ },
1054
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1055
+ },
1056
+ "gpt-rosalind-research": {
1057
+ "input": 5,
1058
+ "output": 25,
1059
+ "cache_read": 0.5,
1060
+ "exact": {
1061
+ "input": "5",
1062
+ "output": "25",
1063
+ "cache_read": "0.5"
1064
+ },
1065
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1066
+ },
1067
+ "gpt-rosalind-discovery": {
1068
+ "input": 5,
1069
+ "output": 25,
1070
+ "cache_read": 0.5,
1071
+ "exact": {
1072
+ "input": "5",
1073
+ "output": "25",
1074
+ "cache_read": "0.5"
1075
+ },
1076
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1077
+ }
78
1078
  }
79
1079
  },
80
1080
  "google": {
81
1081
  "verified": true,
82
- "source": "ai.google.dev/gemini-api/docs/pricing (2026-06)",
1082
+ "source": "ai.google.dev/gemini-api/docs/pricing (2.5 models read 2026-06; 3.x models read 2026-10-09, page updated 2026-10-07). Gemini 3.6-3.8 Flash carry the rates through 2026-12-31 (the page lists higher rates from 2027-01-01); gemini-3.1-pro-preview carries the rate for prompts of 200k tokens or fewer. gemini-3.1-pro is the family key for Antigravity's thinking-level names (gemini-3.1-pro-low, -high), at the same rate; those rows match by family, so they stay marked estimated.",
83
1083
  "models": {
84
- "gemini-2.5-pro": {"input": 1.25, "output": 10.0, "cache_read": 0.125, "exact": {"input": "1.25", "output": "10", "cache_read": "0.125"}},
85
- "gemini-2.5-flash": {"input": 0.3, "output": 2.5, "cache_read": 0.03, "exact": {"input": "0.3", "output": "2.5", "cache_read": "0.03"}},
86
- "gemini-2.5-flash-lite": {"input": 0.1, "output": 0.4, "cache_read": 0.01, "exact": {"input": "0.1", "output": "0.4", "cache_read": "0.01"}}
1084
+ "gemini-2.5-pro": {
1085
+ "input": 1.25,
1086
+ "output": 10,
1087
+ "cache_read": 0.125,
1088
+ "exact": {
1089
+ "input": "1.25",
1090
+ "output": "10",
1091
+ "cache_read": "0.125"
1092
+ }
1093
+ },
1094
+ "gemini-2.5-flash": {
1095
+ "input": 0.3,
1096
+ "output": 2.5,
1097
+ "cache_read": 0.03,
1098
+ "exact": {
1099
+ "input": "0.3",
1100
+ "output": "2.5",
1101
+ "cache_read": "0.03"
1102
+ }
1103
+ },
1104
+ "gemini-2.5-flash-lite": {
1105
+ "input": 0.1,
1106
+ "output": 0.4,
1107
+ "cache_read": 0.01,
1108
+ "exact": {
1109
+ "input": "0.1",
1110
+ "output": "0.4",
1111
+ "cache_read": "0.01"
1112
+ }
1113
+ },
1114
+ "gemini-3.8-flash": {
1115
+ "input": 0.75,
1116
+ "output": 3.75,
1117
+ "cache_read": 0.075,
1118
+ "exact": {
1119
+ "input": "0.75",
1120
+ "output": "3.75",
1121
+ "cache_read": "0.075"
1122
+ }
1123
+ },
1124
+ "gemini-3.7-flash": {
1125
+ "input": 0.75,
1126
+ "output": 3.75,
1127
+ "cache_read": 0.075,
1128
+ "exact": {
1129
+ "input": "0.75",
1130
+ "output": "3.75",
1131
+ "cache_read": "0.075"
1132
+ }
1133
+ },
1134
+ "gemini-3.6-flash": {
1135
+ "input": 0.75,
1136
+ "output": 3.75,
1137
+ "cache_read": 0.075,
1138
+ "exact": {
1139
+ "input": "0.75",
1140
+ "output": "3.75",
1141
+ "cache_read": "0.075"
1142
+ }
1143
+ },
1144
+ "gemini-3.5-flash": {
1145
+ "input": 1.5,
1146
+ "output": 9,
1147
+ "cache_read": 0.15,
1148
+ "exact": {
1149
+ "input": "1.5",
1150
+ "output": "9",
1151
+ "cache_read": "0.15"
1152
+ }
1153
+ },
1154
+ "gemini-3.5-flash-lite": {
1155
+ "input": 0.3,
1156
+ "output": 2.5,
1157
+ "cache_read": 0.03,
1158
+ "exact": {
1159
+ "input": "0.3",
1160
+ "output": "2.5",
1161
+ "cache_read": "0.03"
1162
+ }
1163
+ },
1164
+ "gemini-3.1-flash-lite": {
1165
+ "input": 0.25,
1166
+ "output": 1.5,
1167
+ "cache_read": 0.025,
1168
+ "exact": {
1169
+ "input": "0.25",
1170
+ "output": "1.5",
1171
+ "cache_read": "0.025"
1172
+ }
1173
+ },
1174
+ "gemini-3.1-pro-preview": {
1175
+ "input": 2,
1176
+ "output": 12,
1177
+ "cache_read": 0.2,
1178
+ "exact": {
1179
+ "input": "2",
1180
+ "output": "12",
1181
+ "cache_read": "0.2"
1182
+ }
1183
+ },
1184
+ "gemini-3.1-pro": {
1185
+ "input": 2,
1186
+ "output": 12,
1187
+ "cache_read": 0.2,
1188
+ "exact": {
1189
+ "input": "2",
1190
+ "output": "12",
1191
+ "cache_read": "0.2"
1192
+ }
1193
+ },
1194
+ "gemini-3-flash-preview": {
1195
+ "input": 0.5,
1196
+ "output": 3,
1197
+ "cache_read": 0.05,
1198
+ "exact": {
1199
+ "input": "0.5",
1200
+ "output": "3",
1201
+ "cache_read": "0.05"
1202
+ }
1203
+ },
1204
+ "gemini-robotics-er-2-preview": {
1205
+ "input": 1,
1206
+ "output": 5,
1207
+ "cache_read": 0.1,
1208
+ "exact": {
1209
+ "input": "1",
1210
+ "output": "5",
1211
+ "cache_read": "0.1"
1212
+ },
1213
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1214
+ },
1215
+ "gemini-3.1-flash-lite-preview": {
1216
+ "input": 0.25,
1217
+ "output": 1.5,
1218
+ "cache_read": 0.025,
1219
+ "exact": {
1220
+ "input": "0.25",
1221
+ "output": "1.5",
1222
+ "cache_read": "0.025"
1223
+ },
1224
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1225
+ },
1226
+ "deep-research-preview-04-2026": {
1227
+ "input": 2,
1228
+ "output": 12,
1229
+ "exact": {
1230
+ "input": "2",
1231
+ "output": "12"
1232
+ },
1233
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1234
+ },
1235
+ "deep-research-max-preview-04-2026": {
1236
+ "input": 2,
1237
+ "output": 12,
1238
+ "exact": {
1239
+ "input": "2",
1240
+ "output": "12"
1241
+ },
1242
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1243
+ },
1244
+ "deep-research-pro-preview-12-2025": {
1245
+ "input": 2,
1246
+ "output": 12,
1247
+ "exact": {
1248
+ "input": "2",
1249
+ "output": "12"
1250
+ },
1251
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1252
+ },
1253
+ "gemini-flash-latest": {
1254
+ "input": 0.75,
1255
+ "output": 3.75,
1256
+ "cache_read": 0.075,
1257
+ "exact": {
1258
+ "input": "0.75",
1259
+ "output": "3.75",
1260
+ "cache_read": "0.075"
1261
+ },
1262
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1263
+ },
1264
+ "gemini-flash-lite-latest": {
1265
+ "input": 0.3,
1266
+ "output": 2.5,
1267
+ "cache_read": 0.03,
1268
+ "exact": {
1269
+ "input": "0.3",
1270
+ "output": "2.5",
1271
+ "cache_read": "0.03"
1272
+ },
1273
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1274
+ },
1275
+ "gemini-2.5-computer-use-preview-10-2025": {
1276
+ "input": 1.25,
1277
+ "output": 10,
1278
+ "exact": {
1279
+ "input": "1.25",
1280
+ "output": "10"
1281
+ },
1282
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1283
+ },
1284
+ "gemini-omni-flash-preview": {
1285
+ "input": 1.5,
1286
+ "output": 9,
1287
+ "exact": {
1288
+ "input": "1.5",
1289
+ "output": "9"
1290
+ },
1291
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1292
+ },
1293
+ "gemini-3.1-pro-preview-customtools": {
1294
+ "input": 2,
1295
+ "output": 12,
1296
+ "cache_read": 0.2,
1297
+ "exact": {
1298
+ "input": "2",
1299
+ "output": "12",
1300
+ "cache_read": "0.2"
1301
+ },
1302
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1303
+ },
1304
+ "gemini-2.5-pro-preview-tts": {
1305
+ "input": 1,
1306
+ "output": 20,
1307
+ "cache_read": 0.125,
1308
+ "exact": {
1309
+ "input": "1",
1310
+ "output": "20",
1311
+ "cache_read": "0.125"
1312
+ },
1313
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1314
+ },
1315
+ "gemini-gemma-2-27b-it": {
1316
+ "input": 0.35,
1317
+ "output": 1.05,
1318
+ "exact": {
1319
+ "input": "0.35",
1320
+ "output": "1.05"
1321
+ },
1322
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1323
+ },
1324
+ "gemini-gemma-2-9b-it": {
1325
+ "input": 0.35,
1326
+ "output": 1.05,
1327
+ "exact": {
1328
+ "input": "0.35",
1329
+ "output": "1.05"
1330
+ },
1331
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1332
+ },
1333
+ "gemini-pro-latest": {
1334
+ "input": 2,
1335
+ "output": 12,
1336
+ "cache_read": 0.2,
1337
+ "exact": {
1338
+ "input": "2",
1339
+ "output": "12",
1340
+ "cache_read": "0.2"
1341
+ },
1342
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1343
+ },
1344
+ "gemini-exp-1206": {
1345
+ "input": 0.3,
1346
+ "output": 2.5,
1347
+ "cache_read": 0.03,
1348
+ "exact": {
1349
+ "input": "0.3",
1350
+ "output": "2.5",
1351
+ "cache_read": "0.03"
1352
+ },
1353
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1354
+ },
1355
+ "gemini-robotics-er-2-streaming-preview": {
1356
+ "input": 1,
1357
+ "output": 5,
1358
+ "exact": {
1359
+ "input": "1",
1360
+ "output": "5"
1361
+ },
1362
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1363
+ },
1364
+ "gemini-omni-1.1-flash": {
1365
+ "input": 1.5,
1366
+ "output": 9,
1367
+ "exact": {
1368
+ "input": "1.5",
1369
+ "output": "9"
1370
+ },
1371
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1372
+ },
1373
+ "gemini-4-argon": {
1374
+ "input": 2,
1375
+ "output": 10,
1376
+ "cache_read": 0.1,
1377
+ "exact": {
1378
+ "input": "2",
1379
+ "output": "10",
1380
+ "cache_read": "0.1"
1381
+ },
1382
+ "source": "public price list (LiteLLM model_prices_and_context_window.json, read 2026-10-17); not checked against the provider’s own pricing page"
1383
+ }
87
1384
  }
88
1385
  }
89
1386
  },
90
1387
  "fallbacks": {
91
1388
  "comment": "Used when a model name is unknown. Heuristic match by substring; otherwise the 'unknown' rate (conservative mid-tier) is applied and the request is flagged estimated=true.",
92
- "unknown": {"input": 3.0, "output": 15.0, "cache_read": 0.3, "exact": {"input": "3", "output": "15", "cache_read": "0.3"}}
1389
+ "unknown": {
1390
+ "input": 3,
1391
+ "output": 15,
1392
+ "cache_read": 0.3,
1393
+ "exact": {
1394
+ "input": "3",
1395
+ "output": "15",
1396
+ "cache_read": "0.3"
1397
+ }
1398
+ }
93
1399
  }
94
1400
  }