llm_cost_tracker 0.14.2 → 0.15.0

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 (152) hide show
  1. checksums.yaml +4 -4
  2. data/CHANGELOG.md +116 -0
  3. data/LICENSE.txt +28 -0
  4. data/README.md +33 -41
  5. data/app/controllers/llm_cost_tracker/application_controller.rb +7 -1
  6. data/app/controllers/llm_cost_tracker/calls_controller.rb +12 -94
  7. data/app/controllers/llm_cost_tracker/dashboard_controller.rb +11 -12
  8. data/app/controllers/llm_cost_tracker/pricing_controller.rb +15 -4
  9. data/app/controllers/llm_cost_tracker/tags_controller.rb +21 -14
  10. data/app/helpers/llm_cost_tracker/application_helper.rb +22 -31
  11. data/app/helpers/llm_cost_tracker/chart_helper.rb +57 -108
  12. data/app/helpers/llm_cost_tracker/dashboard_query_helper.rb +30 -17
  13. data/app/helpers/llm_cost_tracker/sortable_table_helper.rb +18 -25
  14. data/app/helpers/llm_cost_tracker/token_usage_helper.rb +30 -0
  15. data/app/models/llm_cost_tracker/call.rb +6 -4
  16. data/app/models/llm_cost_tracker/call_rollup.rb +6 -6
  17. data/app/services/llm_cost_tracker/dashboard/call_order.rb +36 -0
  18. data/app/services/llm_cost_tracker/dashboard/calls_export.rb +68 -0
  19. data/app/services/llm_cost_tracker/dashboard/data_quality/stats_query.rb +77 -0
  20. data/app/services/llm_cost_tracker/dashboard/data_quality/summary.rb +47 -0
  21. data/app/services/llm_cost_tracker/dashboard/data_quality.rb +66 -210
  22. data/app/services/llm_cost_tracker/dashboard/filter.rb +2 -1
  23. data/app/services/llm_cost_tracker/dashboard/monthly_budget.rb +42 -35
  24. data/app/services/llm_cost_tracker/dashboard/percent.rb +12 -0
  25. data/app/services/llm_cost_tracker/dashboard/sort.rb +9 -0
  26. data/app/services/llm_cost_tracker/dashboard/spend_anomaly.rb +19 -17
  27. data/app/services/llm_cost_tracker/dashboard/spend_chart.rb +50 -0
  28. data/app/services/llm_cost_tracker/dashboard/tag_breakdown.rb +7 -8
  29. data/app/services/llm_cost_tracker/dashboard/tag_key_explorer.rb +1 -4
  30. data/app/services/llm_cost_tracker/dashboard/top_models.rb +3 -4
  31. data/app/views/layouts/llm_cost_tracker/application.html.erb +6 -6
  32. data/app/views/llm_cost_tracker/calls/index.html.erb +2 -1
  33. data/app/views/llm_cost_tracker/calls/show.html.erb +3 -14
  34. data/app/views/llm_cost_tracker/errors/query.html.erb +6 -0
  35. data/app/views/llm_cost_tracker/shared/_filter_pill_stream.html.erb +1 -1
  36. data/app/views/llm_cost_tracker/tags/show.html.erb +1 -1
  37. data/lib/llm_cost_tracker/budget/estimate.rb +35 -0
  38. data/lib/llm_cost_tracker/budget/global.rb +69 -0
  39. data/lib/llm_cost_tracker/budget/limit.rb +52 -0
  40. data/lib/llm_cost_tracker/budget/per_tag.rb +59 -27
  41. data/lib/llm_cost_tracker/budget/tagged.rb +74 -0
  42. data/lib/llm_cost_tracker/budget.rb +19 -157
  43. data/lib/llm_cost_tracker/capture/event_window.rb +16 -13
  44. data/lib/llm_cost_tracker/capture/sdk_payload.rb +22 -17
  45. data/lib/llm_cost_tracker/capture/sse.rb +7 -5
  46. data/lib/llm_cost_tracker/capture/stream_collector.rb +89 -96
  47. data/lib/llm_cost_tracker/capture/stream_tap.rb +2 -2
  48. data/lib/llm_cost_tracker/capture/stream_tracker.rb +32 -37
  49. data/lib/llm_cost_tracker/capture_verifier.rb +2 -3
  50. data/lib/llm_cost_tracker/charges/cost_status.rb +23 -19
  51. data/lib/llm_cost_tracker/charges/line_item.rb +31 -33
  52. data/lib/llm_cost_tracker/configuration/budgets.rb +49 -18
  53. data/lib/llm_cost_tracker/configuration/capture.rb +7 -1
  54. data/lib/llm_cost_tracker/configuration/mutability.rb +3 -3
  55. data/lib/llm_cost_tracker/doctor/ingestion_check.rb +20 -2
  56. data/lib/llm_cost_tracker/doctor/price_check.rb +24 -35
  57. data/lib/llm_cost_tracker/doctor/probe.rb +1 -1
  58. data/lib/llm_cost_tracker/doctor.rb +23 -20
  59. data/lib/llm_cost_tracker/engine.rb +8 -0
  60. data/lib/llm_cost_tracker/errors.rb +2 -4
  61. data/lib/llm_cost_tracker/event.rb +22 -29
  62. data/lib/llm_cost_tracker/generators/llm_cost_tracker/templates/create_llm_cost_tracker_calls.rb.erb +4 -2
  63. data/lib/llm_cost_tracker/generators/llm_cost_tracker/templates/initializer.rb.erb +6 -4
  64. data/lib/llm_cost_tracker/generators/llm_cost_tracker/templates/upgrade_call_rollups_provider.rb.erb +1 -0
  65. data/lib/llm_cost_tracker/generators/llm_cost_tracker/templates/upgrade_call_tags_key_value_index.rb.erb +1 -0
  66. data/lib/llm_cost_tracker/generators/llm_cost_tracker/templates/upgrade_indexes.rb.erb +2 -1
  67. data/lib/llm_cost_tracker/generators/llm_cost_tracker/templates/upgrade_per_tag_budgets.rb.erb +1 -0
  68. data/lib/llm_cost_tracker/ingestion/batch.rb +33 -19
  69. data/lib/llm_cost_tracker/ingestion/inbox.rb +20 -11
  70. data/lib/llm_cost_tracker/ingestion/worker.rb +58 -37
  71. data/lib/llm_cost_tracker/ingestion.rb +20 -35
  72. data/lib/llm_cost_tracker/integrations/anthropic/batch_results_capture.rb +40 -0
  73. data/lib/llm_cost_tracker/integrations/anthropic/patches.rb +56 -0
  74. data/lib/llm_cost_tracker/integrations/anthropic.rb +59 -120
  75. data/lib/llm_cost_tracker/integrations/base/patch_target.rb +35 -0
  76. data/lib/llm_cost_tracker/integrations/base.rb +65 -81
  77. data/lib/llm_cost_tracker/integrations/openai/batch_capture.rb +20 -19
  78. data/lib/llm_cost_tracker/integrations/openai/patches.rb +51 -40
  79. data/lib/llm_cost_tracker/integrations/openai/websocket_capture.rb +89 -0
  80. data/lib/llm_cost_tracker/integrations/openai.rb +114 -83
  81. data/lib/llm_cost_tracker/integrations/ruby_llm/v1/patches.rb +67 -0
  82. data/lib/llm_cost_tracker/integrations/ruby_llm/v1/reply.rb +155 -0
  83. data/lib/llm_cost_tracker/integrations/ruby_llm/v1.rb +154 -0
  84. data/lib/llm_cost_tracker/integrations/ruby_llm/v2/attempt/token_counts.rb +159 -0
  85. data/lib/llm_cost_tracker/integrations/ruby_llm/v2/attempt.rb +175 -0
  86. data/lib/llm_cost_tracker/integrations/ruby_llm/v2/frame.rb +75 -0
  87. data/lib/llm_cost_tracker/integrations/ruby_llm/v2/recorder.rb +70 -0
  88. data/lib/llm_cost_tracker/integrations/ruby_llm/v2/seams.rb +86 -0
  89. data/lib/llm_cost_tracker/integrations/ruby_llm/v2.rb +161 -0
  90. data/lib/llm_cost_tracker/integrations/ruby_llm.rb +7 -408
  91. data/lib/llm_cost_tracker/ledger/isolation.rb +15 -2
  92. data/lib/llm_cost_tracker/ledger/period/totals.rb +1 -1
  93. data/lib/llm_cost_tracker/ledger/rollups.rb +24 -8
  94. data/lib/llm_cost_tracker/ledger/schema/adapter.rb +23 -6
  95. data/lib/llm_cost_tracker/ledger/schema/base.rb +9 -5
  96. data/lib/llm_cost_tracker/ledger/store.rb +17 -35
  97. data/lib/llm_cost_tracker/ledger/tags/breakdown.rb +2 -2
  98. data/lib/llm_cost_tracker/middleware/faraday/body.rb +57 -0
  99. data/lib/llm_cost_tracker/middleware/faraday/exchange.rb +153 -0
  100. data/lib/llm_cost_tracker/middleware/faraday/response_reader.rb +75 -0
  101. data/lib/llm_cost_tracker/middleware/faraday/stream_tee.rb +47 -0
  102. data/lib/llm_cost_tracker/middleware/faraday.rb +2 -301
  103. data/lib/llm_cost_tracker/parsers.rb +12 -0
  104. data/lib/llm_cost_tracker/prices.json +1179 -208
  105. data/lib/llm_cost_tracker/pricing/backfill.rb +59 -29
  106. data/lib/llm_cost_tracker/pricing/calculation/iterations.rb +49 -0
  107. data/lib/llm_cost_tracker/pricing/calculation/quantities.rb +40 -0
  108. data/lib/llm_cost_tracker/pricing/calculation/snapshot.rb +51 -0
  109. data/lib/llm_cost_tracker/pricing/calculation/totals.rb +59 -0
  110. data/lib/llm_cost_tracker/pricing/calculation.rb +82 -173
  111. data/lib/llm_cost_tracker/pricing/matcher.rb +31 -14
  112. data/lib/llm_cost_tracker/pricing/mode.rb +6 -19
  113. data/lib/llm_cost_tracker/pricing/off_peak.rb +50 -0
  114. data/lib/llm_cost_tracker/pricing/rate.rb +1 -0
  115. data/lib/llm_cost_tracker/pricing/registry/normalizer.rb +110 -0
  116. data/lib/llm_cost_tracker/pricing/registry.rb +38 -111
  117. data/lib/llm_cost_tracker/pricing/sync/change_printer.rb +40 -20
  118. data/lib/llm_cost_tracker/pricing/sync/fetcher.rb +35 -34
  119. data/lib/llm_cost_tracker/pricing/sync/registry_writer.rb +29 -18
  120. data/lib/llm_cost_tracker/pricing/sync/remote_snapshot.rb +78 -0
  121. data/lib/llm_cost_tracker/pricing/sync/snapshot_guard.rb +2 -0
  122. data/lib/llm_cost_tracker/pricing/sync.rb +7 -53
  123. data/lib/llm_cost_tracker/pricing/unknown.rb +1 -1
  124. data/lib/llm_cost_tracker/providers/anthropic/parser.rb +30 -25
  125. data/lib/llm_cost_tracker/providers/anthropic/response_parser.rb +5 -3
  126. data/lib/llm_cost_tracker/providers/anthropic/usage_extractor.rb +122 -101
  127. data/lib/llm_cost_tracker/providers/azure/hosts.rb +1 -1
  128. data/lib/llm_cost_tracker/providers/azure/parser.rb +3 -6
  129. data/lib/llm_cost_tracker/providers/gemini/grounding.rb +87 -0
  130. data/lib/llm_cost_tracker/providers/gemini/parser.rb +120 -183
  131. data/lib/llm_cost_tracker/providers/gemini/usage_extractor.rb +66 -47
  132. data/lib/llm_cost_tracker/providers/openai/hosts.rb +11 -0
  133. data/lib/llm_cost_tracker/providers/openai/model_families.rb +1 -1
  134. data/lib/llm_cost_tracker/providers/openai/output_item.rb +84 -0
  135. data/lib/llm_cost_tracker/providers/openai/parser.rb +2 -1
  136. data/lib/llm_cost_tracker/providers/openai/response_parser.rb +81 -149
  137. data/lib/llm_cost_tracker/providers/openai/service_charges.rb +133 -156
  138. data/lib/llm_cost_tracker/providers/openai/stream_parser.rb +127 -0
  139. data/lib/llm_cost_tracker/providers/openai/usage_extractor.rb +72 -62
  140. data/lib/llm_cost_tracker/providers/openai_compatible/parser.rb +15 -4
  141. data/lib/llm_cost_tracker/providers.rb +3 -0
  142. data/lib/llm_cost_tracker/redaction.rb +13 -0
  143. data/lib/llm_cost_tracker/report/data.rb +25 -28
  144. data/lib/llm_cost_tracker/tags/context.rb +22 -7
  145. data/lib/llm_cost_tracker/tracker.rb +32 -26
  146. data/lib/llm_cost_tracker/usage/dimensions.yml +24 -0
  147. data/lib/llm_cost_tracker/usage/token_usage.rb +8 -4
  148. data/lib/llm_cost_tracker/version.rb +1 -1
  149. data/lib/llm_cost_tracker.rb +8 -4
  150. data/lib/tasks/llm_cost_tracker.rake +35 -5
  151. data/llm_cost_tracker.gemspec +6 -5
  152. metadata +58 -5
@@ -1,45 +1,170 @@
1
1
  {
2
2
  "metadata": {
3
+ "absent_since": {
4
+ "anthropic/claude-haiku-3": "2026-10-05",
5
+ "gemini/gemini-2.0-flash": "2026-10-05",
6
+ "gemini/gemini-2.0-flash-lite": "2026-10-05",
7
+ "gemini/gemini-2.5-computer-use-preview-10-2025": "2026-10-05",
8
+ "gemini/gemini-2.5-flash-lite-preview-09-2025": "2026-10-05",
9
+ "gemini/gemini-3-pro-image-preview": "2026-10-05",
10
+ "gemini/gemini-3.1-flash-image-preview": "2026-10-05",
11
+ "gemini/gemini-3.1-flash-lite-preview": "2026-10-05",
12
+ "openrouter/ai21/jamba-large-1.7": "2026-10-05",
13
+ "openrouter/aion-labs/aion-1.0": "2026-10-05",
14
+ "openrouter/aion-labs/aion-1.0-mini": "2026-10-05",
15
+ "openrouter/alfredpros/codellama-7b-instruct-solidity": "2026-10-05",
16
+ "openrouter/allenai/olmo-3-32b-think": "2026-10-05",
17
+ "openrouter/anthropic/claude-3-haiku": "2026-10-05",
18
+ "openrouter/anthropic/claude-3.5-haiku": "2026-10-05",
19
+ "openrouter/anthropic/claude-opus-4": "2026-10-05",
20
+ "openrouter/anthropic/claude-opus-4.6-fast": "2026-10-05",
21
+ "openrouter/anthropic/claude-opus-4.7-fast": "2026-10-05",
22
+ "openrouter/anthropic/claude-opus-4.8-fast": "2026-10-05",
23
+ "openrouter/anthropic/claude-opus-5-fast": "2026-10-05",
24
+ "openrouter/arcee-ai/coder-large": "2026-10-05",
25
+ "openrouter/arcee-ai/maestro-reasoning": "2026-10-05",
26
+ "openrouter/arcee-ai/spotlight": "2026-10-05",
27
+ "openrouter/arcee-ai/trinity-mini": "2026-10-05",
28
+ "openrouter/arcee-ai/virtuoso-large": "2026-10-05",
29
+ "openrouter/baidu/ernie-4.5-21b-a3b": "2026-10-05",
30
+ "openrouter/baidu/ernie-4.5-21b-a3b-thinking": "2026-10-05",
31
+ "openrouter/baidu/ernie-4.5-300b-a47b": "2026-10-05",
32
+ "openrouter/baidu/ernie-4.5-vl-28b-a3b": "2026-10-05",
33
+ "openrouter/baidu/ernie-4.5-vl-424b-a47b": "2026-10-08",
34
+ "openrouter/baidu/qianfan-ocr-fast": "2026-10-05",
35
+ "openrouter/deepcogito/cogito-v2.1-671b": "2026-10-05",
36
+ "openrouter/deepseek/deepseek-r1-distill-llama-70b": "2026-10-05",
37
+ "openrouter/deepseek/deepseek-r1-distill-qwen-32b": "2026-10-05",
38
+ "openrouter/deepseek/deepseek-v3.2-speciale": "2026-10-05",
39
+ "openrouter/deepseek/deepseek-v4-flash-0731:batch": "2026-10-05",
40
+ "openrouter/deepseek/deepseek-v4-flash-vision-exp:batch": "2026-10-05",
41
+ "openrouter/deepseek/deepseek-v4-pro-0813:batch": "2026-10-05",
42
+ "openrouter/essentialai/rnj-1-instruct": "2026-10-05",
43
+ "openrouter/google/gemini-2.0-flash-001": "2026-10-05",
44
+ "openrouter/google/gemini-2.0-flash-lite-001": "2026-10-05",
45
+ "openrouter/google/gemini-2.5-flash-lite-preview-09-2025": "2026-10-05",
46
+ "openrouter/google/gemini-2.5-pro-preview-05-06": "2026-10-05",
47
+ "openrouter/google/gemma-3n-e4b-it": "2026-10-05",
48
+ "openrouter/google/gemma-4-31b-it:batch": "2026-10-05",
49
+ "openrouter/ibm-granite/granite-4.1-8b": "2026-10-05",
50
+ "openrouter/inception/mercury-2.5-preview": "2026-10-05",
51
+ "openrouter/inclusionai/ling-2.6-1t": "2026-10-05",
52
+ "openrouter/inclusionai/ling-2.6-flash": "2026-10-05",
53
+ "openrouter/inclusionai/ring-2.6-1t": "2026-10-05",
54
+ "openrouter/inflection/inflection-3-pi": "2026-10-05",
55
+ "openrouter/inflection/inflection-3-productivity": "2026-10-05",
56
+ "openrouter/kwaipilot/kat-coder-air-v2.5": "2026-10-05",
57
+ "openrouter/kwaipilot/kat-coder-pro-v2": "2026-10-05",
58
+ "openrouter/kwaipilot/kat-coder-pro-v2.5": "2026-10-08",
59
+ "openrouter/liquid/lfm-2-24b-a2b": "2026-10-05",
60
+ "openrouter/meta-llama/llama-3-70b-instruct": "2026-10-05",
61
+ "openrouter/meta-llama/llama-3-8b-instruct": "2026-10-05",
62
+ "openrouter/meta-llama/llama-3.2-11b-vision-instruct": "2026-10-05",
63
+ "openrouter/meta-llama/llama-guard-3-8b": "2026-10-05",
64
+ "openrouter/meta/muse-glimmer-30b:batch": "2026-10-05",
65
+ "openrouter/microsoft/phi-4-mini-instruct": "2026-10-05",
66
+ "openrouter/minimax/minimax-m3:batch": "2026-10-05",
67
+ "openrouter/mistralai/devstral-medium": "2026-10-05",
68
+ "openrouter/mistralai/devstral-small": "2026-10-05",
69
+ "openrouter/mistralai/ministral-8b": "2026-10-05",
70
+ "openrouter/mistralai/mistral-7b-instruct-v0.1": "2026-10-05",
71
+ "openrouter/mistralai/mistral-large-2411": "2026-10-05",
72
+ "openrouter/mistralai/pixtral-large-2411": "2026-10-05",
73
+ "openrouter/moonshotai/kimi-k2.7-code:batch": "2026-10-05",
74
+ "openrouter/nex-agi/deepseek-v3.1-nex-n1": "2026-10-05",
75
+ "openrouter/nex-agi/nex-n2-mini": "2026-10-05",
76
+ "openrouter/nex-agi/nex-n2-pro": "2026-10-05",
77
+ "openrouter/nousresearch/hermes-2-pro-llama-3-8b": "2026-10-05",
78
+ "openrouter/nousresearch/hermes-4-70b": "2026-10-05",
79
+ "openrouter/nvidia/llama-3.3-nemotron-super-49b-v1.5": "2026-10-05",
80
+ "openrouter/nvidia/nemotron-3-ultra-550b-a55b:batch": "2026-10-05",
81
+ "openrouter/nvidia/nemotron-nano-9b-v2": "2026-10-05",
82
+ "openrouter/openai/gpt-4-0314": "2026-10-05",
83
+ "openrouter/openai/gpt-4-1106-preview": "2026-10-05",
84
+ "openrouter/openai/gpt-4-turbo-preview": "2026-10-05",
85
+ "openrouter/openai/gpt-4o-audio-preview": "2026-10-05",
86
+ "openrouter/openai/gpt-4o-mini-search-preview": "2026-10-05",
87
+ "openrouter/openai/gpt-4o-search-preview": "2026-10-05",
88
+ "openrouter/openai/gpt-5-chat": "2026-10-05",
89
+ "openrouter/openai/gpt-5-codex": "2026-10-05",
90
+ "openrouter/openai/gpt-5-codex:batch": "2026-10-05",
91
+ "openrouter/openai/gpt-5.1-chat": "2026-10-05",
92
+ "openrouter/openai/gpt-5.3-chat": "2026-10-05",
93
+ "openrouter/openai/gpt-6.1-sol-pro:batch": "2026-10-05",
94
+ "openrouter/openai/gpt-6.1-sol:batch": "2026-10-05",
95
+ "openrouter/openai/o1-pro:batch": "2026-10-05",
96
+ "openrouter/openai/o1:batch": "2026-10-05",
97
+ "openrouter/openai/o3-deep-research": "2026-10-05",
98
+ "openrouter/openai/o3-mini-high:batch": "2026-10-05",
99
+ "openrouter/openai/o3-pro:batch": "2026-10-05",
100
+ "openrouter/openai/o4-mini-deep-research": "2026-10-05",
101
+ "openrouter/openai/o4-mini-high:batch": "2026-10-05",
102
+ "openrouter/poolside/laguna-m.1": "2026-10-05",
103
+ "openrouter/poolside/laguna-xs.2": "2026-10-05",
104
+ "openrouter/prime-intellect/intellect-3": "2026-10-05",
105
+ "openrouter/qwen/qwen-plus-2025-07-28:thinking": "2026-10-05",
106
+ "openrouter/qwen/qwen3.5-9b:batch": "2026-10-05",
107
+ "openrouter/qwen/qwen3.8-2.4t-a95b:batch": "2026-10-05",
108
+ "openrouter/qwen/qwen3.8-max": "2026-10-05",
109
+ "openrouter/sao10k/l3-euryale-70b": "2026-10-05",
110
+ "openrouter/sao10k/l3.1-70b-hanami-x1": "2026-10-05",
111
+ "openrouter/switchpoint/router": "2026-10-05",
112
+ "openrouter/thedrummer/rocinante-12b": "2026-10-05",
113
+ "openrouter/thinkingmachines/inkling-small:batch": "2026-10-05",
114
+ "openrouter/thinkingmachines/inkling:batch": "2026-10-05",
115
+ "openrouter/xiaomi/mimo-v2-flash": "2026-10-05",
116
+ "openrouter/xiaomi/mimo-v2-omni": "2026-10-05",
117
+ "openrouter/xiaomi/mimo-v2-pro": "2026-10-05",
118
+ "openrouter/z-ai/glm-4-32b": "2026-10-05",
119
+ "openrouter/z-ai/glm-5.2:batch": "2026-10-05",
120
+ "openrouter/~openai/gpt-latest": "2026-10-05"
121
+ },
3
122
  "currency": "USD",
4
- "min_gem_version": "0.4.0",
123
+ "min_gem_version": "0.15.0",
5
124
  "schema_version": 1,
6
125
  "source_urls": [
7
126
  "https://platform.claude.com/docs/en/about-claude/pricing",
127
+ "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
128
+ "https://cohere.com/pricing",
129
+ "https://docs.cohere.com/docs/models.md",
130
+ "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json",
131
+ "https://models.dev/api.json",
132
+ "https://api-docs.deepseek.com/quick_start/pricing",
8
133
  "https://ai.google.dev/gemini-api/docs/pricing",
9
134
  "https://console.groq.com/docs/models",
10
135
  "https://console.groq.com/docs/prompt-caching",
11
136
  "https://console.groq.com/docs/flex-processing",
12
137
  "https://console.groq.com/docs/deprecations",
13
138
  "https://console.groq.com/docs/batch",
14
- "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json",
139
+ "https://console.groq.com/docs/speech-to-text",
15
140
  "https://docs.mistral.ai/inference/pricing",
141
+ "https://docs.mistral.ai/models",
16
142
  "https://docs.mistral.ai/studio/batch-processing.md",
17
143
  "https://docs.mistral.ai/inference/priority-tier.md",
18
144
  "https://docs.mistral.ai/inference/regional-inference.md",
19
145
  "https://developers.openai.com/api/docs/pricing",
20
146
  "https://developers.openai.com/api/docs/pricing.md",
21
147
  "https://developers.openai.com/api/docs/deprecations",
22
- "https://developers.openai.com/api/docs/models/gpt-5.4",
23
- "https://developers.openai.com/api/docs/models/gpt-5.4-pro",
24
- "https://developers.openai.com/api/docs/models/gpt-5.5",
25
- "https://developers.openai.com/api/docs/models/gpt-5.5-pro",
26
- "https://developers.openai.com/api/docs/models/gpt-5.6-luna",
27
- "https://developers.openai.com/api/docs/models/gpt-5.6-sol",
28
- "https://developers.openai.com/api/docs/models/gpt-5.6-terra",
29
- "https://developers.openai.com/api/docs/models/gpt-6-astra",
30
- "https://developers.openai.com/api/docs/models/gpt-6-sol",
31
- "https://developers.openai.com/api/docs/models/gpt-6-luna",
148
+ "https://developers.openai.com/api/docs/models/all.md",
149
+ "https://developers.openai.com/api/docs/guides/batch.md",
150
+ "https://developers.openai.com/api/docs/guides/your-data.md",
151
+ "https://developers.openai.com/api/docs/changelog.md",
32
152
  "https://openrouter.ai/api/v1/models",
33
- "https://docs.x.ai/developers/pricing.md",
34
- "https://docs.x.ai/developers/models/grok-4.3.md",
35
- "https://docs.x.ai/developers/models/grok-4.20-0309-reasoning.md",
36
- "https://docs.x.ai/developers/models/grok-4.20-0309-non-reasoning.md",
37
- "https://docs.x.ai/developers/models/grok-4.20-multi-agent-0309.md"
153
+ "https://docs.x.ai/developers/pricing.md"
38
154
  ],
39
155
  "unit": "1M tokens",
40
- "updated_at": "2026-09-27"
156
+ "updated_at": "2026-10-08"
41
157
  },
42
158
  "models": {
159
+ "anthropic/claude-3-5-haiku": {
160
+ "batch_input": 0.4,
161
+ "batch_output": 2.0,
162
+ "cache_read_input": 0.08,
163
+ "cache_write_extended_input": 1.6,
164
+ "cache_write_input": 1.0,
165
+ "input": 0.8,
166
+ "output": 4.0
167
+ },
43
168
  "anthropic/claude-fable-5": {
44
169
  "batch_input": 5.0,
45
170
  "batch_output": 25.0,
@@ -97,6 +222,37 @@
97
222
  "input": 1.0,
98
223
  "output": 5.0
99
224
  },
225
+ "anthropic/claude-haiku-5-5": {
226
+ "_context_price_threshold_tokens": 100000,
227
+ "above_context_batch_input": 0.25,
228
+ "above_context_batch_output": 1.25,
229
+ "above_context_cache_read_input": 0.05,
230
+ "above_context_cache_write_extended_input": 1.0,
231
+ "above_context_cache_write_input": 0.625,
232
+ "above_context_data_residency_batch_input": 0.275,
233
+ "above_context_data_residency_batch_output": 1.375,
234
+ "above_context_data_residency_cache_read_input": 0.055,
235
+ "above_context_data_residency_cache_write_extended_input": 1.1,
236
+ "above_context_data_residency_cache_write_input": 0.6875,
237
+ "above_context_data_residency_input": 0.55,
238
+ "above_context_data_residency_output": 2.75,
239
+ "above_context_input": 0.5,
240
+ "above_context_output": 2.5,
241
+ "batch_input": 0.05,
242
+ "batch_output": 0.25,
243
+ "cache_read_input": 0.01,
244
+ "cache_write_extended_input": 0.2,
245
+ "cache_write_input": 0.125,
246
+ "data_residency_batch_input": 0.055,
247
+ "data_residency_batch_output": 0.275,
248
+ "data_residency_cache_read_input": 0.011,
249
+ "data_residency_cache_write_extended_input": 0.22,
250
+ "data_residency_cache_write_input": 0.1375,
251
+ "data_residency_input": 0.11,
252
+ "data_residency_output": 0.55,
253
+ "input": 0.1,
254
+ "output": 0.5
255
+ },
100
256
  "anthropic/claude-mythos-5": {
101
257
  "batch_input": 5.0,
102
258
  "batch_output": 25.0,
@@ -129,6 +285,24 @@
129
285
  "input": 10.0,
130
286
  "output": 50.0
131
287
  },
288
+ "anthropic/claude-opus-4": {
289
+ "batch_input": 7.5,
290
+ "batch_output": 37.5,
291
+ "cache_read_input": 1.5,
292
+ "cache_write_extended_input": 30.0,
293
+ "cache_write_input": 18.75,
294
+ "input": 15.0,
295
+ "output": 75.0
296
+ },
297
+ "anthropic/claude-opus-4-1": {
298
+ "batch_input": 7.5,
299
+ "batch_output": 37.5,
300
+ "cache_read_input": 1.5,
301
+ "cache_write_extended_input": 30.0,
302
+ "cache_write_input": 18.75,
303
+ "input": 15.0,
304
+ "output": 75.0
305
+ },
132
306
  "anthropic/claude-opus-4-5": {
133
307
  "batch_input": 2.5,
134
308
  "batch_output": 12.5,
@@ -255,7 +429,31 @@
255
429
  "input": 4.0,
256
430
  "output": 20.0
257
431
  },
432
+ "anthropic/claude-sonnet-4": {
433
+ "batch_input": 1.5,
434
+ "batch_output": 7.5,
435
+ "cache_read_input": 0.3,
436
+ "cache_write_extended_input": 6.0,
437
+ "cache_write_input": 3.75,
438
+ "input": 3.0,
439
+ "output": 15.0
440
+ },
258
441
  "anthropic/claude-sonnet-4-5": {
442
+ "_context_price_threshold_tokens": 200000,
443
+ "above_context_batch_input": 3.0,
444
+ "above_context_batch_output": 11.25,
445
+ "above_context_cache_read_input": 0.6,
446
+ "above_context_cache_write_extended_input": 12.0,
447
+ "above_context_cache_write_input": 7.5,
448
+ "above_context_data_residency_batch_input": 3.3,
449
+ "above_context_data_residency_batch_output": 12.375,
450
+ "above_context_data_residency_cache_read_input": 0.66,
451
+ "above_context_data_residency_cache_write_extended_input": 13.2,
452
+ "above_context_data_residency_cache_write_input": 8.25,
453
+ "above_context_data_residency_input": 6.6,
454
+ "above_context_data_residency_output": 24.75,
455
+ "above_context_input": 6.0,
456
+ "above_context_output": 22.5,
259
457
  "batch_input": 1.5,
260
458
  "batch_output": 7.5,
261
459
  "cache_read_input": 0.3,
@@ -303,6 +501,206 @@
303
501
  "input": 2.0,
304
502
  "output": 10.0
305
503
  },
504
+ "anthropic/claude-sonnet-5-5": {
505
+ "batch_input": 1.0,
506
+ "batch_output": 5.0,
507
+ "cache_read_input": 0.1,
508
+ "cache_write_extended_input": 4.0,
509
+ "cache_write_input": 2.5,
510
+ "data_residency_batch_input": 1.1,
511
+ "data_residency_batch_output": 5.5,
512
+ "data_residency_cache_read_input": 0.11,
513
+ "data_residency_cache_write_extended_input": 4.4,
514
+ "data_residency_cache_write_input": 2.75,
515
+ "data_residency_input": 2.2,
516
+ "data_residency_output": 11.0,
517
+ "input": 2.0,
518
+ "output": 10.0
519
+ },
520
+ "cohere/c4ai-aya-expanse-32b": {
521
+ "input": 0.5,
522
+ "output": 1.5
523
+ },
524
+ "cohere/command": {
525
+ "input": 1.0,
526
+ "output": 2.0
527
+ },
528
+ "cohere/command-a-03-2025": {
529
+ "_source": "litellm",
530
+ "input": 2.5,
531
+ "output": 10.0
532
+ },
533
+ "cohere/command-light": {
534
+ "input": 0.3,
535
+ "output": 0.6
536
+ },
537
+ "cohere/command-r-03-2024": {
538
+ "input": 0.5,
539
+ "output": 1.5
540
+ },
541
+ "cohere/command-r-08-2024": {
542
+ "input": 0.15,
543
+ "output": 0.6
544
+ },
545
+ "cohere/command-r-plus-04-2024": {
546
+ "input": 3.0,
547
+ "output": 15.0
548
+ },
549
+ "cohere/command-r-plus-08-2024": {
550
+ "input": 2.5,
551
+ "output": 10.0
552
+ },
553
+ "cohere/command-r7b-12-2024": {
554
+ "input": 0.0375,
555
+ "output": 0.15
556
+ },
557
+ "cohere/embed-v5.0-fast": {
558
+ "input": 0.08
559
+ },
560
+ "cohere/embed-v5.0-pro": {
561
+ "input": 0.12
562
+ },
563
+ "cohere/parse-v5.0": {
564
+ "ocr_page": 1.5
565
+ },
566
+ "cohere/rerank-v4.0-fast": {
567
+ "rerank_search_unit": 2.0
568
+ },
569
+ "cohere/rerank-v4.0-pro": {
570
+ "rerank_search_unit": 2.5
571
+ },
572
+ "deepseek/deepseek-flash": {
573
+ "_off_peak_windows": [
574
+ {
575
+ "hours_utc": [
576
+ "00:00-01:00",
577
+ "04:00-06:00",
578
+ "10:00-24:00"
579
+ ],
580
+ "weekdays": [
581
+ 1,
582
+ 2,
583
+ 3,
584
+ 4,
585
+ 5
586
+ ]
587
+ },
588
+ {
589
+ "hours_utc": [
590
+ "00:00-24:00"
591
+ ],
592
+ "weekdays": [
593
+ 6,
594
+ 7
595
+ ]
596
+ }
597
+ ],
598
+ "cache_read_input": 0.006,
599
+ "input": 0.3,
600
+ "off_peak_cache_read_input": 0.003,
601
+ "off_peak_input": 0.15,
602
+ "off_peak_output": 0.6,
603
+ "output": 1.2
604
+ },
605
+ "deepseek/deepseek-v4-flash": {
606
+ "_off_peak_windows": [
607
+ {
608
+ "hours_utc": [
609
+ "00:00-01:00",
610
+ "04:00-06:00",
611
+ "10:00-24:00"
612
+ ],
613
+ "weekdays": [
614
+ 1,
615
+ 2,
616
+ 3,
617
+ 4,
618
+ 5
619
+ ]
620
+ },
621
+ {
622
+ "hours_utc": [
623
+ "00:00-24:00"
624
+ ],
625
+ "weekdays": [
626
+ 6,
627
+ 7
628
+ ]
629
+ }
630
+ ],
631
+ "cache_read_input": 0.006,
632
+ "input": 0.3,
633
+ "off_peak_cache_read_input": 0.003,
634
+ "off_peak_input": 0.15,
635
+ "off_peak_output": 0.6,
636
+ "output": 1.2
637
+ },
638
+ "deepseek/deepseek-v4-flash-vision-exp": {
639
+ "_off_peak_windows": [
640
+ {
641
+ "hours_utc": [
642
+ "00:00-01:00",
643
+ "04:00-06:00",
644
+ "10:00-24:00"
645
+ ],
646
+ "weekdays": [
647
+ 1,
648
+ 2,
649
+ 3,
650
+ 4,
651
+ 5
652
+ ]
653
+ },
654
+ {
655
+ "hours_utc": [
656
+ "00:00-24:00"
657
+ ],
658
+ "weekdays": [
659
+ 6,
660
+ 7
661
+ ]
662
+ }
663
+ ],
664
+ "cache_read_input": 0.006,
665
+ "input": 0.3,
666
+ "off_peak_cache_read_input": 0.003,
667
+ "off_peak_input": 0.15,
668
+ "off_peak_output": 0.6,
669
+ "output": 1.2
670
+ },
671
+ "deepseek/deepseek-v4-pro": {
672
+ "_off_peak_windows": [
673
+ {
674
+ "hours_utc": [
675
+ "00:00-01:00",
676
+ "04:00-06:00",
677
+ "10:00-24:00"
678
+ ],
679
+ "weekdays": [
680
+ 1,
681
+ 2,
682
+ 3,
683
+ 4,
684
+ 5
685
+ ]
686
+ },
687
+ {
688
+ "hours_utc": [
689
+ "00:00-24:00"
690
+ ],
691
+ "weekdays": [
692
+ 6,
693
+ 7
694
+ ]
695
+ }
696
+ ],
697
+ "cache_read_input": 0.044,
698
+ "input": 1.32,
699
+ "off_peak_cache_read_input": 0.022,
700
+ "off_peak_input": 0.66,
701
+ "off_peak_output": 1.98,
702
+ "output": 3.96
703
+ },
306
704
  "gemini/gemini-2.0-flash": {
307
705
  "audio_input": 0.7,
308
706
  "batch_audio_input": 0.35,
@@ -326,6 +724,17 @@
326
724
  "input": 0.075,
327
725
  "output": 0.3
328
726
  },
727
+ "gemini/gemini-2.5-computer-use-preview-10-2025": {
728
+ "_context_price_threshold_tokens": 200000,
729
+ "above_context_audio_input": 2.5,
730
+ "above_context_image_input": 2.5,
731
+ "above_context_input": 2.5,
732
+ "above_context_output": 15.0,
733
+ "audio_input": 1.25,
734
+ "image_input": 1.25,
735
+ "input": 1.25,
736
+ "output": 10.0
737
+ },
329
738
  "gemini/gemini-2.5-flash": {
330
739
  "audio_cache_read_input": 0.1,
331
740
  "audio_input": 1.0,
@@ -548,10 +957,18 @@
548
957
  "priority_output": 21.6
549
958
  },
550
959
  "gemini/gemini-3.1-flash-image": {
960
+ "batch_data_residency_image_input_from_2026-07-01": 0.275,
961
+ "batch_data_residency_image_output_from_2026-07-01": 33.0,
962
+ "batch_data_residency_input_from_2026-07-01": 0.275,
963
+ "batch_data_residency_output_from_2026-07-01": 1.65,
551
964
  "batch_image_input": 0.25,
552
965
  "batch_image_output": 30.0,
553
966
  "batch_input": 0.25,
554
967
  "batch_output": 1.5,
968
+ "data_residency_image_input_from_2026-07-01": 0.55,
969
+ "data_residency_image_output_from_2026-07-01": 66.0,
970
+ "data_residency_input_from_2026-07-01": 0.55,
971
+ "data_residency_output_from_2026-07-01": 3.3,
555
972
  "grounding_request": 14.0,
556
973
  "image_input": 0.5,
557
974
  "image_output": 60.0,
@@ -574,14 +991,32 @@
574
991
  "batch_audio_cache_read_input": 0.025,
575
992
  "batch_audio_input": 0.25,
576
993
  "batch_cache_read_input": 0.0125,
994
+ "batch_data_residency_audio_cache_read_input_from_2026-07-01": 0.0275,
995
+ "batch_data_residency_audio_input_from_2026-07-01": 0.275,
996
+ "batch_data_residency_cache_read_input_from_2026-07-01": 0.01375,
997
+ "batch_data_residency_image_input_from_2026-07-01": 0.1375,
998
+ "batch_data_residency_input_from_2026-07-01": 0.1375,
999
+ "batch_data_residency_output_from_2026-07-01": 0.825,
577
1000
  "batch_image_input": 0.125,
578
1001
  "batch_input": 0.125,
579
1002
  "batch_output": 0.75,
580
1003
  "cache_read_input": 0.025,
581
1004
  "cache_storage_token_hour": 1.0,
1005
+ "data_residency_audio_cache_read_input_from_2026-07-01": 0.055,
1006
+ "data_residency_audio_input_from_2026-07-01": 0.55,
1007
+ "data_residency_cache_read_input_from_2026-07-01": 0.0275,
1008
+ "data_residency_image_input_from_2026-07-01": 0.275,
1009
+ "data_residency_input_from_2026-07-01": 0.275,
1010
+ "data_residency_output_from_2026-07-01": 1.65,
582
1011
  "flex_audio_cache_read_input": 0.025,
583
1012
  "flex_audio_input": 0.25,
584
1013
  "flex_cache_read_input": 0.0125,
1014
+ "flex_data_residency_audio_cache_read_input_from_2026-07-01": 0.0275,
1015
+ "flex_data_residency_audio_input_from_2026-07-01": 0.275,
1016
+ "flex_data_residency_cache_read_input_from_2026-07-01": 0.01375,
1017
+ "flex_data_residency_image_input_from_2026-07-01": 0.1375,
1018
+ "flex_data_residency_input_from_2026-07-01": 0.1375,
1019
+ "flex_data_residency_output_from_2026-07-01": 0.825,
585
1020
  "flex_image_input": 0.125,
586
1021
  "flex_input": 0.125,
587
1022
  "flex_output": 0.75,
@@ -593,6 +1028,12 @@
593
1028
  "priority_audio_cache_read_input": 0.09,
594
1029
  "priority_audio_input": 0.9,
595
1030
  "priority_cache_read_input": 0.045,
1031
+ "priority_data_residency_audio_cache_read_input_from_2026-07-01": 0.099,
1032
+ "priority_data_residency_audio_input_from_2026-07-01": 0.99,
1033
+ "priority_data_residency_cache_read_input_from_2026-07-01": 0.0495,
1034
+ "priority_data_residency_image_input_from_2026-07-01": 0.495,
1035
+ "priority_data_residency_input_from_2026-07-01": 0.495,
1036
+ "priority_data_residency_output_from_2026-07-01": 2.97,
596
1037
  "priority_image_input": 0.45,
597
1038
  "priority_input": 0.45,
598
1039
  "priority_output": 2.7
@@ -735,13 +1176,28 @@
735
1176
  "audio_input": 1.5,
736
1177
  "batch_audio_input": 0.75,
737
1178
  "batch_cache_read_input": 0.075,
1179
+ "batch_data_residency_audio_input_from_2026-07-01": 0.825,
1180
+ "batch_data_residency_cache_read_input_from_2026-07-01": 0.0825,
1181
+ "batch_data_residency_image_input_from_2026-07-01": 0.825,
1182
+ "batch_data_residency_input_from_2026-07-01": 0.825,
1183
+ "batch_data_residency_output_from_2026-07-01": 4.95,
738
1184
  "batch_image_input": 0.75,
739
1185
  "batch_input": 0.75,
740
1186
  "batch_output": 4.5,
741
1187
  "cache_read_input": 0.15,
742
1188
  "cache_storage_token_hour": 1.0,
1189
+ "data_residency_audio_input_from_2026-07-01": 1.65,
1190
+ "data_residency_cache_read_input_from_2026-07-01": 0.165,
1191
+ "data_residency_image_input_from_2026-07-01": 1.65,
1192
+ "data_residency_input_from_2026-07-01": 1.65,
1193
+ "data_residency_output_from_2026-07-01": 9.9,
743
1194
  "flex_audio_input": 0.75,
744
1195
  "flex_cache_read_input": 0.08,
1196
+ "flex_data_residency_audio_input_from_2026-07-01": 0.825,
1197
+ "flex_data_residency_cache_read_input_from_2026-07-01": 0.088,
1198
+ "flex_data_residency_image_input_from_2026-07-01": 0.825,
1199
+ "flex_data_residency_input_from_2026-07-01": 0.825,
1200
+ "flex_data_residency_output_from_2026-07-01": 4.95,
745
1201
  "flex_image_input": 0.75,
746
1202
  "flex_input": 0.75,
747
1203
  "flex_output": 4.5,
@@ -752,6 +1208,11 @@
752
1208
  "output": 9.0,
753
1209
  "priority_audio_input": 2.7,
754
1210
  "priority_cache_read_input": 0.27,
1211
+ "priority_data_residency_audio_input_from_2026-07-01": 2.97,
1212
+ "priority_data_residency_cache_read_input_from_2026-07-01": 0.297,
1213
+ "priority_data_residency_image_input_from_2026-07-01": 2.97,
1214
+ "priority_data_residency_input_from_2026-07-01": 2.97,
1215
+ "priority_data_residency_output_from_2026-07-01": 17.82,
755
1216
  "priority_image_input": 2.7,
756
1217
  "priority_input": 2.7,
757
1218
  "priority_output": 16.2
@@ -760,13 +1221,28 @@
760
1221
  "audio_input": 0.3,
761
1222
  "batch_audio_input": 0.15,
762
1223
  "batch_cache_read_input": 0.02,
1224
+ "batch_data_residency_audio_input_from_2026-07-01": 0.165,
1225
+ "batch_data_residency_cache_read_input_from_2026-07-01": 0.022,
1226
+ "batch_data_residency_image_input_from_2026-07-01": 0.165,
1227
+ "batch_data_residency_input_from_2026-07-01": 0.165,
1228
+ "batch_data_residency_output_from_2026-07-01": 1.375,
763
1229
  "batch_image_input": 0.15,
764
1230
  "batch_input": 0.15,
765
1231
  "batch_output": 1.25,
766
1232
  "cache_read_input": 0.03,
767
1233
  "cache_storage_token_hour": 1.0,
1234
+ "data_residency_audio_input_from_2026-07-01": 0.33,
1235
+ "data_residency_cache_read_input_from_2026-07-01": 0.033,
1236
+ "data_residency_image_input_from_2026-07-01": 0.33,
1237
+ "data_residency_input_from_2026-07-01": 0.33,
1238
+ "data_residency_output_from_2026-07-01": 2.75,
768
1239
  "flex_audio_input": 0.15,
769
1240
  "flex_cache_read_input": 0.02,
1241
+ "flex_data_residency_audio_input_from_2026-07-01": 0.165,
1242
+ "flex_data_residency_cache_read_input_from_2026-07-01": 0.022,
1243
+ "flex_data_residency_image_input_from_2026-07-01": 0.165,
1244
+ "flex_data_residency_input_from_2026-07-01": 0.165,
1245
+ "flex_data_residency_output_from_2026-07-01": 1.375,
770
1246
  "flex_image_input": 0.15,
771
1247
  "flex_input": 0.15,
772
1248
  "flex_output": 1.25,
@@ -777,10 +1253,27 @@
777
1253
  "output": 2.5,
778
1254
  "priority_audio_input": 0.54,
779
1255
  "priority_cache_read_input": 0.05,
1256
+ "priority_data_residency_audio_input_from_2026-07-01": 0.594,
1257
+ "priority_data_residency_cache_read_input_from_2026-07-01": 0.055,
1258
+ "priority_data_residency_image_input_from_2026-07-01": 0.594,
1259
+ "priority_data_residency_input_from_2026-07-01": 0.594,
1260
+ "priority_data_residency_output_from_2026-07-01": 4.95,
780
1261
  "priority_image_input": 0.54,
781
1262
  "priority_input": 0.54,
782
1263
  "priority_output": 4.5
783
1264
  },
1265
+ "gemini/gemini-3.5-transcribe": {
1266
+ "audio_input": 2.0,
1267
+ "image_input": 2.0,
1268
+ "input": 2.0,
1269
+ "output": 12.0
1270
+ },
1271
+ "gemini/gemini-3.5-transcribe-live": {
1272
+ "audio_input": 3.5,
1273
+ "image_input": 3.5,
1274
+ "input": 3.5,
1275
+ "output": 21.0
1276
+ },
784
1277
  "gemini/gemini-3.6-flash": {
785
1278
  "audio_input": 0.75,
786
1279
  "audio_input_from_2027-01-01": 1.5,
@@ -788,6 +1281,16 @@
788
1281
  "batch_audio_input_from_2027-01-01": 0.75,
789
1282
  "batch_cache_read_input": 0.0375,
790
1283
  "batch_cache_read_input_from_2027-01-01": 0.075,
1284
+ "batch_data_residency_audio_input_from_2026-07-01": 0.4125,
1285
+ "batch_data_residency_audio_input_from_2027-01-01": 0.825,
1286
+ "batch_data_residency_cache_read_input_from_2026-07-01": 0.04125,
1287
+ "batch_data_residency_cache_read_input_from_2027-01-01": 0.0825,
1288
+ "batch_data_residency_image_input_from_2026-07-01": 0.4125,
1289
+ "batch_data_residency_image_input_from_2027-01-01": 0.825,
1290
+ "batch_data_residency_input_from_2026-07-01": 0.4125,
1291
+ "batch_data_residency_input_from_2027-01-01": 0.825,
1292
+ "batch_data_residency_output_from_2026-07-01": 2.0625,
1293
+ "batch_data_residency_output_from_2027-01-01": 4.125,
791
1294
  "batch_image_input": 0.375,
792
1295
  "batch_image_input_from_2027-01-01": 0.75,
793
1296
  "batch_input": 0.375,
@@ -798,10 +1301,30 @@
798
1301
  "cache_read_input_from_2027-01-01": 0.15,
799
1302
  "cache_storage_token_hour": 0.5,
800
1303
  "cache_storage_token_hour_from_2027-01-01": 1.0,
1304
+ "data_residency_audio_input_from_2026-07-01": 0.825,
1305
+ "data_residency_audio_input_from_2027-01-01": 1.65,
1306
+ "data_residency_cache_read_input_from_2026-07-01": 0.0825,
1307
+ "data_residency_cache_read_input_from_2027-01-01": 0.165,
1308
+ "data_residency_image_input_from_2026-07-01": 0.825,
1309
+ "data_residency_image_input_from_2027-01-01": 1.65,
1310
+ "data_residency_input_from_2026-07-01": 0.825,
1311
+ "data_residency_input_from_2027-01-01": 1.65,
1312
+ "data_residency_output_from_2026-07-01": 4.125,
1313
+ "data_residency_output_from_2027-01-01": 8.25,
801
1314
  "flex_audio_input": 0.375,
802
1315
  "flex_audio_input_from_2027-01-01": 0.75,
803
1316
  "flex_cache_read_input": 0.0375,
804
1317
  "flex_cache_read_input_from_2027-01-01": 0.075,
1318
+ "flex_data_residency_audio_input_from_2026-07-01": 0.4125,
1319
+ "flex_data_residency_audio_input_from_2027-01-01": 0.825,
1320
+ "flex_data_residency_cache_read_input_from_2026-07-01": 0.04125,
1321
+ "flex_data_residency_cache_read_input_from_2027-01-01": 0.0825,
1322
+ "flex_data_residency_image_input_from_2026-07-01": 0.4125,
1323
+ "flex_data_residency_image_input_from_2027-01-01": 0.825,
1324
+ "flex_data_residency_input_from_2026-07-01": 0.4125,
1325
+ "flex_data_residency_input_from_2027-01-01": 0.825,
1326
+ "flex_data_residency_output_from_2026-07-01": 2.0625,
1327
+ "flex_data_residency_output_from_2027-01-01": 4.125,
805
1328
  "flex_image_input": 0.375,
806
1329
  "flex_image_input_from_2027-01-01": 0.75,
807
1330
  "flex_input": 0.375,
@@ -820,6 +1343,16 @@
820
1343
  "priority_audio_input_from_2027-01-01": 2.7,
821
1344
  "priority_cache_read_input": 0.135,
822
1345
  "priority_cache_read_input_from_2027-01-01": 0.27,
1346
+ "priority_data_residency_audio_input_from_2026-07-01": 1.485,
1347
+ "priority_data_residency_audio_input_from_2027-01-01": 2.97,
1348
+ "priority_data_residency_cache_read_input_from_2026-07-01": 0.1485,
1349
+ "priority_data_residency_cache_read_input_from_2027-01-01": 0.297,
1350
+ "priority_data_residency_image_input_from_2026-07-01": 1.485,
1351
+ "priority_data_residency_image_input_from_2027-01-01": 2.97,
1352
+ "priority_data_residency_input_from_2026-07-01": 1.485,
1353
+ "priority_data_residency_input_from_2027-01-01": 2.97,
1354
+ "priority_data_residency_output_from_2026-07-01": 7.425,
1355
+ "priority_data_residency_output_from_2027-01-01": 14.85,
823
1356
  "priority_image_input": 1.35,
824
1357
  "priority_image_input_from_2027-01-01": 2.7,
825
1358
  "priority_input": 1.35,
@@ -834,6 +1367,16 @@
834
1367
  "batch_audio_input_from_2027-01-01": 0.75,
835
1368
  "batch_cache_read_input": 0.0375,
836
1369
  "batch_cache_read_input_from_2027-01-01": 0.075,
1370
+ "batch_data_residency_audio_input_from_2026-07-01": 0.4125,
1371
+ "batch_data_residency_audio_input_from_2027-01-01": 0.825,
1372
+ "batch_data_residency_cache_read_input_from_2026-07-01": 0.04125,
1373
+ "batch_data_residency_cache_read_input_from_2027-01-01": 0.0825,
1374
+ "batch_data_residency_image_input_from_2026-07-01": 0.4125,
1375
+ "batch_data_residency_image_input_from_2027-01-01": 0.825,
1376
+ "batch_data_residency_input_from_2026-07-01": 0.4125,
1377
+ "batch_data_residency_input_from_2027-01-01": 0.825,
1378
+ "batch_data_residency_output_from_2026-07-01": 2.0625,
1379
+ "batch_data_residency_output_from_2027-01-01": 4.125,
837
1380
  "batch_image_input": 0.375,
838
1381
  "batch_image_input_from_2027-01-01": 0.75,
839
1382
  "batch_input": 0.375,
@@ -844,10 +1387,30 @@
844
1387
  "cache_read_input_from_2027-01-01": 0.15,
845
1388
  "cache_storage_token_hour": 0.5,
846
1389
  "cache_storage_token_hour_from_2027-01-01": 1.0,
1390
+ "data_residency_audio_input_from_2026-07-01": 0.825,
1391
+ "data_residency_audio_input_from_2027-01-01": 1.65,
1392
+ "data_residency_cache_read_input_from_2026-07-01": 0.0825,
1393
+ "data_residency_cache_read_input_from_2027-01-01": 0.165,
1394
+ "data_residency_image_input_from_2026-07-01": 0.825,
1395
+ "data_residency_image_input_from_2027-01-01": 1.65,
1396
+ "data_residency_input_from_2026-07-01": 0.825,
1397
+ "data_residency_input_from_2027-01-01": 1.65,
1398
+ "data_residency_output_from_2026-07-01": 4.125,
1399
+ "data_residency_output_from_2027-01-01": 8.25,
847
1400
  "flex_audio_input": 0.375,
848
1401
  "flex_audio_input_from_2027-01-01": 0.75,
849
1402
  "flex_cache_read_input": 0.0375,
850
1403
  "flex_cache_read_input_from_2027-01-01": 0.075,
1404
+ "flex_data_residency_audio_input_from_2026-07-01": 0.4125,
1405
+ "flex_data_residency_audio_input_from_2027-01-01": 0.825,
1406
+ "flex_data_residency_cache_read_input_from_2026-07-01": 0.04125,
1407
+ "flex_data_residency_cache_read_input_from_2027-01-01": 0.0825,
1408
+ "flex_data_residency_image_input_from_2026-07-01": 0.4125,
1409
+ "flex_data_residency_image_input_from_2027-01-01": 0.825,
1410
+ "flex_data_residency_input_from_2026-07-01": 0.4125,
1411
+ "flex_data_residency_input_from_2027-01-01": 0.825,
1412
+ "flex_data_residency_output_from_2026-07-01": 2.0625,
1413
+ "flex_data_residency_output_from_2027-01-01": 4.125,
851
1414
  "flex_image_input": 0.375,
852
1415
  "flex_image_input_from_2027-01-01": 0.75,
853
1416
  "flex_input": 0.375,
@@ -866,6 +1429,16 @@
866
1429
  "priority_audio_input_from_2027-01-01": 2.7,
867
1430
  "priority_cache_read_input": 0.135,
868
1431
  "priority_cache_read_input_from_2027-01-01": 0.27,
1432
+ "priority_data_residency_audio_input_from_2026-07-01": 1.485,
1433
+ "priority_data_residency_audio_input_from_2027-01-01": 2.97,
1434
+ "priority_data_residency_cache_read_input_from_2026-07-01": 0.1485,
1435
+ "priority_data_residency_cache_read_input_from_2027-01-01": 0.297,
1436
+ "priority_data_residency_image_input_from_2026-07-01": 1.485,
1437
+ "priority_data_residency_image_input_from_2027-01-01": 2.97,
1438
+ "priority_data_residency_input_from_2026-07-01": 1.485,
1439
+ "priority_data_residency_input_from_2027-01-01": 2.97,
1440
+ "priority_data_residency_output_from_2026-07-01": 7.425,
1441
+ "priority_data_residency_output_from_2027-01-01": 14.85,
869
1442
  "priority_image_input": 1.35,
870
1443
  "priority_image_input_from_2027-01-01": 2.7,
871
1444
  "priority_input": 1.35,
@@ -880,6 +1453,16 @@
880
1453
  "batch_audio_input_from_2027-01-01": 0.75,
881
1454
  "batch_cache_read_input": 0.0375,
882
1455
  "batch_cache_read_input_from_2027-01-01": 0.075,
1456
+ "batch_data_residency_audio_input_from_2026-07-01": 0.4125,
1457
+ "batch_data_residency_audio_input_from_2027-01-01": 0.825,
1458
+ "batch_data_residency_cache_read_input_from_2026-07-01": 0.04125,
1459
+ "batch_data_residency_cache_read_input_from_2027-01-01": 0.0825,
1460
+ "batch_data_residency_image_input_from_2026-07-01": 0.4125,
1461
+ "batch_data_residency_image_input_from_2027-01-01": 0.825,
1462
+ "batch_data_residency_input_from_2026-07-01": 0.4125,
1463
+ "batch_data_residency_input_from_2027-01-01": 0.825,
1464
+ "batch_data_residency_output_from_2026-07-01": 2.0625,
1465
+ "batch_data_residency_output_from_2027-01-01": 4.125,
883
1466
  "batch_image_input": 0.375,
884
1467
  "batch_image_input_from_2027-01-01": 0.75,
885
1468
  "batch_input": 0.375,
@@ -890,10 +1473,30 @@
890
1473
  "cache_read_input_from_2027-01-01": 0.15,
891
1474
  "cache_storage_token_hour": 0.5,
892
1475
  "cache_storage_token_hour_from_2027-01-01": 1.0,
1476
+ "data_residency_audio_input_from_2026-07-01": 0.825,
1477
+ "data_residency_audio_input_from_2027-01-01": 1.65,
1478
+ "data_residency_cache_read_input_from_2026-07-01": 0.0825,
1479
+ "data_residency_cache_read_input_from_2027-01-01": 0.165,
1480
+ "data_residency_image_input_from_2026-07-01": 0.825,
1481
+ "data_residency_image_input_from_2027-01-01": 1.65,
1482
+ "data_residency_input_from_2026-07-01": 0.825,
1483
+ "data_residency_input_from_2027-01-01": 1.65,
1484
+ "data_residency_output_from_2026-07-01": 4.125,
1485
+ "data_residency_output_from_2027-01-01": 8.25,
893
1486
  "flex_audio_input": 0.375,
894
1487
  "flex_audio_input_from_2027-01-01": 0.75,
895
1488
  "flex_cache_read_input": 0.0375,
896
1489
  "flex_cache_read_input_from_2027-01-01": 0.075,
1490
+ "flex_data_residency_audio_input_from_2026-07-01": 0.4125,
1491
+ "flex_data_residency_audio_input_from_2027-01-01": 0.825,
1492
+ "flex_data_residency_cache_read_input_from_2026-07-01": 0.04125,
1493
+ "flex_data_residency_cache_read_input_from_2027-01-01": 0.0825,
1494
+ "flex_data_residency_image_input_from_2026-07-01": 0.4125,
1495
+ "flex_data_residency_image_input_from_2027-01-01": 0.825,
1496
+ "flex_data_residency_input_from_2026-07-01": 0.4125,
1497
+ "flex_data_residency_input_from_2027-01-01": 0.825,
1498
+ "flex_data_residency_output_from_2026-07-01": 2.0625,
1499
+ "flex_data_residency_output_from_2027-01-01": 4.125,
897
1500
  "flex_image_input": 0.375,
898
1501
  "flex_image_input_from_2027-01-01": 0.75,
899
1502
  "flex_input": 0.375,
@@ -912,6 +1515,16 @@
912
1515
  "priority_audio_input_from_2027-01-01": 2.7,
913
1516
  "priority_cache_read_input": 0.135,
914
1517
  "priority_cache_read_input_from_2027-01-01": 0.27,
1518
+ "priority_data_residency_audio_input_from_2026-07-01": 1.485,
1519
+ "priority_data_residency_audio_input_from_2027-01-01": 2.97,
1520
+ "priority_data_residency_cache_read_input_from_2026-07-01": 0.1485,
1521
+ "priority_data_residency_cache_read_input_from_2027-01-01": 0.297,
1522
+ "priority_data_residency_image_input_from_2026-07-01": 1.485,
1523
+ "priority_data_residency_image_input_from_2027-01-01": 2.97,
1524
+ "priority_data_residency_input_from_2026-07-01": 1.485,
1525
+ "priority_data_residency_input_from_2027-01-01": 2.97,
1526
+ "priority_data_residency_output_from_2026-07-01": 7.425,
1527
+ "priority_data_residency_output_from_2027-01-01": 14.85,
915
1528
  "priority_image_input": 1.35,
916
1529
  "priority_image_input_from_2027-01-01": 2.7,
917
1530
  "priority_input": 1.35,
@@ -919,6 +1532,48 @@
919
1532
  "priority_output": 6.75,
920
1533
  "priority_output_from_2027-01-01": 13.5
921
1534
  },
1535
+ "gemini/gemini-3.8-flash-cyber": {
1536
+ "audio_input": 1.5,
1537
+ "batch_audio_input": 0.75,
1538
+ "batch_cache_read_input": 0.075,
1539
+ "batch_data_residency_audio_input_from_2026-07-01": 0.825,
1540
+ "batch_data_residency_cache_read_input_from_2026-07-01": 0.0825,
1541
+ "batch_data_residency_image_input_from_2026-07-01": 0.825,
1542
+ "batch_data_residency_input_from_2026-07-01": 0.825,
1543
+ "batch_data_residency_output_from_2026-07-01": 4.125,
1544
+ "batch_image_input": 0.75,
1545
+ "batch_input": 0.75,
1546
+ "batch_output": 3.75,
1547
+ "cache_read_input": 0.15,
1548
+ "data_residency_audio_input_from_2026-07-01": 1.65,
1549
+ "data_residency_cache_read_input_from_2026-07-01": 0.165,
1550
+ "data_residency_image_input_from_2026-07-01": 1.65,
1551
+ "data_residency_input_from_2026-07-01": 1.65,
1552
+ "data_residency_output_from_2026-07-01": 8.25,
1553
+ "flex_audio_input": 0.75,
1554
+ "flex_cache_read_input": 0.075,
1555
+ "flex_data_residency_audio_input_from_2026-07-01": 0.825,
1556
+ "flex_data_residency_cache_read_input_from_2026-07-01": 0.0825,
1557
+ "flex_data_residency_image_input_from_2026-07-01": 0.825,
1558
+ "flex_data_residency_input_from_2026-07-01": 0.825,
1559
+ "flex_data_residency_output_from_2026-07-01": 4.125,
1560
+ "flex_image_input": 0.75,
1561
+ "flex_input": 0.75,
1562
+ "flex_output": 3.75,
1563
+ "image_input": 1.5,
1564
+ "input": 1.5,
1565
+ "output": 7.5,
1566
+ "priority_audio_input": 2.7,
1567
+ "priority_cache_read_input": 0.27,
1568
+ "priority_data_residency_audio_input_from_2026-07-01": 2.97,
1569
+ "priority_data_residency_cache_read_input_from_2026-07-01": 0.297,
1570
+ "priority_data_residency_image_input_from_2026-07-01": 2.97,
1571
+ "priority_data_residency_input_from_2026-07-01": 2.97,
1572
+ "priority_data_residency_output_from_2026-07-01": 14.85,
1573
+ "priority_image_input": 2.7,
1574
+ "priority_input": 2.7,
1575
+ "priority_output": 13.5
1576
+ },
922
1577
  "gemini/gemini-3.8-flash-lite-tts": {
923
1578
  "audio_output": 6.0,
924
1579
  "audio_output_from_2027-01-01": 12.0,
@@ -1017,6 +1672,31 @@
1017
1672
  "input": 0.2,
1018
1673
  "video_input": 12.0
1019
1674
  },
1675
+ "gemini/gemini-nano-banana-2.1": {
1676
+ "batch_image_input": 0.75,
1677
+ "batch_image_output": 15.0,
1678
+ "batch_input": 0.75,
1679
+ "batch_output": 3.75,
1680
+ "grounding_request": 14.0,
1681
+ "image_input": 1.5,
1682
+ "image_output": 30.0,
1683
+ "input": 1.5,
1684
+ "output": 7.5
1685
+ },
1686
+ "gemini/gemini-omni-1.1-flash": {
1687
+ "audio_input": 1.5,
1688
+ "image_input": 1.5,
1689
+ "input": 1.5,
1690
+ "output": 9.0,
1691
+ "video_output": 17.5
1692
+ },
1693
+ "gemini/gemini-omni-flash-preview": {
1694
+ "audio_input": 1.5,
1695
+ "image_input": 1.5,
1696
+ "input": 1.5,
1697
+ "output": 9.0,
1698
+ "video_output": 17.5
1699
+ },
1020
1700
  "gemini/gemini-robotics-er-2-preview": {
1021
1701
  "audio_input": 1.0,
1022
1702
  "audio_input_from_2027-01-01": 2.0,
@@ -1042,6 +1722,12 @@
1042
1722
  "output": 5.0,
1043
1723
  "output_from_2027-01-01": 10.0
1044
1724
  },
1725
+ "groq/canopylabs/orpheus-arabic-saudi": {
1726
+ "text_to_speech_character": 40.0
1727
+ },
1728
+ "groq/canopylabs/orpheus-v1-english": {
1729
+ "text_to_speech_character": 22.0
1730
+ },
1045
1731
  "groq/meta-llama/llama-prompt-guard-2-22m": {
1046
1732
  "flex_input": 0.03,
1047
1733
  "flex_output": 0.03,
@@ -1105,6 +1791,14 @@
1105
1791
  "on_demand_output": 4.0,
1106
1792
  "output": 4.0
1107
1793
  },
1794
+ "groq/whisper-large-v3": {
1795
+ "_minimum_billed_seconds": 10,
1796
+ "transcription_minute": 0.00185
1797
+ },
1798
+ "groq/whisper-large-v3-turbo": {
1799
+ "_minimum_billed_seconds": 10,
1800
+ "transcription_minute": 0.0006666666666666666
1801
+ },
1108
1802
  "mistral/codestral-2508": {
1109
1803
  "batch_cache_read_input": 0.015,
1110
1804
  "batch_input": 0.15,
@@ -1122,6 +1816,22 @@
1122
1816
  "priority_input": 0.525,
1123
1817
  "priority_output": 1.575
1124
1818
  },
1819
+ "mistral/codestral-embed": {
1820
+ "batch_cache_read_input": 0.0075,
1821
+ "batch_input": 0.075,
1822
+ "cache_read_input": 0.015,
1823
+ "data_residency_cache_read_input": 0.0165,
1824
+ "data_residency_input": 0.165,
1825
+ "input": 0.15
1826
+ },
1827
+ "mistral/codestral-embed-2505": {
1828
+ "batch_cache_read_input": 0.0075,
1829
+ "batch_input": 0.075,
1830
+ "cache_read_input": 0.015,
1831
+ "data_residency_cache_read_input": 0.0165,
1832
+ "data_residency_input": 0.165,
1833
+ "input": 0.15
1834
+ },
1125
1835
  "mistral/codestral-latest": {
1126
1836
  "batch_cache_read_input": 0.015,
1127
1837
  "batch_input": 0.15,
@@ -1140,6 +1850,7 @@
1140
1850
  "priority_output": 1.575
1141
1851
  },
1142
1852
  "mistral/glm-5-2": {
1853
+ "_source": "litellm",
1143
1854
  "batch_cache_read_input": 0.07,
1144
1855
  "batch_input": 0.7,
1145
1856
  "batch_output": 2.2,
@@ -1156,40 +1867,6 @@
1156
1867
  "priority_input": 2.45,
1157
1868
  "priority_output": 7.7
1158
1869
  },
1159
- "mistral/magistral-medium-latest": {
1160
- "batch_cache_read_input": 0.075,
1161
- "batch_input": 0.75,
1162
- "batch_output": 3.75,
1163
- "cache_read_input": 0.15,
1164
- "data_residency_cache_read_input": 0.165,
1165
- "data_residency_input": 1.65,
1166
- "data_residency_output": 8.25,
1167
- "input": 1.5,
1168
- "output": 7.5,
1169
- "priority_cache_read_input": 0.2625,
1170
- "priority_data_residency_cache_read_input": 0.28875,
1171
- "priority_data_residency_input": 2.8875,
1172
- "priority_data_residency_output": 14.4375,
1173
- "priority_input": 2.625,
1174
- "priority_output": 13.125
1175
- },
1176
- "mistral/magistral-small-latest": {
1177
- "batch_cache_read_input": 0.0075,
1178
- "batch_input": 0.075,
1179
- "batch_output": 0.3,
1180
- "cache_read_input": 0.015,
1181
- "data_residency_cache_read_input": 0.0165,
1182
- "data_residency_input": 0.165,
1183
- "data_residency_output": 0.66,
1184
- "input": 0.15,
1185
- "output": 0.6,
1186
- "priority_cache_read_input": 0.02625,
1187
- "priority_data_residency_cache_read_input": 0.028875,
1188
- "priority_data_residency_input": 0.28875,
1189
- "priority_data_residency_output": 1.155,
1190
- "priority_input": 0.2625,
1191
- "priority_output": 1.05
1192
- },
1193
1870
  "mistral/ministral-14b-2512": {
1194
1871
  "batch_cache_read_input": 0.01,
1195
1872
  "batch_input": 0.1,
@@ -1326,6 +2003,18 @@
1326
2003
  "priority_input": 0.525,
1327
2004
  "priority_output": 1.575
1328
2005
  },
2006
+ "mistral/mistral-embed": {
2007
+ "_source": "litellm",
2008
+ "batch_input": 0.05,
2009
+ "data_residency_input": 0.11,
2010
+ "input": 0.1
2011
+ },
2012
+ "mistral/mistral-embed-2312": {
2013
+ "_source": "litellm",
2014
+ "batch_input": 0.05,
2015
+ "data_residency_input": 0.11,
2016
+ "input": 0.1
2017
+ },
1329
2018
  "mistral/mistral-large-2512": {
1330
2019
  "batch_cache_read_input": 0.025,
1331
2020
  "batch_input": 0.25,
@@ -1360,6 +2049,40 @@
1360
2049
  "priority_input": 0.875,
1361
2050
  "priority_output": 2.625
1362
2051
  },
2052
+ "mistral/mistral-large-4": {
2053
+ "batch_cache_read_input": 0.035,
2054
+ "batch_input": 0.34,
2055
+ "batch_output": 1.045,
2056
+ "cache_read_input": 0.07,
2057
+ "data_residency_cache_read_input": 0.077,
2058
+ "data_residency_input": 0.748,
2059
+ "data_residency_output": 2.299,
2060
+ "input": 0.68,
2061
+ "output": 2.09,
2062
+ "priority_cache_read_input": 0.1225,
2063
+ "priority_data_residency_cache_read_input": 0.13475,
2064
+ "priority_data_residency_input": 1.309,
2065
+ "priority_data_residency_output": 4.02325,
2066
+ "priority_input": 1.19,
2067
+ "priority_output": 3.6575
2068
+ },
2069
+ "mistral/mistral-large-4-0": {
2070
+ "batch_cache_read_input": 0.035,
2071
+ "batch_input": 0.34,
2072
+ "batch_output": 1.045,
2073
+ "cache_read_input": 0.07,
2074
+ "data_residency_cache_read_input": 0.077,
2075
+ "data_residency_input": 0.748,
2076
+ "data_residency_output": 2.299,
2077
+ "input": 0.68,
2078
+ "output": 2.09,
2079
+ "priority_cache_read_input": 0.1225,
2080
+ "priority_data_residency_cache_read_input": 0.13475,
2081
+ "priority_data_residency_input": 1.309,
2082
+ "priority_data_residency_output": 4.02325,
2083
+ "priority_input": 1.19,
2084
+ "priority_output": 3.6575
2085
+ },
1363
2086
  "mistral/mistral-large-latest": {
1364
2087
  "batch_cache_read_input": 0.025,
1365
2088
  "batch_input": 0.25,
@@ -1479,6 +2202,32 @@
1479
2202
  "priority_input": 2.625,
1480
2203
  "priority_output": 13.125
1481
2204
  },
2205
+ "mistral/mistral-moderation-2603": {
2206
+ "batch_cache_read_input": 0.0,
2207
+ "batch_input": 0.0,
2208
+ "batch_output": 0.0,
2209
+ "cache_read_input": 0.0,
2210
+ "data_residency_cache_read_input": 0.0,
2211
+ "data_residency_input": 0.0,
2212
+ "data_residency_output": 0.0,
2213
+ "input": 0.0,
2214
+ "output": 0.0,
2215
+ "priority_cache_read_input": 0.0,
2216
+ "priority_data_residency_cache_read_input": 0.0,
2217
+ "priority_data_residency_input": 0.0,
2218
+ "priority_data_residency_output": 0.0,
2219
+ "priority_input": 0.0,
2220
+ "priority_output": 0.0
2221
+ },
2222
+ "mistral/mistral-ocr-4": {
2223
+ "ocr_page": 4.0
2224
+ },
2225
+ "mistral/mistral-ocr-4-1": {
2226
+ "ocr_page": 4.0
2227
+ },
2228
+ "mistral/mistral-ocr-latest": {
2229
+ "ocr_page": 4.0
2230
+ },
1482
2231
  "mistral/mistral-small-2603": {
1483
2232
  "batch_cache_read_input": 0.0075,
1484
2233
  "batch_input": 0.075,
@@ -1564,6 +2313,37 @@
1564
2313
  "priority_input": 2.625,
1565
2314
  "priority_output": 13.125
1566
2315
  },
2316
+ "mistral/voxtral-mini-2602": {
2317
+ "transcription_minute": 0.003
2318
+ },
2319
+ "mistral/voxtral-mini-latest": {
2320
+ "transcription_minute": 0.003
2321
+ },
2322
+ "mistral/voxtral-mini-tts-2603": {
2323
+ "text_to_speech_character": 16.0
2324
+ },
2325
+ "mistral/voxtral-mini-tts-latest": {
2326
+ "text_to_speech_character": 16.0
2327
+ },
2328
+ "mistral/voxtral-small-2507": {
2329
+ "_source": "litellm",
2330
+ "batch_cache_read_input": 0.005,
2331
+ "batch_input": 0.05,
2332
+ "batch_output": 0.2,
2333
+ "cache_read_input": 0.01,
2334
+ "data_residency_cache_read_input": 0.011,
2335
+ "data_residency_input": 0.11,
2336
+ "data_residency_output": 0.44,
2337
+ "input": 0.1,
2338
+ "output": 0.4,
2339
+ "priority_cache_read_input": 0.0175,
2340
+ "priority_data_residency_cache_read_input": 0.01925,
2341
+ "priority_data_residency_input": 0.1925,
2342
+ "priority_data_residency_output": 0.77,
2343
+ "priority_input": 0.175,
2344
+ "priority_output": 0.7,
2345
+ "transcription_minute": 0.004
2346
+ },
1567
2347
  "mistral/zai-glm-5": {
1568
2348
  "batch_cache_read_input": 0.07,
1569
2349
  "batch_input": 0.7,
@@ -1582,6 +2362,7 @@
1582
2362
  "priority_output": 7.7
1583
2363
  },
1584
2364
  "mistral/zai-glm-5-2": {
2365
+ "_source": "litellm",
1585
2366
  "batch_cache_read_input": 0.07,
1586
2367
  "batch_input": 0.7,
1587
2368
  "batch_output": 2.2,
@@ -1632,12 +2413,6 @@
1632
2413
  "priority_input": 2.45,
1633
2414
  "priority_output": 7.7
1634
2415
  },
1635
- "openai/babbage-002": {
1636
- "batch_input": 0.2,
1637
- "batch_output": 0.2,
1638
- "input": 0.4,
1639
- "output": 0.4
1640
- },
1641
2416
  "openai/chat-latest": {
1642
2417
  "cache_read_input": 0.5,
1643
2418
  "input": 5.0,
@@ -1657,12 +2432,6 @@
1657
2432
  "input": 5.0,
1658
2433
  "output": 10.0
1659
2434
  },
1660
- "openai/davinci-002": {
1661
- "batch_input": 1.0,
1662
- "batch_output": 1.0,
1663
- "input": 2.0,
1664
- "output": 2.0
1665
- },
1666
2435
  "openai/gpt-3.5-turbo": {
1667
2436
  "input": 0.5,
1668
2437
  "output": 1.5
@@ -1673,16 +2442,6 @@
1673
2442
  "input": 0.5,
1674
2443
  "output": 1.5
1675
2444
  },
1676
- "openai/gpt-3.5-turbo-1106": {
1677
- "batch_input": 1.0,
1678
- "batch_output": 2.0,
1679
- "input": 1.0,
1680
- "output": 2.0
1681
- },
1682
- "openai/gpt-3.5-turbo-instruct": {
1683
- "input": 1.5,
1684
- "output": 2.0
1685
- },
1686
2445
  "openai/gpt-4": {
1687
2446
  "batch_input": 15.0,
1688
2447
  "batch_output": 30.0,
@@ -1701,6 +2460,12 @@
1701
2460
  "input": 10.0,
1702
2461
  "output": 30.0
1703
2462
  },
2463
+ "openai/gpt-4-turbo-2024-04-09": {
2464
+ "batch_input": 5.0,
2465
+ "batch_output": 15.0,
2466
+ "input": 10.0,
2467
+ "output": 30.0
2468
+ },
1704
2469
  "openai/gpt-4.1": {
1705
2470
  "batch_input": 1.0,
1706
2471
  "batch_output": 4.0,
@@ -1781,6 +2546,10 @@
1781
2546
  "input": 1.25,
1782
2547
  "output": 5.0
1783
2548
  },
2549
+ "openai/gpt-4o-mini-tts": {
2550
+ "audio_output": 12.0,
2551
+ "input": 0.6
2552
+ },
1784
2553
  "openai/gpt-4o-transcribe": {
1785
2554
  "audio_input": 6.0,
1786
2555
  "input": 2.5,
@@ -2400,6 +3169,14 @@
2400
3169
  "above_context_priority_data_residency_output": 165.0,
2401
3170
  "above_context_priority_input": 40.0,
2402
3171
  "above_context_priority_output": 150.0,
3172
+ "above_context_ultrafast_cache_read_input": 12.0,
3173
+ "above_context_ultrafast_cache_write_input": 150.0,
3174
+ "above_context_ultrafast_data_residency_cache_read_input": 13.2,
3175
+ "above_context_ultrafast_data_residency_cache_write_input": 165.0,
3176
+ "above_context_ultrafast_data_residency_input": 132.0,
3177
+ "above_context_ultrafast_data_residency_output": 495.0,
3178
+ "above_context_ultrafast_input": 120.0,
3179
+ "above_context_ultrafast_output": 450.0,
2403
3180
  "batch_cache_read_input": 0.5,
2404
3181
  "batch_cache_write_input": 6.25,
2405
3182
  "batch_data_residency_cache_read_input": 0.55,
@@ -2439,7 +3216,15 @@
2439
3216
  "priority_data_residency_input": 22.0,
2440
3217
  "priority_data_residency_output": 110.0,
2441
3218
  "priority_input": 20.0,
2442
- "priority_output": 100.0
3219
+ "priority_output": 100.0,
3220
+ "ultrafast_cache_read_input": 6.0,
3221
+ "ultrafast_cache_write_input": 75.0,
3222
+ "ultrafast_data_residency_cache_read_input": 6.6,
3223
+ "ultrafast_data_residency_cache_write_input": 82.5,
3224
+ "ultrafast_data_residency_input": 66.0,
3225
+ "ultrafast_data_residency_output": 330.0,
3226
+ "ultrafast_input": 60.0,
3227
+ "ultrafast_output": 300.0
2443
3228
  },
2444
3229
  "openai/gpt-6-luna": {
2445
3230
  "_context_price_threshold_tokens": 272000,
@@ -2524,33 +3309,116 @@
2524
3309
  "priority_input": 0.2,
2525
3310
  "priority_output": 1.0
2526
3311
  },
2527
- "openai/gpt-6-sol": {
3312
+ "openai/gpt-6-sol": {
3313
+ "_context_price_threshold_tokens": 272000,
3314
+ "above_context_batch_cache_read_input": 0.2,
3315
+ "above_context_batch_cache_write_input": 2.5,
3316
+ "above_context_batch_data_residency_cache_read_input": 0.22,
3317
+ "above_context_batch_data_residency_cache_write_input": 2.75,
3318
+ "above_context_batch_data_residency_input": 2.2,
3319
+ "above_context_batch_data_residency_output": 8.25,
3320
+ "above_context_batch_input": 2.0,
3321
+ "above_context_batch_output": 7.5,
3322
+ "above_context_cache_read_input": 0.4,
3323
+ "above_context_cache_write_input": 5.0,
3324
+ "above_context_data_residency_cache_read_input": 0.44,
3325
+ "above_context_data_residency_cache_write_input": 5.5,
3326
+ "above_context_data_residency_input": 4.4,
3327
+ "above_context_data_residency_output": 16.5,
3328
+ "above_context_fast_cache_read_input": 0.8,
3329
+ "above_context_fast_cache_write_input": 10.0,
3330
+ "above_context_fast_data_residency_cache_read_input": 0.88,
3331
+ "above_context_fast_data_residency_cache_write_input": 11.0,
3332
+ "above_context_fast_data_residency_input": 8.8,
3333
+ "above_context_fast_data_residency_output": 33.0,
3334
+ "above_context_fast_input": 8.0,
3335
+ "above_context_fast_output": 30.0,
3336
+ "above_context_flex_cache_read_input": 0.2,
3337
+ "above_context_flex_cache_write_input": 2.5,
3338
+ "above_context_flex_data_residency_cache_read_input": 0.22,
3339
+ "above_context_flex_data_residency_cache_write_input": 2.75,
3340
+ "above_context_flex_data_residency_input": 2.2,
3341
+ "above_context_flex_data_residency_output": 8.25,
3342
+ "above_context_flex_input": 2.0,
3343
+ "above_context_flex_output": 7.5,
3344
+ "above_context_input": 4.0,
3345
+ "above_context_output": 15.0,
3346
+ "above_context_priority_cache_read_input": 0.8,
3347
+ "above_context_priority_cache_write_input": 10.0,
3348
+ "above_context_priority_data_residency_cache_read_input": 0.88,
3349
+ "above_context_priority_data_residency_cache_write_input": 11.0,
3350
+ "above_context_priority_data_residency_input": 8.8,
3351
+ "above_context_priority_data_residency_output": 33.0,
3352
+ "above_context_priority_input": 8.0,
3353
+ "above_context_priority_output": 30.0,
3354
+ "batch_cache_read_input": 0.1,
3355
+ "batch_cache_write_input": 1.25,
3356
+ "batch_data_residency_cache_read_input": 0.11,
3357
+ "batch_data_residency_cache_write_input": 1.375,
3358
+ "batch_data_residency_input": 1.1,
3359
+ "batch_data_residency_output": 5.5,
3360
+ "batch_input": 1.0,
3361
+ "batch_output": 5.0,
3362
+ "cache_read_input": 0.2,
3363
+ "cache_write_input": 2.5,
3364
+ "data_residency_cache_read_input": 0.22,
3365
+ "data_residency_cache_write_input": 2.75,
3366
+ "data_residency_input": 2.2,
3367
+ "data_residency_output": 11.0,
3368
+ "fast_cache_read_input": 0.4,
3369
+ "fast_cache_write_input": 5.0,
3370
+ "fast_data_residency_cache_read_input": 0.44,
3371
+ "fast_data_residency_cache_write_input": 5.5,
3372
+ "fast_data_residency_input": 4.4,
3373
+ "fast_data_residency_output": 22.0,
3374
+ "fast_input": 4.0,
3375
+ "fast_output": 20.0,
3376
+ "flex_cache_read_input": 0.1,
3377
+ "flex_cache_write_input": 1.25,
3378
+ "flex_data_residency_cache_read_input": 0.11,
3379
+ "flex_data_residency_cache_write_input": 1.375,
3380
+ "flex_data_residency_input": 1.1,
3381
+ "flex_data_residency_output": 5.5,
3382
+ "flex_input": 1.0,
3383
+ "flex_output": 5.0,
3384
+ "input": 2.0,
3385
+ "output": 10.0,
3386
+ "priority_cache_read_input": 0.4,
3387
+ "priority_cache_write_input": 5.0,
3388
+ "priority_data_residency_cache_read_input": 0.44,
3389
+ "priority_data_residency_cache_write_input": 5.5,
3390
+ "priority_data_residency_input": 4.4,
3391
+ "priority_data_residency_output": 22.0,
3392
+ "priority_input": 4.0,
3393
+ "priority_output": 20.0
3394
+ },
3395
+ "openai/gpt-6.1-sol": {
2528
3396
  "_context_price_threshold_tokens": 272000,
2529
- "above_context_batch_cache_read_input": 0.2,
3397
+ "above_context_batch_cache_read_input": 0.1,
2530
3398
  "above_context_batch_cache_write_input": 2.5,
2531
- "above_context_batch_data_residency_cache_read_input": 0.22,
3399
+ "above_context_batch_data_residency_cache_read_input": 0.11,
2532
3400
  "above_context_batch_data_residency_cache_write_input": 2.75,
2533
3401
  "above_context_batch_data_residency_input": 2.2,
2534
3402
  "above_context_batch_data_residency_output": 8.25,
2535
3403
  "above_context_batch_input": 2.0,
2536
3404
  "above_context_batch_output": 7.5,
2537
- "above_context_cache_read_input": 0.4,
3405
+ "above_context_cache_read_input": 0.2,
2538
3406
  "above_context_cache_write_input": 5.0,
2539
- "above_context_data_residency_cache_read_input": 0.44,
3407
+ "above_context_data_residency_cache_read_input": 0.22,
2540
3408
  "above_context_data_residency_cache_write_input": 5.5,
2541
3409
  "above_context_data_residency_input": 4.4,
2542
3410
  "above_context_data_residency_output": 16.5,
2543
- "above_context_fast_cache_read_input": 0.8,
3411
+ "above_context_fast_cache_read_input": 0.4,
2544
3412
  "above_context_fast_cache_write_input": 10.0,
2545
- "above_context_fast_data_residency_cache_read_input": 0.88,
3413
+ "above_context_fast_data_residency_cache_read_input": 0.44,
2546
3414
  "above_context_fast_data_residency_cache_write_input": 11.0,
2547
3415
  "above_context_fast_data_residency_input": 8.8,
2548
3416
  "above_context_fast_data_residency_output": 33.0,
2549
3417
  "above_context_fast_input": 8.0,
2550
3418
  "above_context_fast_output": 30.0,
2551
- "above_context_flex_cache_read_input": 0.2,
3419
+ "above_context_flex_cache_read_input": 0.1,
2552
3420
  "above_context_flex_cache_write_input": 2.5,
2553
- "above_context_flex_data_residency_cache_read_input": 0.22,
3421
+ "above_context_flex_data_residency_cache_read_input": 0.11,
2554
3422
  "above_context_flex_data_residency_cache_write_input": 2.75,
2555
3423
  "above_context_flex_data_residency_input": 2.2,
2556
3424
  "above_context_flex_data_residency_output": 8.25,
@@ -2558,39 +3426,39 @@
2558
3426
  "above_context_flex_output": 7.5,
2559
3427
  "above_context_input": 4.0,
2560
3428
  "above_context_output": 15.0,
2561
- "above_context_priority_cache_read_input": 0.8,
3429
+ "above_context_priority_cache_read_input": 0.4,
2562
3430
  "above_context_priority_cache_write_input": 10.0,
2563
- "above_context_priority_data_residency_cache_read_input": 0.88,
3431
+ "above_context_priority_data_residency_cache_read_input": 0.44,
2564
3432
  "above_context_priority_data_residency_cache_write_input": 11.0,
2565
3433
  "above_context_priority_data_residency_input": 8.8,
2566
3434
  "above_context_priority_data_residency_output": 33.0,
2567
3435
  "above_context_priority_input": 8.0,
2568
3436
  "above_context_priority_output": 30.0,
2569
- "batch_cache_read_input": 0.1,
3437
+ "batch_cache_read_input": 0.05,
2570
3438
  "batch_cache_write_input": 1.25,
2571
- "batch_data_residency_cache_read_input": 0.11,
3439
+ "batch_data_residency_cache_read_input": 0.055,
2572
3440
  "batch_data_residency_cache_write_input": 1.375,
2573
3441
  "batch_data_residency_input": 1.1,
2574
3442
  "batch_data_residency_output": 5.5,
2575
3443
  "batch_input": 1.0,
2576
3444
  "batch_output": 5.0,
2577
- "cache_read_input": 0.2,
3445
+ "cache_read_input": 0.1,
2578
3446
  "cache_write_input": 2.5,
2579
- "data_residency_cache_read_input": 0.22,
3447
+ "data_residency_cache_read_input": 0.11,
2580
3448
  "data_residency_cache_write_input": 2.75,
2581
3449
  "data_residency_input": 2.2,
2582
3450
  "data_residency_output": 11.0,
2583
- "fast_cache_read_input": 0.4,
3451
+ "fast_cache_read_input": 0.2,
2584
3452
  "fast_cache_write_input": 5.0,
2585
- "fast_data_residency_cache_read_input": 0.44,
3453
+ "fast_data_residency_cache_read_input": 0.22,
2586
3454
  "fast_data_residency_cache_write_input": 5.5,
2587
3455
  "fast_data_residency_input": 4.4,
2588
3456
  "fast_data_residency_output": 22.0,
2589
3457
  "fast_input": 4.0,
2590
3458
  "fast_output": 20.0,
2591
- "flex_cache_read_input": 0.1,
3459
+ "flex_cache_read_input": 0.05,
2592
3460
  "flex_cache_write_input": 1.25,
2593
- "flex_data_residency_cache_read_input": 0.11,
3461
+ "flex_data_residency_cache_read_input": 0.055,
2594
3462
  "flex_data_residency_cache_write_input": 1.375,
2595
3463
  "flex_data_residency_input": 1.1,
2596
3464
  "flex_data_residency_output": 5.5,
@@ -2598,9 +3466,9 @@
2598
3466
  "flex_output": 5.0,
2599
3467
  "input": 2.0,
2600
3468
  "output": 10.0,
2601
- "priority_cache_read_input": 0.4,
3469
+ "priority_cache_read_input": 0.2,
2602
3470
  "priority_cache_write_input": 5.0,
2603
- "priority_data_residency_cache_read_input": 0.44,
3471
+ "priority_data_residency_cache_read_input": 0.22,
2604
3472
  "priority_data_residency_cache_write_input": 5.5,
2605
3473
  "priority_data_residency_input": 4.4,
2606
3474
  "priority_data_residency_output": 22.0,
@@ -2680,6 +3548,13 @@
2680
3548
  "input": 5.0
2681
3549
  },
2682
3550
  "openai/gpt-image-2.5-flare": {
3551
+ "batch_cache_read_input": 0.625,
3552
+ "batch_data_residency_cache_read_input": 0.6875,
3553
+ "batch_data_residency_input": 2.75,
3554
+ "batch_image_cache_read_input": 1.0,
3555
+ "batch_image_input": 4.0,
3556
+ "batch_image_output": 15.0,
3557
+ "batch_input": 2.5,
2683
3558
  "cache_read_input": 1.25,
2684
3559
  "data_residency_cache_read_input": 1.375,
2685
3560
  "data_residency_input": 5.5,
@@ -2689,6 +3564,13 @@
2689
3564
  "input": 5.0
2690
3565
  },
2691
3566
  "openai/gpt-image-2.5-sunburst": {
3567
+ "batch_cache_read_input": 0.625,
3568
+ "batch_data_residency_cache_read_input": 0.6875,
3569
+ "batch_data_residency_input": 2.75,
3570
+ "batch_image_cache_read_input": 1.0,
3571
+ "batch_image_input": 4.0,
3572
+ "batch_image_output": 15.0,
3573
+ "batch_input": 2.5,
2692
3574
  "cache_read_input": 1.25,
2693
3575
  "data_residency_cache_read_input": 1.375,
2694
3576
  "data_residency_input": 5.5,
@@ -2726,6 +3608,9 @@
2726
3608
  "audio_input": 32.0,
2727
3609
  "audio_output": 64.0,
2728
3610
  "cache_read_input": 0.4,
3611
+ "data_residency_cache_read_input": 0.44,
3612
+ "data_residency_input": 4.4,
3613
+ "data_residency_output": 26.4,
2729
3614
  "image_cache_read_input": 0.5,
2730
3615
  "image_input": 5.0,
2731
3616
  "input": 4.0,
@@ -2736,6 +3621,9 @@
2736
3621
  "audio_input": 32.0,
2737
3622
  "audio_output": 64.0,
2738
3623
  "cache_read_input": 0.4,
3624
+ "data_residency_cache_read_input": 0.44,
3625
+ "data_residency_input": 4.4,
3626
+ "data_residency_output": 26.4,
2739
3627
  "image_cache_read_input": 0.5,
2740
3628
  "image_input": 5.0,
2741
3629
  "input": 4.0,
@@ -2746,6 +3634,9 @@
2746
3634
  "audio_input": 10.0,
2747
3635
  "audio_output": 20.0,
2748
3636
  "cache_read_input": 0.06,
3637
+ "data_residency_cache_read_input": 0.066,
3638
+ "data_residency_input": 0.66,
3639
+ "data_residency_output": 2.64,
2749
3640
  "image_cache_read_input": 0.08,
2750
3641
  "image_input": 0.8,
2751
3642
  "input": 0.6,
@@ -2854,6 +3745,10 @@
2854
3745
  "batch_input": 0.05,
2855
3746
  "input": 0.1
2856
3747
  },
3748
+ "openai/text-embedding-ada-002-v2": {
3749
+ "batch_input": 0.05,
3750
+ "input": 0.1
3751
+ },
2857
3752
  "openai/tts-1": {
2858
3753
  "text_to_speech_character": 15.0
2859
3754
  },
@@ -2985,6 +3880,18 @@
2985
3880
  "input": 0.5,
2986
3881
  "output": 2.5
2987
3882
  },
3883
+ "openrouter/anthropic/claude-haiku-5.5": {
3884
+ "cache_read_input": 0.01,
3885
+ "cache_write_input": 0.125,
3886
+ "input": 0.1,
3887
+ "output": 0.5
3888
+ },
3889
+ "openrouter/anthropic/claude-haiku-5.5:batch": {
3890
+ "cache_read_input": 0.005,
3891
+ "cache_write_input": 0.0625,
3892
+ "input": 0.05,
3893
+ "output": 0.25
3894
+ },
2988
3895
  "openrouter/anthropic/claude-opus-4": {
2989
3896
  "cache_read_input": 1.5,
2990
3897
  "cache_write_input": 18.75,
@@ -3135,6 +4042,18 @@
3135
4042
  "input": 2.0,
3136
4043
  "output": 10.0
3137
4044
  },
4045
+ "openrouter/anthropic/claude-sonnet-5.5": {
4046
+ "cache_read_input": 0.1,
4047
+ "cache_write_input": 2.5,
4048
+ "input": 2.0,
4049
+ "output": 10.0
4050
+ },
4051
+ "openrouter/anthropic/claude-sonnet-5.5:batch": {
4052
+ "cache_read_input": 0.05,
4053
+ "cache_write_input": 1.25,
4054
+ "input": 1.0,
4055
+ "output": 5.0
4056
+ },
3138
4057
  "openrouter/anthropic/claude-sonnet-5:batch": {
3139
4058
  "cache_read_input": 0.1,
3140
4059
  "cache_write_input": 1.25,
@@ -3249,12 +4168,13 @@
3249
4168
  "output": 1.25
3250
4169
  },
3251
4170
  "openrouter/deepseek/deepseek-chat": {
3252
- "input": 0.32,
3253
- "output": 0.89
4171
+ "input": 0.2574,
4172
+ "output": 1.0287
3254
4173
  },
3255
4174
  "openrouter/deepseek/deepseek-chat-v3-0324": {
3256
- "input": 0.25,
3257
- "output": 1.0
4175
+ "cache_read_input": 0.11,
4176
+ "input": 0.29,
4177
+ "output": 1.14
3258
4178
  },
3259
4179
  "openrouter/deepseek/deepseek-chat-v3.1": {
3260
4180
  "cache_read_input": 0.13,
@@ -3279,14 +4199,13 @@
3279
4199
  "output": 0.29
3280
4200
  },
3281
4201
  "openrouter/deepseek/deepseek-v3.1-terminus": {
3282
- "cache_read_input": 0.135,
3283
4202
  "input": 0.27,
3284
4203
  "output": 1.0
3285
4204
  },
3286
4205
  "openrouter/deepseek/deepseek-v3.2": {
3287
- "cache_read_input": 0.1345,
3288
- "input": 0.269,
3289
- "output": 0.4
4206
+ "cache_read_input": 0.135,
4207
+ "input": 0.259,
4208
+ "output": 0.42
3290
4209
  },
3291
4210
  "openrouter/deepseek/deepseek-v3.2-exp": {
3292
4211
  "input": 0.27,
@@ -3298,14 +4217,14 @@
3298
4217
  "output": 0.431
3299
4218
  },
3300
4219
  "openrouter/deepseek/deepseek-v4-flash": {
3301
- "cache_read_input": 0.00938,
3302
- "input": 0.0469,
3303
- "output": 0.0938
4220
+ "cache_read_input": 0.0131,
4221
+ "input": 0.0131,
4222
+ "output": 1.28
3304
4223
  },
3305
4224
  "openrouter/deepseek/deepseek-v4-flash-0731": {
3306
- "cache_read_input": 0.016,
3307
- "input": 0.021,
3308
- "output": 0.32
4225
+ "cache_read_input": 0.006,
4226
+ "input": 0.006,
4227
+ "output": 1.28
3309
4228
  },
3310
4229
  "openrouter/deepseek/deepseek-v4-flash-0731:batch": {
3311
4230
  "cache_read_input": 0.0035,
@@ -3323,14 +4242,14 @@
3323
4242
  "output": 0.33
3324
4243
  },
3325
4244
  "openrouter/deepseek/deepseek-v4-pro": {
3326
- "cache_read_input": 0.029,
3327
- "input": 0.348,
3328
- "output": 0.696
4245
+ "cache_read_input": 0.02436,
4246
+ "input": 0.29232,
4247
+ "output": 0.58464
3329
4248
  },
3330
4249
  "openrouter/deepseek/deepseek-v4-pro-0813": {
3331
- "cache_read_input": 0.24452,
3332
- "input": 0.24502,
3333
- "output": 3.5
4250
+ "cache_read_input": 0.044,
4251
+ "input": 1.32,
4252
+ "output": 3.96
3334
4253
  },
3335
4254
  "openrouter/deepseek/deepseek-v4-pro-0813:batch": {
3336
4255
  "cache_read_input": 0.022,
@@ -3338,9 +4257,9 @@
3338
4257
  "output": 1.98
3339
4258
  },
3340
4259
  "openrouter/deepseek/deepseek-v4.1-flash": {
3341
- "cache_read_input": 0.001,
3342
- "input": 0.035,
3343
- "output": 0.29
4260
+ "cache_read_input": 0.01,
4261
+ "input": 0.0283,
4262
+ "output": 1.0
3344
4263
  },
3345
4264
  "openrouter/deepseek/deepseek-v4.1-flash:batch": {
3346
4265
  "cache_read_input": 0.00336,
@@ -3612,6 +4531,10 @@
3612
4531
  "input": 0.375,
3613
4532
  "output": 1.875
3614
4533
  },
4534
+ "openrouter/google/gemini-nano-banana-2.1": {
4535
+ "input": 1.5,
4536
+ "output": 7.5
4537
+ },
3615
4538
  "openrouter/google/gemma-2-27b-it": {
3616
4539
  "input": 0.65,
3617
4540
  "output": 0.65
@@ -3634,9 +4557,9 @@
3634
4557
  "output": 0.12
3635
4558
  },
3636
4559
  "openrouter/google/gemma-4-26b-a4b-it": {
3637
- "cache_read_input": 0.0375,
3638
- "input": 0.0675,
3639
- "output": 0.225
4560
+ "cache_read_input": 0.05,
4561
+ "input": 0.09,
4562
+ "output": 0.3
3640
4563
  },
3641
4564
  "openrouter/google/gemma-4-31b-it": {
3642
4565
  "cache_read_input": 0.05,
@@ -3696,9 +4619,9 @@
3696
4619
  "output": 0.063
3697
4620
  },
3698
4621
  "openrouter/inclusionai/ling-3.0-flash-fin": {
3699
- "cache_read_input": 0.012,
3700
- "input": 0.06,
3701
- "output": 0.18
4622
+ "cache_read_input": 0.0084,
4623
+ "input": 0.042,
4624
+ "output": 0.1232
3702
4625
  },
3703
4626
  "openrouter/inclusionai/ling-3.0-flash-vl": {
3704
4627
  "cache_read_input": 0.0042,
@@ -3790,6 +4713,7 @@
3790
4713
  "output": 0.32
3791
4714
  },
3792
4715
  "openrouter/meta-llama/llama-4-maverick": {
4716
+ "cache_read_input": 0.05,
3793
4717
  "input": 0.1875,
3794
4718
  "output": 0.6525
3795
4719
  },
@@ -3858,12 +4782,12 @@
3858
4782
  "output": 1.1
3859
4783
  },
3860
4784
  "openrouter/minimax/minimax-m1": {
3861
- "input": 0.4,
4785
+ "input": 0.55,
3862
4786
  "output": 2.2
3863
4787
  },
3864
4788
  "openrouter/minimax/minimax-m2": {
3865
- "input": 0.255,
3866
- "output": 1.02
4789
+ "input": 0.3,
4790
+ "output": 1.2
3867
4791
  },
3868
4792
  "openrouter/minimax/minimax-m2-her": {
3869
4793
  "cache_read_input": 0.03,
@@ -3973,6 +4897,11 @@
3973
4897
  "input": 0.25,
3974
4898
  "output": 0.75
3975
4899
  },
4900
+ "openrouter/mistralai/mistral-large-4-0": {
4901
+ "cache_read_input": 0.07,
4902
+ "input": 0.68,
4903
+ "output": 2.09
4904
+ },
3976
4905
  "openrouter/mistralai/mistral-medium-3": {
3977
4906
  "cache_read_input": 0.04,
3978
4907
  "input": 0.4,
@@ -4052,7 +4981,6 @@
4052
4981
  "output": 2.5
4053
4982
  },
4054
4983
  "openrouter/moonshotai/kimi-k2-thinking": {
4055
- "cache_read_input": 0.15,
4056
4984
  "input": 0.6,
4057
4985
  "output": 2.5
4058
4986
  },
@@ -4062,14 +4990,14 @@
4062
4990
  "output": 2.25
4063
4991
  },
4064
4992
  "openrouter/moonshotai/kimi-k2.6": {
4065
- "cache_read_input": 0.16,
4066
- "input": 0.95,
4067
- "output": 4.0
4993
+ "cache_read_input": 0.1211,
4994
+ "input": 0.4375,
4995
+ "output": 2.45
4068
4996
  },
4069
4997
  "openrouter/moonshotai/kimi-k2.7-code": {
4070
4998
  "cache_read_input": 0.18,
4071
- "input": 0.6562,
4072
- "output": 3.3
4999
+ "input": 0.6712,
5000
+ "output": 3.35
4073
5001
  },
4074
5002
  "openrouter/moonshotai/kimi-k2.7-code:batch": {
4075
5003
  "cache_read_input": 0.19,
@@ -4077,9 +5005,9 @@
4077
5005
  "output": 4.0
4078
5006
  },
4079
5007
  "openrouter/moonshotai/kimi-k3": {
4080
- "cache_read_input": 0.3,
4081
- "input": 3.0,
4082
- "output": 15.0
5008
+ "cache_read_input": 0.43,
5009
+ "input": 0.62,
5010
+ "output": 12.3
4083
5011
  },
4084
5012
  "openrouter/moonshotai/kimi-k3:batch": {
4085
5013
  "cache_read_input": 0.228,
@@ -4108,6 +5036,16 @@
4108
5036
  "input": 0.25,
4109
5037
  "output": 1.0
4110
5038
  },
5039
+ "openrouter/nex-agi/nex-n2.5-mini": {
5040
+ "cache_read_input": 0.0025,
5041
+ "input": 0.025,
5042
+ "output": 0.1
5043
+ },
5044
+ "openrouter/nex-agi/nex-n2.5-pro": {
5045
+ "cache_read_input": 0.015,
5046
+ "input": 0.075,
5047
+ "output": 0.25
5048
+ },
4111
5049
  "openrouter/nousresearch/hermes-2-pro-llama-3-8b": {
4112
5050
  "input": 0.14,
4113
5051
  "output": 0.14
@@ -4133,18 +5071,17 @@
4133
5071
  "output": 0.4
4134
5072
  },
4135
5073
  "openrouter/nvidia/nemotron-3-nano-30b-a3b": {
4136
- "cache_read_input": 0.03,
4137
- "input": 0.05,
4138
- "output": 0.2
5074
+ "input": 0.06,
5075
+ "output": 0.24
4139
5076
  },
4140
5077
  "openrouter/nvidia/nemotron-3-super-120b-a12b": {
4141
5078
  "input": 0.08,
4142
5079
  "output": 0.45
4143
5080
  },
4144
5081
  "openrouter/nvidia/nemotron-3-ultra-550b-a55b": {
4145
- "cache_read_input": 0.12,
4146
- "input": 0.6,
4147
- "output": 2.4
5082
+ "cache_read_input": 0.1,
5083
+ "input": 0.5,
5084
+ "output": 2.2
4148
5085
  },
4149
5086
  "openrouter/nvidia/nemotron-3-ultra-550b-a55b:batch": {
4150
5087
  "cache_read_input": 0.2,
@@ -4156,9 +5093,9 @@
4156
5093
  "output": 0.2
4157
5094
  },
4158
5095
  "openrouter/nvidia/nemotron-3.5-lightning": {
4159
- "cache_read_input": 0.04,
4160
- "input": 0.08,
4161
- "output": 0.2
5096
+ "cache_read_input": 0.0245,
5097
+ "input": 0.049,
5098
+ "output": 0.14
4162
5099
  },
4163
5100
  "openrouter/nvidia/nemotron-nano-9b-v2": {
4164
5101
  "input": 0.04,
@@ -4622,6 +5559,30 @@
4622
5559
  "input": 1.0,
4623
5560
  "output": 5.0
4624
5561
  },
5562
+ "openrouter/openai/gpt-6.1-sol": {
5563
+ "cache_read_input": 0.1,
5564
+ "cache_write_input": 2.5,
5565
+ "input": 2.0,
5566
+ "output": 10.0
5567
+ },
5568
+ "openrouter/openai/gpt-6.1-sol-pro": {
5569
+ "cache_read_input": 0.1,
5570
+ "cache_write_input": 2.5,
5571
+ "input": 2.0,
5572
+ "output": 10.0
5573
+ },
5574
+ "openrouter/openai/gpt-6.1-sol-pro:batch": {
5575
+ "cache_read_input": 0.05,
5576
+ "cache_write_input": 1.25,
5577
+ "input": 1.0,
5578
+ "output": 5.0
5579
+ },
5580
+ "openrouter/openai/gpt-6.1-sol:batch": {
5581
+ "cache_read_input": 0.05,
5582
+ "cache_write_input": 1.25,
5583
+ "input": 1.0,
5584
+ "output": 5.0
5585
+ },
4625
5586
  "openrouter/openai/gpt-audio": {
4626
5587
  "audio_input": 32.0,
4627
5588
  "input": 2.5,
@@ -4638,15 +5599,15 @@
4638
5599
  "output": 30.0
4639
5600
  },
4640
5601
  "openrouter/openai/gpt-oss-120b": {
4641
- "cache_read_input": 0.075,
4642
- "input": 0.15,
4643
- "output": 0.6
5602
+ "input": 0.037,
5603
+ "output": 0.17
4644
5604
  },
4645
5605
  "openrouter/openai/gpt-oss-120b:batch": {
4646
5606
  "input": 0.0296,
4647
5607
  "output": 0.136
4648
5608
  },
4649
5609
  "openrouter/openai/gpt-oss-20b": {
5610
+ "cache_read_input": 0.009,
4650
5611
  "input": 0.018,
4651
5612
  "output": 0.09
4652
5613
  },
@@ -4798,6 +5759,7 @@
4798
5759
  "output": 1.1
4799
5760
  },
4800
5761
  "openrouter/prism-ml/ternary-bonsai-2-27b": {
5762
+ "cache_read_input": 0.0375,
4801
5763
  "input": 0.075,
4802
5764
  "output": 0.5
4803
5765
  },
@@ -4841,9 +5803,8 @@
4841
5803
  "output": 1.82
4842
5804
  },
4843
5805
  "openrouter/qwen/qwen3-235b-a22b-2507": {
4844
- "cache_read_input": 0.0175,
4845
- "input": 0.0875,
4846
- "output": 0.35
5806
+ "input": 0.09,
5807
+ "output": 0.55
4847
5808
  },
4848
5809
  "openrouter/qwen/qwen3-235b-a22b-thinking-2507": {
4849
5810
  "input": 0.23,
@@ -4906,8 +5867,7 @@
4906
5867
  "output": 3.9
4907
5868
  },
4908
5869
  "openrouter/qwen/qwen3-next-80b-a3b-instruct": {
4909
- "cache_read_input": 0.07,
4910
- "input": 0.1,
5870
+ "input": 0.09,
4911
5871
  "output": 1.1
4912
5872
  },
4913
5873
  "openrouter/qwen/qwen3-next-80b-a3b-thinking": {
@@ -4948,18 +5908,18 @@
4948
5908
  "output": 2.08
4949
5909
  },
4950
5910
  "openrouter/qwen/qwen3.5-27b": {
4951
- "input": 0.195,
4952
- "output": 1.56
5911
+ "input": 0.26,
5912
+ "output": 2.6
4953
5913
  },
4954
5914
  "openrouter/qwen/qwen3.5-35b-a3b": {
4955
- "cache_read_input": 0.15625,
4956
- "input": 0.3125,
4957
- "output": 1.25
5915
+ "cache_read_input": 0.05,
5916
+ "input": 0.15,
5917
+ "output": 1.0
4958
5918
  },
4959
5919
  "openrouter/qwen/qwen3.5-397b-a17b": {
4960
- "cache_read_input": 0.225,
4961
- "input": 0.55,
4962
- "output": 3.5
5920
+ "cache_read_input": 0.22,
5921
+ "input": 0.45,
5922
+ "output": 3.0
4963
5923
  },
4964
5924
  "openrouter/qwen/qwen3.5-9b": {
4965
5925
  "input": 0.1,
@@ -4983,8 +5943,8 @@
4983
5943
  "output": 1.8
4984
5944
  },
4985
5945
  "openrouter/qwen/qwen3.6-27b": {
4986
- "input": 0.32,
4987
- "output": 3.2
5946
+ "input": 0.45,
5947
+ "output": 2.7
4988
5948
  },
4989
5949
  "openrouter/qwen/qwen3.6-35b-a3b": {
4990
5950
  "cache_read_input": 0.05,
@@ -5036,8 +5996,9 @@
5036
5996
  },
5037
5997
  "openrouter/qwen/qwen3.8-27b": {
5038
5998
  "cache_read_input": 0.085,
5039
- "input": 0.42,
5040
- "output": 3.0
5999
+ "cache_write_input": 0.53125,
6000
+ "input": 0.425,
6001
+ "output": 2.55
5041
6002
  },
5042
6003
  "openrouter/qwen/qwen3.8-flash": {
5043
6004
  "cache_read_input": 0.016,
@@ -5132,6 +6093,11 @@
5132
6093
  "input": 0.2,
5133
6094
  "output": 1.15
5134
6095
  },
6096
+ "openrouter/stepfun/step-5-preview": {
6097
+ "cache_read_input": 0.05,
6098
+ "input": 1.0,
6099
+ "output": 2.7
6100
+ },
5135
6101
  "openrouter/switchpoint/router": {
5136
6102
  "input": 0.85,
5137
6103
  "output": 3.4
@@ -5210,6 +6176,11 @@
5210
6176
  "input": 2.5,
5211
6177
  "output": 7.5
5212
6178
  },
6179
+ "openrouter/unbiased/pareto-26.10-preview": {
6180
+ "cache_read_input": 0.03,
6181
+ "input": 0.8,
6182
+ "output": 3.2
6183
+ },
5213
6184
  "openrouter/undi95/remm-slerp-l2-13b": {
5214
6185
  "input": 0.35,
5215
6186
  "output": 0.65
@@ -5264,9 +6235,9 @@
5264
6235
  "output": 6.0
5265
6236
  },
5266
6237
  "openrouter/x-ai/grok-4.7": {
5267
- "cache_read_input": 0.4,
5268
- "input": 1.6,
5269
- "output": 4.8
6238
+ "cache_read_input": 0.5,
6239
+ "input": 2.0,
6240
+ "output": 6.0
5270
6241
  },
5271
6242
  "openrouter/x-ai/grok-build-0.1": {
5272
6243
  "cache_read_input": 0.2,
@@ -5362,14 +6333,14 @@
5362
6333
  "output": 4.0
5363
6334
  },
5364
6335
  "openrouter/z-ai/glm-5.1": {
5365
- "cache_read_input": 0.17914,
5366
- "input": 0.9646,
5367
- "output": 3.0316
6336
+ "cache_read_input": 0.1794,
6337
+ "input": 0.966,
6338
+ "output": 3.036
5368
6339
  },
5369
6340
  "openrouter/z-ai/glm-5.2": {
5370
- "cache_read_input": 0.12064,
5371
- "input": 0.6496,
5372
- "output": 2.0416
6341
+ "cache_read_input": 0.03,
6342
+ "input": 0.03,
6343
+ "output": 10.0
5373
6344
  },
5374
6345
  "openrouter/z-ai/glm-5.2:batch": {
5375
6346
  "cache_read_input": 0.07,
@@ -5377,14 +6348,14 @@
5377
6348
  "output": 2.2
5378
6349
  },
5379
6350
  "openrouter/z-ai/glm-5.3": {
5380
- "cache_read_input": 0.26,
5381
- "input": 1.4,
5382
- "output": 4.4
6351
+ "cache_read_input": 0.048,
6352
+ "input": 0.075,
6353
+ "output": 4.2
5383
6354
  },
5384
6355
  "openrouter/z-ai/glm-5.3-flash": {
5385
- "cache_read_input": 0.01,
5386
- "input": 0.045,
5387
- "output": 0.14
6356
+ "cache_read_input": 0.03,
6357
+ "input": 0.15,
6358
+ "output": 0.5
5388
6359
  },
5389
6360
  "openrouter/z-ai/glm-5.3-flash:batch": {
5390
6361
  "cache_read_input": 0.012,
@@ -5418,10 +6389,10 @@
5418
6389
  "output": 50.0
5419
6390
  },
5420
6391
  "openrouter/~anthropic/claude-haiku-latest": {
5421
- "cache_read_input": 0.1,
5422
- "cache_write_input": 1.25,
5423
- "input": 1.0,
5424
- "output": 5.0
6392
+ "cache_read_input": 0.01,
6393
+ "cache_write_input": 0.125,
6394
+ "input": 0.1,
6395
+ "output": 0.5
5425
6396
  },
5426
6397
  "openrouter/~anthropic/claude-opus-latest": {
5427
6398
  "cache_read_input": 0.2,
@@ -5430,25 +6401,25 @@
5430
6401
  "output": 20.0
5431
6402
  },
5432
6403
  "openrouter/~anthropic/claude-sonnet-latest": {
5433
- "cache_read_input": 0.2,
6404
+ "cache_read_input": 0.1,
5434
6405
  "cache_write_input": 2.5,
5435
6406
  "input": 2.0,
5436
6407
  "output": 10.0
5437
6408
  },
5438
6409
  "openrouter/~deepseek/deepseek-flash-latest": {
5439
- "cache_read_input": 0.001,
5440
- "input": 0.035,
5441
- "output": 0.29
6410
+ "cache_read_input": 0.01,
6411
+ "input": 0.0283,
6412
+ "output": 1.0
5442
6413
  },
5443
6414
  "openrouter/~deepseek/deepseek-pro-latest": {
5444
- "cache_read_input": 0.00777,
5445
- "input": 0.2442,
5446
- "output": 0.7326
6415
+ "cache_read_input": 0.0953,
6416
+ "input": 0.1271,
6417
+ "output": 8.0
5447
6418
  },
5448
6419
  "openrouter/~deepseek/deepseek-v4-flash-latest": {
5449
- "cache_read_input": 0.016,
5450
- "input": 0.021,
5451
- "output": 0.32
6420
+ "cache_read_input": 0.0048,
6421
+ "input": 0.0048,
6422
+ "output": 0.554651
5452
6423
  },
5453
6424
  "openrouter/~google/gemini-flash-latest": {
5454
6425
  "audio_input": 0.75,
@@ -5467,9 +6438,9 @@
5467
6438
  "output": 12.0
5468
6439
  },
5469
6440
  "openrouter/~moonshotai/kimi-latest": {
5470
- "cache_read_input": 0.11455,
5471
- "input": 0.9875,
5472
- "output": 5.53
6441
+ "cache_read_input": 0.45,
6442
+ "input": 0.45,
6443
+ "output": 13.0
5473
6444
  },
5474
6445
  "openrouter/~openai/gpt-astra-latest": {
5475
6446
  "cache_read_input": 1.0,
@@ -5495,7 +6466,7 @@
5495
6466
  "output": 4.5
5496
6467
  },
5497
6468
  "openrouter/~openai/gpt-sol-latest": {
5498
- "cache_read_input": 0.2,
6469
+ "cache_read_input": 0.1,
5499
6470
  "cache_write_input": 2.5,
5500
6471
  "input": 2.0,
5501
6472
  "output": 10.0
@@ -5507,19 +6478,19 @@
5507
6478
  "output": 12.0
5508
6479
  },
5509
6480
  "openrouter/~x-ai/grok-latest": {
5510
- "cache_read_input": 0.4,
5511
- "input": 1.6,
5512
- "output": 4.8
6481
+ "cache_read_input": 0.5,
6482
+ "input": 2.0,
6483
+ "output": 6.0
5513
6484
  },
5514
6485
  "openrouter/~z-ai/glm-flash-latest": {
5515
- "cache_read_input": 0.01,
5516
- "input": 0.045,
5517
- "output": 0.14
6486
+ "cache_read_input": 0.02,
6487
+ "input": 0.032,
6488
+ "output": 5.372581
5518
6489
  },
5519
6490
  "openrouter/~z-ai/glm-latest": {
5520
- "cache_read_input": 0.044965,
5521
- "input": 0.2737,
5522
- "output": 2.574
6491
+ "cache_read_input": 0.0439,
6492
+ "input": 0.0472,
6493
+ "output": 12.0
5523
6494
  },
5524
6495
  "xai/grok-4.20": {
5525
6496
  "_context_price_threshold_tokens": 199999,