agent-cost-analyzer 0.0.0 → 0.16.1

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 (47) hide show
  1. package/LICENSE +21 -0
  2. package/README.md +72 -5
  3. package/THIRD-PARTY-NOTICES.md +3510 -0
  4. package/bin/agent-cost-analyzer.js +22 -0
  5. package/bin/node-gate.js +41 -0
  6. package/dist/cli.js +315313 -0
  7. package/dist/data/learn-scripts/cache-basics.json +163 -0
  8. package/dist/data/learn-scripts/cache-ttl-1-hour-breakpoint.json +176 -0
  9. package/dist/data/learn-scripts/cache-ttl-smoke-break.json +190 -0
  10. package/dist/data/learn-scripts/cascading-model-switch-then-ttl-lapse.json +121 -0
  11. package/dist/data/learn-scripts/clear.json +133 -0
  12. package/dist/data/learn-scripts/compaction.json +98 -0
  13. package/dist/data/learn-scripts/image-attachment-invalidation.json +108 -0
  14. package/dist/data/learn-scripts/inline-exploration-bloat.json +115 -0
  15. package/dist/data/learn-scripts/instructions-edit.json +99 -0
  16. package/dist/data/learn-scripts/mcp-tool-change.json +93 -0
  17. package/dist/data/learn-scripts/model-switch.json +88 -0
  18. package/dist/data/learn-scripts/reasoning-budget-toggle.json +98 -0
  19. package/dist/data/learn-scripts/rewind.json +139 -0
  20. package/dist/data/learn-scripts/session-forking-multi-branch.json +124 -0
  21. package/dist/data/learn-scripts/session-forking.json +99 -0
  22. package/dist/data/learn-scripts/silent-instructions-pullin.json +104 -0
  23. package/dist/data/learn-scripts/subagent-cheaper-model.json +70 -0
  24. package/dist/data/learn-scripts/subagent-session.json +70 -0
  25. package/dist/data/price-book/anthropic-api.json +662 -0
  26. package/dist/data/price-book/github-copilot.json +1402 -0
  27. package/dist/data/price-book/google-api.json +507 -0
  28. package/dist/data/price-book/openai-api.json +1184 -0
  29. package/dist/data/vendor-profiles/anthropic.json +568 -0
  30. package/dist/data/vendor-profiles/google.json +190 -0
  31. package/dist/data/vendor-profiles/microsoft.json +96 -0
  32. package/dist/data/vendor-profiles/moonshot.json +115 -0
  33. package/dist/data/vendor-profiles/openai.json +442 -0
  34. package/dist/data/vendor-profiles/xai.json +217 -0
  35. package/dist/mcp-apps/views.html +124 -0
  36. package/dist/web/assets/commit-mono-latin-400-normal-s0S3qwFW.woff +0 -0
  37. package/dist/web/assets/commit-mono-latin-400-normal-wzhe4RuD.woff2 +0 -0
  38. package/dist/web/assets/commit-mono-latin-700-normal-1-GU0IUE.woff +0 -0
  39. package/dist/web/assets/commit-mono-latin-700-normal-DU8mrtj2.woff2 +0 -0
  40. package/dist/web/assets/index-DeqVluBu.js +76 -0
  41. package/dist/web/assets/index-EJpifWDV.css +1 -0
  42. package/dist/web/assets/source-serif-4-latin-400-normal-C1O10bxN.woff +0 -0
  43. package/dist/web/assets/source-serif-4-latin-400-normal-DJ5YJwmz.woff2 +0 -0
  44. package/dist/web/assets/source-serif-4-latin-600-normal-DeJomR3S.woff +0 -0
  45. package/dist/web/assets/source-serif-4-latin-600-normal-DouSKlru.woff2 +0 -0
  46. package/dist/web/index.html +32 -0
  47. package/package.json +18 -4
@@ -0,0 +1,507 @@
1
+ {
2
+ "channel": "google-api",
3
+ "sources": [
4
+ {
5
+ "id": "google-api-pricing-gemini-4-argon",
6
+ "title": "Gemini Developer API pricing: Gemini 4 Argon (Standard tab, Paid Tier column; rows joined by ' | ')",
7
+ "url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-4-argon",
8
+ "quote": "Input price: $2.00 through November 30, 2026. $4.00 starting December 1, 2026. | Output price (including thinking tokens): $10.00 through November 30, 2026. $20.00 starting December 1, 2026. | Context caching price: $0.10 through November 30, 2026. $0.20 starting December 1, 2026. Implicit caching only (explicit caching is not supported).",
9
+ "checkedAt": "2026-11-06"
10
+ },
11
+ {
12
+ "id": "google-api-pricing-gemini-3.8-flash",
13
+ "title": "Gemini Developer API pricing: Gemini 3.8 Flash (Standard tab, Paid Tier column; rows joined by ' | ')",
14
+ "url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-flash",
15
+ "quote": "Input price: $0.75 through December 31, 2026. $1.50 starting January 1, 2027. | Output price (including thinking tokens): $3.75 through December 31, 2026. $7.50 starting January 1, 2027. | Context caching price: $0.075 through December 31, 2026. $0.15 starting January 1, 2027. $0.50 / 1,000,000 tokens per hour (storage price) through December 31, 2026. $1.00 / 1,000,000 tokens per hour (storage price) starting January 1, 2027.",
16
+ "checkedAt": "2026-11-06"
17
+ },
18
+ {
19
+ "id": "google-api-pricing-gemini-3.6-flash",
20
+ "title": "Gemini Developer API pricing: Gemini 3.6 Flash (Standard tab, Paid Tier column; rows joined by ' | ')",
21
+ "url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.6-flash",
22
+ "quote": "Input price: $0.75 through December 31, 2026. $1.50 starting January 1, 2027. | Output price (including thinking tokens): $3.75 through December 31, 2026. $7.50 starting January 1, 2027. | Context caching price: $0.075 through December 31, 2026. $0.15 starting January 1, 2027. $0.50 / 1,000,000 tokens per hour (storage price) through December 31, 2026. $1.00 / 1,000,000 tokens per hour (storage price) starting January 1, 2027.",
23
+ "checkedAt": "2026-11-06"
24
+ },
25
+ {
26
+ "id": "google-api-pricing-gemini-3.5-flash-lite",
27
+ "title": "Gemini Developer API pricing: Gemini 3.5 Flash-Lite (Standard tab, Paid Tier column; rows joined by ' | ')",
28
+ "url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash-lite",
29
+ "quote": "Input price: $0.30 (text / image / video / audio) | Output price (including thinking tokens): $2.50 | Context caching price: $0.03 $1.00 / 1,000,000 tokens per hour (storage price)",
30
+ "checkedAt": "2026-11-06"
31
+ },
32
+ {
33
+ "id": "google-api-pricing-gemini-3.1-flash-lite",
34
+ "title": "Gemini Developer API pricing: Gemini 3.1 Flash-Lite (Standard tab, Paid Tier column; rows joined by ' | ')",
35
+ "url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite",
36
+ "quote": "Input price: $0.25 (text / image / video) $0.50 (audio) | Output price (including thinking tokens): $1.50 | Context caching price: $0.025 (text / image / video) $0.05 (audio) $1.00 / 1,000,000 tokens per hour (storage price)",
37
+ "checkedAt": "2026-11-06"
38
+ },
39
+ {
40
+ "id": "google-api-pricing-gemini-3.1-pro-preview",
41
+ "title": "Gemini Developer API pricing: Gemini 3.1 Pro Preview (Standard tab, Paid Tier column; rows joined by ' | ')",
42
+ "url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview",
43
+ "quote": "Input price: $2.00, prompts <= 200k tokens $4.00, prompts > 200k tokens | Output price (including thinking tokens): $12.00, prompts <= 200k tokens $18.00, prompts > 200k | Context caching price: $0.20, prompts <= 200k tokens $0.40, prompts > 200k $4.50 / 1,000,000 tokens per hour (storage price)",
44
+ "checkedAt": "2026-11-06"
45
+ },
46
+ {
47
+ "id": "google-api-pricing-gemini-3-flash-preview",
48
+ "title": "Gemini Developer API pricing: Gemini 3 Flash Preview (Standard tab, Paid Tier column; rows joined by ' | ')",
49
+ "url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview",
50
+ "quote": "Input price: $0.50 (text / image / video) $1.00 (audio) | Output price (including thinking tokens): $3.00 | Context caching price: $0.05 (text / image / video) $0.10 (audio) $1.00 / 1,000,000 tokens per hour (storage price)",
51
+ "checkedAt": "2026-11-06"
52
+ },
53
+ {
54
+ "id": "google-api-pricing-gemini-2.5-pro",
55
+ "title": "Gemini Developer API pricing: Gemini 2.5 Pro (Standard tab, Paid Tier column; rows joined by ' | ')",
56
+ "url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro",
57
+ "quote": "Input price: $1.25, prompts <= 200k tokens $2.50, prompts > 200k tokens | Output price (including thinking tokens): $10.00, prompts <= 200k tokens $15.00, prompts > 200k | Context caching price: $0.125, prompts <= 200k tokens $0.25, prompts > 200k $4.50 / 1,000,000 tokens per hour (storage price)",
58
+ "checkedAt": "2026-11-06"
59
+ },
60
+ {
61
+ "id": "google-api-pricing-gemini-2.5-flash",
62
+ "title": "Gemini Developer API pricing: Gemini 2.5 Flash (Standard tab, Paid Tier column; rows joined by ' | ')",
63
+ "url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash",
64
+ "quote": "Input price: $0.30 (text / image / video) $1.00 (audio) | Output price (including thinking tokens): $2.50 | Context caching price: $0.03 (text / image / video) $0.1 (audio) $1.00 / 1,000,000 tokens per hour (storage price)",
65
+ "checkedAt": "2026-11-06"
66
+ },
67
+ {
68
+ "id": "google-api-pricing-gemini-2.5-flash-lite",
69
+ "title": "Gemini Developer API pricing: Gemini 2.5 Flash-Lite (Standard tab, Paid Tier column; rows joined by ' | ')",
70
+ "url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite",
71
+ "quote": "Input price (text, image, video): $0.10 (text / image / video) $0.30 (audio) | Output price (including thinking tokens): $0.40 | Context caching price: $0.01 (text / image / video) $0.03 (audio) $1.00 / 1,000,000 tokens per hour (storage price)",
72
+ "checkedAt": "2026-11-06"
73
+ },
74
+ {
75
+ "id": "google-api-pricing-gemini-2.5-pro-routing",
76
+ "title": "Gemini Developer API pricing: Gemini 2.5 Pro deprecation notice",
77
+ "url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro",
78
+ "quote": "Effective December 1, 2026, all API requests to `gemini-2.5-pro` will automatically route to Gemini 3.8 Flash (`gemini-3.8-flash`) and be billed at Gemini 3.8 Flash rates.",
79
+ "checkedAt": "2026-11-06"
80
+ },
81
+ {
82
+ "id": "google-api-pricing-gemini-2.5-flash-routing",
83
+ "title": "Gemini Developer API pricing: Gemini 2.5 Flash deprecation notice",
84
+ "url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash",
85
+ "quote": "Effective December 1, 2026, all API requests to `gemini-2.5-flash` will automatically route to Gemini 3.5 Flash-Lite (`gemini-3.5-flash-lite`)",
86
+ "checkedAt": "2026-11-06"
87
+ },
88
+ {
89
+ "id": "google-api-notes-2026-11-02-gemini-2.5-deprecation",
90
+ "title": "Gemini API release notes, November 2, 2026 (Gemini 2.5 Pro and 2.5 Flash deprecation)",
91
+ "url": "https://ai.google.dev/gemini-api/docs/changelog#11-02-2026",
92
+ "quote": "Effective December 1, 2026, all API requests to `gemini-2.5-pro` will automatically route to `gemini-3.8-flash` and be billed at Gemini 3.8 Flash rates. ... all API requests to `gemini-2.5-flash` will automatically route to `gemini-3.5-flash-lite` and be billed at Gemini 3.5 Flash-Lite rates.",
93
+ "checkedAt": "2026-11-06"
94
+ },
95
+ {
96
+ "id": "google-api-notes-2026-10-13-gemini-4-argon",
97
+ "title": "Gemini API release notes, October 13, 2026 (Gemini 4 Argon GA)",
98
+ "url": "https://ai.google.dev/gemini-api/docs/changelog#10-13-2026",
99
+ "quote": "Gemini 4 Argon (`gemini-4-argon`) generally available (GA): Released Gemini 4 Argon (`gemini-4-argon`), our most capable model built for complex coding, agentic, math, and science tasks.",
100
+ "checkedAt": "2026-11-06"
101
+ },
102
+ {
103
+ "id": "google-api-latest-model-gemini-4-argon-pricing",
104
+ "title": "What's new in Gemini 4 Argon: Pricing",
105
+ "url": "https://ai.google.dev/gemini-api/docs/latest-model#pricing",
106
+ "quote": "Gemini 4 Argon is available at introductory pricing through November 30, 2026: Input tokens: $2.00 per 1M tokens ($4.00 starting December 1, 2026) Cached input tokens: Implicit caching discounts cached input by 95%, to $0.10 per 1M tokens ($0.20 starting December 1, 2026). Output tokens, including thinking tokens: $10.00 per 1M tokens ($20.00 starting December 1, 2026)",
107
+ "checkedAt": "2026-11-06"
108
+ },
109
+ {
110
+ "id": "google-api-notes-2026-09-02-gemini-3.8-flash",
111
+ "title": "Gemini API release notes, September 2, 2026 (Gemini 3.8 Flash GA)",
112
+ "url": "https://ai.google.dev/gemini-api/docs/changelog#09-02-2026",
113
+ "quote": "Gemini 3.8 Flash generally available (GA): Released `gemini-3.8-flash`, our most intelligent Flash model",
114
+ "checkedAt": "2026-11-06"
115
+ },
116
+ {
117
+ "id": "google-api-whats-new-3.8-introductory-pricing",
118
+ "title": "What's new in Gemini 3.8 Flash: introductory pricing",
119
+ "url": "https://ai.google.dev/gemini-api/docs/whats-new-gemini-3.8",
120
+ "quote": "Introductory pricing: Gemini 3.8 Flash is available at an introductory rate of $0.75/1M input tokens and $3.75/1M output tokens through December 31, 2026. Standard pricing of $1.50/1M input tokens and $7.50/1M output tokens takes effect January 1, 2027.",
121
+ "checkedAt": "2026-11-06"
122
+ },
123
+ {
124
+ "id": "google-api-whats-new-3.8-pricing-3.6-flash",
125
+ "title": "What's new in Gemini 3.8 Flash: Pricing (Gemini 3.8 Flash and Gemini 3.6 Flash)",
126
+ "url": "https://ai.google.dev/gemini-api/docs/whats-new-gemini-3.8#pricing",
127
+ "quote": "Take advantage of introductory pricing across Google AI Studio and Gemini Enterprise Agent Platform through December 31, 2026 for Gemini 3.8 Flash and Gemini 3.6 Flash. Standard pricing takes effect January 1, 2027.",
128
+ "checkedAt": "2026-11-06"
129
+ },
130
+ {
131
+ "id": "google-api-notes-2026-07-21-gemini-3.6-3.5-lite",
132
+ "title": "Gemini API release notes, July 21, 2026 (Gemini 3.6 Flash and Gemini 3.5 Flash-Lite GA)",
133
+ "url": "https://ai.google.dev/gemini-api/docs/changelog#07-21-2026",
134
+ "quote": "Gemini 3.6 Flash and Gemini 3.5 Flash-Lite generally available (GA): Released stable, production-ready versions of our latest 3.x Flash models",
135
+ "checkedAt": "2026-11-06"
136
+ },
137
+ {
138
+ "id": "google-api-whats-new-3.6-launch-prices",
139
+ "title": "What's new in Gemini 3.6 Flash and 3.5 Flash-Lite: New models table (launch prices)",
140
+ "url": "https://ai.google.dev/gemini-api/docs/whats-new-gemini-3.6#new-models",
141
+ "quote": "| Gemini 3.6 Flash | `gemini-3.6-flash` | `medium` | $1.50/1M input tokens and $7.50/1M output tokens | ... | Gemini 3.5 Flash-Lite | `gemini-3.5-flash-lite` | `minimal` | $0.30/1M input tokens and $2.50/1M output tokens |",
142
+ "checkedAt": "2026-11-06"
143
+ },
144
+ {
145
+ "id": "google-api-caching-implicit",
146
+ "title": "Gemini API: Context caching (implicit caching)",
147
+ "url": "https://ai.google.dev/gemini-api/docs/caching#implicit-caching",
148
+ "quote": "Implicit caching is enabled by default for all Gemini 2.5 and newer models. ... We automatically pass on cost savings if your request hits caches.",
149
+ "checkedAt": "2026-11-06"
150
+ },
151
+ {
152
+ "id": "google-api-caching-no-explicit-argon",
153
+ "title": "Gemini API: Context caching (explicit caching support)",
154
+ "url": "https://ai.google.dev/gemini-api/docs/caching",
155
+ "quote": "Explicit caching (manually creating and managing cache objects) is not supported in the Interactions API, or for Gemini 4 Argon and onward.",
156
+ "checkedAt": "2026-11-06"
157
+ }
158
+ ],
159
+ "versions": [
160
+ {
161
+ "id": "google-api:gemini-4-argon:2026-10-13",
162
+ "channel": "google-api",
163
+ "modelId": "gemini-4-argon",
164
+ "currency": "USD",
165
+ "effectiveFrom": "2026-10-13",
166
+ "effectiveTo": "2026-12-01",
167
+ "tiers": [
168
+ {
169
+ "inputUsdPerM": 2,
170
+ "cachedInputUsdPerM": 0.1,
171
+ "cacheWriteUsdPerM": null,
172
+ "outputUsdPerM": 10
173
+ }
174
+ ],
175
+ "kind": "promo",
176
+ "promoEndsAt": "2026-11-30",
177
+ "sourceIds": [
178
+ "google-api-pricing-gemini-4-argon",
179
+ "google-api-latest-model-gemini-4-argon-pricing",
180
+ "google-api-notes-2026-10-13-gemini-4-argon",
181
+ "google-api-caching-no-explicit-argon"
182
+ ],
183
+ "note": "Launched 2026-10-13 (release notes) at an introductory price through 2026-11-30, per the Gemini 4 Argon guide and today's pricing page; no earlier price. Implicit caching only (no explicit caches, so no storage price); cached input is 95% off input. Not on the free tier. Google states dates, not times; boundaries are 00:00 UTC. Gemini Developer API paid tier, Standard inference, text/image/video input prices; free tier, Batch, Flex, Priority, audio input, Vertex AI / Gemini Enterprise Agent Platform and grounding prices are not modelled. cacheWriteUsdPerM is null: Gemini has no per-token cache write price (explicit cache creation bills its tokens at the input price)."
184
+ },
185
+ {
186
+ "id": "google-api:gemini-4-argon:2026-12-01",
187
+ "channel": "google-api",
188
+ "modelId": "gemini-4-argon",
189
+ "currency": "USD",
190
+ "effectiveFrom": "2026-12-01",
191
+ "tiers": [
192
+ {
193
+ "inputUsdPerM": 4,
194
+ "cachedInputUsdPerM": 0.2,
195
+ "cacheWriteUsdPerM": null,
196
+ "outputUsdPerM": 20
197
+ }
198
+ ],
199
+ "kind": "list",
200
+ "sourceIds": [
201
+ "google-api-pricing-gemini-4-argon",
202
+ "google-api-latest-model-gemini-4-argon-pricing",
203
+ "google-api-caching-no-explicit-argon"
204
+ ],
205
+ "note": "Scheduled standard price from 2026-12-01 (\"starting December 1, 2026\"), as stated on today's pricing page and in the Gemini 4 Argon guide. Implicit caching only. Google states dates, not times; boundaries are 00:00 UTC. Gemini Developer API paid tier, Standard inference, text/image/video input prices; free tier, Batch, Flex, Priority, audio input, Vertex AI / Gemini Enterprise Agent Platform and grounding prices are not modelled. cacheWriteUsdPerM is null: Gemini has no per-token cache write price (explicit cache creation bills its tokens at the input price)."
206
+ },
207
+ {
208
+ "id": "google-api:gemini-3.8-flash:2026-10-01",
209
+ "channel": "google-api",
210
+ "modelId": "gemini-3.8-flash",
211
+ "currency": "USD",
212
+ "effectiveFrom": "2026-10-01",
213
+ "effectiveTo": "2027-01-01",
214
+ "tiers": [
215
+ {
216
+ "inputUsdPerM": 0.75,
217
+ "cachedInputUsdPerM": 0.075,
218
+ "cacheWriteUsdPerM": null,
219
+ "outputUsdPerM": 3.75
220
+ }
221
+ ],
222
+ "kind": "promo",
223
+ "promoEndsAt": "2026-12-31",
224
+ "sourceIds": [
225
+ "google-api-pricing-gemini-3.8-flash",
226
+ "google-api-whats-new-3.8-introductory-pricing",
227
+ "google-api-notes-2026-09-02-gemini-3.8-flash",
228
+ "google-api-caching-implicit"
229
+ ],
230
+ "note": "In force from 2026-10-01: launched 2026-09-02 (release notes), and its guide gives an introductory rate of $0.75/$3.75 from launch through 2026-12-31; today's pricing page lists the same, and no release note records a change in between. The cached input price ($0.075) is from today's pricing page only, under the same introductory period. Explicit context caching also bills storage at $0.50 per 1M tokens per hour, which the tiers can't hold. Google states dates, not times; boundaries are 00:00 UTC. Gemini Developer API paid tier, Standard inference, text/image/video input prices; free tier, Batch, Flex, Priority, audio input, Vertex AI / Gemini Enterprise Agent Platform and grounding prices are not modelled. cacheWriteUsdPerM is null: Gemini has no per-token cache write price (explicit cache creation bills its tokens at the input price)."
231
+ },
232
+ {
233
+ "id": "google-api:gemini-3.8-flash:2027-01-01",
234
+ "channel": "google-api",
235
+ "modelId": "gemini-3.8-flash",
236
+ "currency": "USD",
237
+ "effectiveFrom": "2027-01-01",
238
+ "tiers": [
239
+ {
240
+ "inputUsdPerM": 1.5,
241
+ "cachedInputUsdPerM": 0.15,
242
+ "cacheWriteUsdPerM": null,
243
+ "outputUsdPerM": 7.5
244
+ }
245
+ ],
246
+ "kind": "list",
247
+ "sourceIds": [
248
+ "google-api-pricing-gemini-3.8-flash",
249
+ "google-api-whats-new-3.8-introductory-pricing"
250
+ ],
251
+ "note": "Scheduled standard price from 2027-01-01 (\"Standard pricing ... takes effect January 1, 2027\"). Explicit context caching also bills storage at $1.00 per 1M tokens per hour, which the tiers can't hold. Google states dates, not times; boundaries are 00:00 UTC. Gemini Developer API paid tier, Standard inference, text/image/video input prices; free tier, Batch, Flex, Priority, audio input, Vertex AI / Gemini Enterprise Agent Platform and grounding prices are not modelled. cacheWriteUsdPerM is null: Gemini has no per-token cache write price (explicit cache creation bills its tokens at the input price)."
252
+ },
253
+ {
254
+ "id": "google-api:gemini-3.6-flash:2026-11-06",
255
+ "channel": "google-api",
256
+ "modelId": "gemini-3.6-flash",
257
+ "currency": "USD",
258
+ "effectiveFrom": "2026-11-06",
259
+ "effectiveTo": "2027-01-01",
260
+ "tiers": [
261
+ {
262
+ "inputUsdPerM": 0.75,
263
+ "cachedInputUsdPerM": 0.075,
264
+ "cacheWriteUsdPerM": null,
265
+ "outputUsdPerM": 3.75
266
+ }
267
+ ],
268
+ "kind": "promo",
269
+ "promoEndsAt": "2026-12-31",
270
+ "sourceIds": [
271
+ "google-api-pricing-gemini-3.6-flash",
272
+ "google-api-whats-new-3.8-pricing-3.6-flash",
273
+ "google-api-whats-new-3.6-launch-prices"
274
+ ],
275
+ "note": "Introductory price through 2026-12-31. Only today's pricing page (checked 2026-11-06) gives this price; no dated Google source earlier in the window was found (the release notes carry no prices for it), so earlier turns price as unknown. Launched 2026-07-21 at $1.50/$7.50 (launch guide); Google has since put it on introductory pricing but does not say when, so October turns stay unknown. Explicit context caching also bills storage at $0.50 per 1M tokens per hour, which the tiers can't hold. Google states dates, not times; boundaries are 00:00 UTC. Gemini Developer API paid tier, Standard inference, text/image/video input prices; free tier, Batch, Flex, Priority, audio input, Vertex AI / Gemini Enterprise Agent Platform and grounding prices are not modelled. cacheWriteUsdPerM is null: Gemini has no per-token cache write price (explicit cache creation bills its tokens at the input price)."
276
+ },
277
+ {
278
+ "id": "google-api:gemini-3.6-flash:2027-01-01",
279
+ "channel": "google-api",
280
+ "modelId": "gemini-3.6-flash",
281
+ "currency": "USD",
282
+ "effectiveFrom": "2027-01-01",
283
+ "tiers": [
284
+ {
285
+ "inputUsdPerM": 1.5,
286
+ "cachedInputUsdPerM": 0.15,
287
+ "cacheWriteUsdPerM": null,
288
+ "outputUsdPerM": 7.5
289
+ }
290
+ ],
291
+ "kind": "list",
292
+ "sourceIds": [
293
+ "google-api-pricing-gemini-3.6-flash",
294
+ "google-api-whats-new-3.8-pricing-3.6-flash"
295
+ ],
296
+ "note": "Scheduled standard price from 2027-01-01 (\"starting January 1, 2027\"). Explicit context caching also bills storage at $1.00 per 1M tokens per hour, which the tiers can't hold. Google states dates, not times; boundaries are 00:00 UTC. Gemini Developer API paid tier, Standard inference, text/image/video input prices; free tier, Batch, Flex, Priority, audio input, Vertex AI / Gemini Enterprise Agent Platform and grounding prices are not modelled. cacheWriteUsdPerM is null: Gemini has no per-token cache write price (explicit cache creation bills its tokens at the input price)."
297
+ },
298
+ {
299
+ "id": "google-api:gemini-3.5-flash-lite:2026-10-01",
300
+ "channel": "google-api",
301
+ "modelId": "gemini-3.5-flash-lite",
302
+ "currency": "USD",
303
+ "effectiveFrom": "2026-10-01",
304
+ "tiers": [
305
+ {
306
+ "inputUsdPerM": 0.3,
307
+ "cachedInputUsdPerM": 0.03,
308
+ "cacheWriteUsdPerM": null,
309
+ "outputUsdPerM": 2.5
310
+ }
311
+ ],
312
+ "kind": "list",
313
+ "sourceIds": [
314
+ "google-api-pricing-gemini-3.5-flash-lite",
315
+ "google-api-whats-new-3.6-launch-prices",
316
+ "google-api-notes-2026-07-21-gemini-3.6-3.5-lite"
317
+ ],
318
+ "note": "In force from 2026-10-01: launched 2026-07-21 (release notes) at $0.30/$2.50 per its launch guide, today's pricing page lists the same, and no release note records a change in between. The cached input price ($0.03) is from today's pricing page only. One price for text, image, video and audio input. Explicit context caching also bills storage at $1.00 per 1M tokens per hour, which the tiers can't hold. Gemini Developer API paid tier, Standard inference, text/image/video input prices; free tier, Batch, Flex, Priority, audio input, Vertex AI / Gemini Enterprise Agent Platform and grounding prices are not modelled. cacheWriteUsdPerM is null: Gemini has no per-token cache write price (explicit cache creation bills its tokens at the input price)."
319
+ },
320
+ {
321
+ "id": "google-api:gemini-3.1-flash-lite:2026-11-06",
322
+ "channel": "google-api",
323
+ "modelId": "gemini-3.1-flash-lite",
324
+ "currency": "USD",
325
+ "effectiveFrom": "2026-11-06",
326
+ "tiers": [
327
+ {
328
+ "inputUsdPerM": 0.25,
329
+ "cachedInputUsdPerM": 0.025,
330
+ "cacheWriteUsdPerM": null,
331
+ "outputUsdPerM": 1.5
332
+ }
333
+ ],
334
+ "kind": "list",
335
+ "sourceIds": [
336
+ "google-api-pricing-gemini-3.1-flash-lite"
337
+ ],
338
+ "note": "GA since 2026-05-07 (release notes). Only today's pricing page (checked 2026-11-06) gives this price; no dated Google source earlier in the window was found (the release notes carry no prices for it), so earlier turns price as unknown. Explicit context caching also bills storage at $1.00 per 1M tokens per hour, which the tiers can't hold. Gemini Developer API paid tier, Standard inference, text/image/video input prices; free tier, Batch, Flex, Priority, audio input, Vertex AI / Gemini Enterprise Agent Platform and grounding prices are not modelled. cacheWriteUsdPerM is null: Gemini has no per-token cache write price (explicit cache creation bills its tokens at the input price)."
339
+ },
340
+ {
341
+ "id": "google-api:gemini-3.1-pro-preview:2026-11-06",
342
+ "channel": "google-api",
343
+ "modelId": "gemini-3.1-pro-preview",
344
+ "currency": "USD",
345
+ "effectiveFrom": "2026-11-06",
346
+ "tiers": [
347
+ {
348
+ "maxInputTokens": 200000,
349
+ "inputUsdPerM": 2,
350
+ "cachedInputUsdPerM": 0.2,
351
+ "cacheWriteUsdPerM": null,
352
+ "outputUsdPerM": 12
353
+ },
354
+ {
355
+ "inputUsdPerM": 4,
356
+ "cachedInputUsdPerM": 0.4,
357
+ "cacheWriteUsdPerM": null,
358
+ "outputUsdPerM": 18
359
+ }
360
+ ],
361
+ "kind": "list",
362
+ "sourceIds": [
363
+ "google-api-pricing-gemini-3.1-pro-preview"
364
+ ],
365
+ "note": "Released 2026-02-19 (release notes). Only today's pricing page (checked 2026-11-06) gives this price; no dated Google source earlier in the window was found (the release notes carry no prices for it), so earlier turns price as unknown. Priced by prompt length: the first tier covers prompts up to 200k tokens. The pricing page gives gemini-3.1-pro-preview-customtools the same prices (not listed separately here). Explicit context caching also bills storage at $4.50 per 1M tokens per hour, which the tiers can't hold. Gemini Developer API paid tier, Standard inference, text/image/video input prices; free tier, Batch, Flex, Priority, audio input, Vertex AI / Gemini Enterprise Agent Platform and grounding prices are not modelled. cacheWriteUsdPerM is null: Gemini has no per-token cache write price (explicit cache creation bills its tokens at the input price)."
366
+ },
367
+ {
368
+ "id": "google-api:gemini-3-flash-preview:2026-11-06",
369
+ "channel": "google-api",
370
+ "modelId": "gemini-3-flash-preview",
371
+ "currency": "USD",
372
+ "effectiveFrom": "2026-11-06",
373
+ "tiers": [
374
+ {
375
+ "inputUsdPerM": 0.5,
376
+ "cachedInputUsdPerM": 0.05,
377
+ "cacheWriteUsdPerM": null,
378
+ "outputUsdPerM": 3
379
+ }
380
+ ],
381
+ "kind": "list",
382
+ "sourceIds": [
383
+ "google-api-pricing-gemini-3-flash-preview"
384
+ ],
385
+ "note": "Launched 2025-12-17 (release notes). Only today's pricing page (checked 2026-11-06) gives this price; no dated Google source earlier in the window was found (the release notes carry no prices for it), so earlier turns price as unknown. Explicit context caching also bills storage at $1.00 per 1M tokens per hour, which the tiers can't hold. Gemini Developer API paid tier, Standard inference, text/image/video input prices; free tier, Batch, Flex, Priority, audio input, Vertex AI / Gemini Enterprise Agent Platform and grounding prices are not modelled. cacheWriteUsdPerM is null: Gemini has no per-token cache write price (explicit cache creation bills its tokens at the input price)."
386
+ },
387
+ {
388
+ "id": "google-api:gemini-2.5-pro:2026-11-06",
389
+ "channel": "google-api",
390
+ "modelId": "gemini-2.5-pro",
391
+ "currency": "USD",
392
+ "effectiveFrom": "2026-11-06",
393
+ "effectiveTo": "2026-12-01",
394
+ "tiers": [
395
+ {
396
+ "maxInputTokens": 200000,
397
+ "inputUsdPerM": 1.25,
398
+ "cachedInputUsdPerM": 0.125,
399
+ "cacheWriteUsdPerM": null,
400
+ "outputUsdPerM": 10
401
+ },
402
+ {
403
+ "inputUsdPerM": 2.5,
404
+ "cachedInputUsdPerM": 0.25,
405
+ "cacheWriteUsdPerM": null,
406
+ "outputUsdPerM": 15
407
+ }
408
+ ],
409
+ "kind": "list",
410
+ "sourceIds": [
411
+ "google-api-pricing-gemini-2.5-pro",
412
+ "google-api-pricing-gemini-2.5-pro-routing",
413
+ "google-api-notes-2026-11-02-gemini-2.5-deprecation"
414
+ ],
415
+ "note": "Only today's pricing page (checked 2026-11-06) gives this price; no dated Google source earlier in the window was found (the release notes carry no prices for it), so earlier turns price as unknown. Priced by prompt length: the first tier covers prompts up to 200k tokens. Deprecated 2026-11-02; from 2026-12-01 requests route to gemini-3.8-flash and are billed at its rates, so this version ends then. Explicit context caching also bills storage at $4.50 per 1M tokens per hour, which the tiers can't hold. Google states dates, not times; boundaries are 00:00 UTC. Gemini Developer API paid tier, Standard inference, text/image/video input prices; free tier, Batch, Flex, Priority, audio input, Vertex AI / Gemini Enterprise Agent Platform and grounding prices are not modelled. cacheWriteUsdPerM is null: Gemini has no per-token cache write price (explicit cache creation bills its tokens at the input price)."
416
+ },
417
+ {
418
+ "id": "google-api:gemini-2.5-pro:2026-12-01",
419
+ "channel": "google-api",
420
+ "modelId": "gemini-2.5-pro",
421
+ "currency": "USD",
422
+ "effectiveFrom": "2026-12-01",
423
+ "effectiveTo": "2027-01-01",
424
+ "tiers": [
425
+ {
426
+ "inputUsdPerM": 0.75,
427
+ "cachedInputUsdPerM": 0.075,
428
+ "cacheWriteUsdPerM": null,
429
+ "outputUsdPerM": 3.75
430
+ }
431
+ ],
432
+ "kind": "promo",
433
+ "promoEndsAt": "2026-12-31",
434
+ "sourceIds": [
435
+ "google-api-pricing-gemini-2.5-pro-routing",
436
+ "google-api-notes-2026-11-02-gemini-2.5-deprecation",
437
+ "google-api-pricing-gemini-3.8-flash"
438
+ ],
439
+ "note": "From 2026-12-01 requests to gemini-2.5-pro route to gemini-3.8-flash and are billed at Gemini 3.8 Flash rates: its introductory price through 2026-12-31. Google states dates, not times; boundaries are 00:00 UTC. Gemini Developer API paid tier, Standard inference, text/image/video input prices; free tier, Batch, Flex, Priority, audio input, Vertex AI / Gemini Enterprise Agent Platform and grounding prices are not modelled. cacheWriteUsdPerM is null: Gemini has no per-token cache write price (explicit cache creation bills its tokens at the input price)."
440
+ },
441
+ {
442
+ "id": "google-api:gemini-2.5-pro:2027-01-01",
443
+ "channel": "google-api",
444
+ "modelId": "gemini-2.5-pro",
445
+ "currency": "USD",
446
+ "effectiveFrom": "2027-01-01",
447
+ "tiers": [
448
+ {
449
+ "inputUsdPerM": 1.5,
450
+ "cachedInputUsdPerM": 0.15,
451
+ "cacheWriteUsdPerM": null,
452
+ "outputUsdPerM": 7.5
453
+ }
454
+ ],
455
+ "kind": "list",
456
+ "sourceIds": [
457
+ "google-api-pricing-gemini-2.5-pro-routing",
458
+ "google-api-notes-2026-11-02-gemini-2.5-deprecation",
459
+ "google-api-pricing-gemini-3.8-flash"
460
+ ],
461
+ "note": "Routed to gemini-3.8-flash since 2026-12-01 and billed at its rates: its standard price from 2027-01-01. Google states dates, not times; boundaries are 00:00 UTC. Gemini Developer API paid tier, Standard inference, text/image/video input prices; free tier, Batch, Flex, Priority, audio input, Vertex AI / Gemini Enterprise Agent Platform and grounding prices are not modelled. cacheWriteUsdPerM is null: Gemini has no per-token cache write price (explicit cache creation bills its tokens at the input price)."
462
+ },
463
+ {
464
+ "id": "google-api:gemini-2.5-flash:2026-11-06",
465
+ "channel": "google-api",
466
+ "modelId": "gemini-2.5-flash",
467
+ "currency": "USD",
468
+ "effectiveFrom": "2026-11-06",
469
+ "tiers": [
470
+ {
471
+ "inputUsdPerM": 0.3,
472
+ "cachedInputUsdPerM": 0.03,
473
+ "cacheWriteUsdPerM": null,
474
+ "outputUsdPerM": 2.5
475
+ }
476
+ ],
477
+ "kind": "list",
478
+ "sourceIds": [
479
+ "google-api-pricing-gemini-2.5-flash",
480
+ "google-api-pricing-gemini-2.5-flash-routing",
481
+ "google-api-notes-2026-11-02-gemini-2.5-deprecation",
482
+ "google-api-pricing-gemini-3.5-flash-lite"
483
+ ],
484
+ "note": "Only today's pricing page (checked 2026-11-06) gives this price; no dated Google source earlier in the window was found (the release notes carry no prices for it), so earlier turns price as unknown. Deprecated 2026-11-02; from 2026-12-01 requests route to gemini-3.5-flash-lite and are billed at its rates, which are the same for text ($0.30/$0.03/$2.50), so no boundary is needed; its audio input price changes ($1.00 to $0.30), which the tiers don't hold. Explicit context caching also bills storage at $1.00 per 1M tokens per hour, which the tiers can't hold. Gemini Developer API paid tier, Standard inference, text/image/video input prices; free tier, Batch, Flex, Priority, audio input, Vertex AI / Gemini Enterprise Agent Platform and grounding prices are not modelled. cacheWriteUsdPerM is null: Gemini has no per-token cache write price (explicit cache creation bills its tokens at the input price)."
485
+ },
486
+ {
487
+ "id": "google-api:gemini-2.5-flash-lite:2026-11-06",
488
+ "channel": "google-api",
489
+ "modelId": "gemini-2.5-flash-lite",
490
+ "currency": "USD",
491
+ "effectiveFrom": "2026-11-06",
492
+ "tiers": [
493
+ {
494
+ "inputUsdPerM": 0.1,
495
+ "cachedInputUsdPerM": 0.01,
496
+ "cacheWriteUsdPerM": null,
497
+ "outputUsdPerM": 0.4
498
+ }
499
+ ],
500
+ "kind": "list",
501
+ "sourceIds": [
502
+ "google-api-pricing-gemini-2.5-flash-lite"
503
+ ],
504
+ "note": "GA since 2025-07-22 (release notes). Only today's pricing page (checked 2026-11-06) gives this price; no dated Google source earlier in the window was found (the release notes carry no prices for it), so earlier turns price as unknown. Explicit context caching also bills storage at $1.00 per 1M tokens per hour, which the tiers can't hold. Gemini Developer API paid tier, Standard inference, text/image/video input prices; free tier, Batch, Flex, Priority, audio input, Vertex AI / Gemini Enterprise Agent Platform and grounding prices are not modelled. cacheWriteUsdPerM is null: Gemini has no per-token cache write price (explicit cache creation bills its tokens at the input price)."
505
+ }
506
+ ]
507
+ }