scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-15 09:12:18 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 311

feat(cost-map): infer successor_model as the next version in the same family for 136 dated rows with no published replacement

Browse source
This commit is contained in:
devin-ai-integration[bot] 2026-11-03 20:04:49 +00:00
parent 71b27c83a4
commit e685d855ad
2 changed files with 272 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

136
litellm/model_prices_and_context_window_backup.json
View file

@ -3409,6 +3409,7 @@
"cache_creation_input_token_cost": 3.75e-06,
"cache_read_input_token_cost": 3e-07,
"deprecation_date": "2026-10-14",
"successor_model": "anthropic.claude-sonnet-5",
"input_cost_per_token": 3e-06,
"input_cost_per_token_above_200k_tokens": 6e-06,
"output_cost_per_token_above_200k_tokens": 2.25e-05,
@ -3452,6 +3453,7 @@
"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
"deprecation_date": "2027-04-08",
"successor_model": "anthropic.claude-sonnet-5-5",
"litellm_provider": "bedrock_converse",
"supports_tool_search": true,
"max_input_tokens": 200000,
@ -3686,6 +3688,7 @@
"cache_creation_input_token_cost": 3.75e-06,
"cache_read_input_token_cost": 3e-07,
"deprecation_date": "2026-10-14",
"successor_model": "apac.anthropic.claude-sonnet-5",
"input_cost_per_token": 3e-06,
"input_cost_per_token_above_200k_tokens": 6e-06,
"output_cost_per_token_above_200k_tokens": 2.25e-05,
@ -3741,6 +3744,7 @@
"cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05,
"cache_read_input_token_cost_above_200k_tokens": 6.6e-07,
"deprecation_date": "2027-04-08",
"successor_model": "au.anthropic.claude-sonnet-5-5",
"litellm_provider": "bedrock_converse",
"supports_tool_search": true,
"max_input_tokens": 200000,
@ -3824,6 +3828,7 @@
},
"azure_ai/claude-haiku-4-5": {
"deprecation_date": "2026-11-15",
"successor_model": "azure_ai/claude-haiku-5-5",
"cache_creation_input_token_cost": 1.25e-06,
"cache_creation_input_token_cost_above_1hr": 2e-06,
"cache_read_input_token_cost": 1e-07,
@ -3847,6 +3852,7 @@
},
"azure_ai/claude-opus-4-5": {
"deprecation_date": "2026-11-24",
"successor_model": "azure_ai/claude-opus-5-5",
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_1hr": 1e-05,
"cache_read_input_token_cost": 5e-07,
@ -4726,6 +4732,7 @@
},
"azure_ai/gpt-5.4": {
"deprecation_date": "2027-09-02",
"successor_model": "azure_ai/gpt-5.5",
"cache_read_input_token_cost": 2.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 5e-07,
"cache_read_input_token_cost_priority": 5e-07,
@ -4773,6 +4780,7 @@
},
"azure_ai/gpt-5.4-2026-03-05": {
"deprecation_date": "2027-09-02",
"successor_model": "azure_ai/gpt-5.5",
"cache_read_input_token_cost": 2.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 5e-07,
"cache_read_input_token_cost_priority": 5e-07,
@ -5270,6 +5278,7 @@
"cache_read_input_token_cost": 1.375e-07,
"cache_read_input_token_cost_priority": 2.75e-07,
"deprecation_date": "2027-02-09",
"successor_model": "azure/eu/gpt-5.1",
"input_cost_per_token": 1.375e-06,
"input_cost_per_token_batches": 6.875e-07,
"input_cost_per_token_priority": 2.75e-06,
@ -5314,6 +5323,7 @@
"cache_read_input_token_cost": 2.75e-08,
"cache_read_input_token_cost_priority": 4.95e-08,
"deprecation_date": "2027-02-09",
"successor_model": "azure/eu/gpt-5.4-mini",
"input_cost_per_token": 2.75e-07,
"input_cost_per_token_batches": 1.375e-07,
"input_cost_per_token_priority": 4.95e-07,
@ -5356,6 +5366,7 @@
},
"azure/eu/gpt-5.1": {
"deprecation_date": "2027-05-15",
"successor_model": "azure/eu/gpt-5.2",
"cache_read_input_token_cost": 1.375e-07,
"cache_read_input_token_cost_batches": 6.875e-08,
"cache_read_input_token_cost_priority": 2.75e-07,
@ -5403,6 +5414,7 @@
},
"azure/eu/gpt-5.1-codex": {
"deprecation_date": "2027-05-15",
"successor_model": "azure/eu/gpt-5.2-codex",
"cache_read_input_token_cost": 1.375e-07,
"input_cost_per_token": 1.375e-06,
"litellm_provider": "azure",
@ -5466,6 +5478,7 @@
"azure/eu/gpt-5-nano-2025-08-07": {
"cache_read_input_token_cost": 5.5e-09,
"deprecation_date": "2027-02-09",
"successor_model": "azure/eu/gpt-5.4-nano",
"input_cost_per_token": 5.5e-08,
"input_cost_per_token_batches": 2.75e-08,
"litellm_provider": "azure",
@ -5872,6 +5885,7 @@
},
"azure/gpt-4": {
"deprecation_date": "2025-06-06",
"successor_model": "azure/gpt-4.1",
"input_cost_per_token": 3e-05,
"litellm_provider": "azure",
"max_input_tokens": 8192,
@ -5895,6 +5909,7 @@
},
"azure/gpt-4-0613": {
"deprecation_date": "2025-06-06",
"successor_model": "azure/gpt-4.1",
"input_cost_per_token": 3e-05,
"litellm_provider": "azure",
"max_input_tokens": 8192,
@ -5976,6 +5991,7 @@
},
"azure/gpt-4.1": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/gpt-5.1",
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_priority": 8.75e-07,
"input_cost_per_token": 2e-06,
@ -6018,6 +6034,7 @@
},
"azure/gpt-4.1-2025-04-14": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/gpt-5.1",
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_priority": 8.75e-07,
"input_cost_per_token": 2e-06,
@ -6060,6 +6077,7 @@
},
"azure/gpt-4.1-mini": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/gpt-5.4-mini",
"cache_read_input_token_cost": 1e-07,
"cache_read_input_token_cost_priority": 1.75e-07,
"input_cost_per_token": 4e-07,
@ -6102,6 +6120,7 @@
},
"azure/gpt-4.1-mini-2025-04-14": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/gpt-5.4-mini",
"cache_read_input_token_cost": 1e-07,
"cache_read_input_token_cost_priority": 1.75e-07,
"input_cost_per_token": 4e-07,
@ -6144,6 +6163,7 @@
},
"azure/gpt-4.1-nano": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/gpt-5.4-nano",
"cache_read_input_token_cost": 2.5e-08,
"input_cost_per_token": 1e-07,
"input_cost_per_token_batches": 5e-08,
@ -6177,6 +6197,7 @@
},
"azure/gpt-4.1-nano-2025-04-14": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/gpt-5.4-nano",
"cache_read_input_token_cost": 2.5e-08,
"input_cost_per_token": 1e-07,
"input_cost_per_token_batches": 5e-08,
@ -6711,6 +6732,7 @@
"cache_read_input_audio_token_cost": 4e-07,
"cache_read_input_token_cost": 4e-07,
"deprecation_date": "2027-08-24",
"successor_model": "azure/gpt-realtime-2.1-2026-07-07",
"input_cost_per_audio_token": 3.2e-05,
"input_cost_per_image_token": 5e-06,
"input_cost_per_token": 4e-06,
@ -6748,6 +6770,7 @@
"cache_read_input_audio_token_cost": 4e-07,
"cache_read_input_token_cost": 4e-07,
"deprecation_date": "2027-08-24",
"successor_model": "azure/gpt-realtime-2.1-2026-07-07",
"input_cost_per_audio_token": 3.2e-05,
"input_cost_per_image_token": 5e-06,
"input_cost_per_token": 4e-06,
@ -7065,6 +7088,7 @@
"cache_read_input_token_cost": 1.25e-07,
"cache_read_input_token_cost_priority": 2.5e-07,
"deprecation_date": "2027-05-15",
"successor_model": "azure/gpt-5.2",
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_priority": 2.5e-06,
"litellm_provider": "azure",
@ -7112,6 +7136,7 @@
"cache_read_input_token_cost": 1.25e-07,
"cache_read_input_token_cost_priority": 2.5e-07,
"deprecation_date": "2027-05-15",
"successor_model": "azure/gpt-5.2-codex",
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_priority": 2.5e-06,
"litellm_provider": "azure",
@ -7178,6 +7203,7 @@
},
"azure/gpt-5": {
"deprecation_date": "2027-02-09",
"successor_model": "azure/gpt-5.1",
"cache_read_input_token_cost": 1.25e-07,
"cache_read_input_token_cost_batches": 6.25e-08,
"cache_read_input_token_cost_priority": 2.5e-07,
@ -7224,6 +7250,7 @@
"cache_read_input_token_cost": 1.25e-07,
"cache_read_input_token_cost_priority": 2.5e-07,
"deprecation_date": "2027-02-09",
"successor_model": "azure/gpt-5.1",
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_batches": 6.25e-07,
"input_cost_per_token_priority": 2.5e-06,
@ -7267,6 +7294,7 @@
"azure/gpt-5-codex": {
"cache_read_input_token_cost": 1.25e-07,
"deprecation_date": "2027-03-17",
"successor_model": "azure/gpt-5.1-codex",
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
@ -7297,6 +7325,7 @@
},
"azure/gpt-5-mini": {
"deprecation_date": "2027-02-09",
"successor_model": "azure/gpt-5.4-mini",
"cache_read_input_token_cost": 2.5e-08,
"cache_read_input_token_cost_batches": 1.25e-08,
"cache_read_input_token_cost_priority": 4.5e-08,
@ -7343,6 +7372,7 @@
"cache_read_input_token_cost": 2.5e-08,
"cache_read_input_token_cost_priority": 4.5e-08,
"deprecation_date": "2027-02-09",
"successor_model": "azure/gpt-5.4-mini",
"input_cost_per_token": 2.5e-07,
"input_cost_per_token_batches": 1.25e-07,
"input_cost_per_token_priority": 4.5e-07,
@ -7385,6 +7415,7 @@
},
"azure/gpt-5-nano": {
"deprecation_date": "2027-02-09",
"successor_model": "azure/gpt-5.4-nano",
"cache_read_input_token_cost": 5e-09,
"cache_read_input_token_cost_batches": 2.5e-09,
"input_cost_per_token": 5e-08,
@ -7427,6 +7458,7 @@
"azure/gpt-5-nano-2025-08-07": {
"cache_read_input_token_cost": 5e-09,
"deprecation_date": "2027-02-09",
"successor_model": "azure/gpt-5.4-nano",
"input_cost_per_token": 5e-08,
"input_cost_per_token_batches": 2.5e-08,
"litellm_provider": "azure",
@ -7467,6 +7499,7 @@
},
"azure/gpt-5-pro": {
"deprecation_date": "2027-04-07",
"successor_model": "azure/gpt-5.2-pro",
"input_cost_per_token": 1.5e-05,
"input_cost_per_token_batches": 7.5e-06,
"litellm_provider": "azure",
@ -7503,6 +7536,7 @@
},
"azure/gpt-5.1": {
"deprecation_date": "2027-05-15",
"successor_model": "azure/gpt-5.2",
"cache_read_input_token_cost": 1.25e-07,
"cache_read_input_token_cost_batches": 6.25e-08,
"cache_read_input_token_cost_priority": 2.5e-07,
@ -7799,6 +7833,7 @@
},
"azure/gpt-5.1-codex": {
"deprecation_date": "2027-05-15",
"successor_model": "azure/gpt-5.2-codex",
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
@ -7892,6 +7927,7 @@
},
"azure/gpt-5.2": {
"deprecation_date": "2027-06-08",
"successor_model": "azure/gpt-5.4",
"cache_read_input_token_cost": 1.75e-07,
"cache_read_input_token_cost_batches": 8.75e-08,
"cache_read_input_token_cost_priority": 3.5e-07,
@ -7939,6 +7975,7 @@
"cache_read_input_token_cost": 1.75e-07,
"cache_read_input_token_cost_priority": 3.5e-07,
"deprecation_date": "2027-06-08",
"successor_model": "azure/gpt-5.4",
"input_cost_per_token": 1.75e-06,
"input_cost_per_token_batches": 8.75e-07,
"input_cost_per_token_priority": 3.5e-06,
@ -7983,6 +8020,7 @@
"azure/gpt-5.2-codex": {
"cache_read_input_token_cost": 1.75e-07,
"deprecation_date": "2027-07-13",
"successor_model": "azure/gpt-5.3-codex",
"input_cost_per_token": 1.75e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
@ -8128,6 +8166,7 @@
},
"azure/gpt-5.4": {
"deprecation_date": "2027-09-02",
"successor_model": "azure/gpt-5.5",
"cache_read_input_token_cost": 2.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 5e-07,
"cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-07,
@ -8185,6 +8224,7 @@
},
"azure/us/gpt-5.4": {
"deprecation_date": "2027-09-02",
"successor_model": "azure/us/gpt-5.5",
"cache_read_input_token_cost": 2.75e-07,
"cache_read_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07,
@ -8234,6 +8274,7 @@
},
"azure/eu/gpt-5.4": {
"deprecation_date": "2027-09-02",
"successor_model": "azure/eu/gpt-5.5",
"cache_read_input_token_cost": 2.75e-07,
"cache_read_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07,
@ -8288,6 +8329,7 @@
"cache_read_input_token_cost_priority": 5e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 1e-06,
"deprecation_date": "2027-09-02",
"successor_model": "azure/gpt-5.5",
"input_cost_per_token": 2.5e-06,
"input_cost_per_token_above_272k_tokens": 5e-06,
"input_cost_per_token_priority": 5e-06,
@ -8343,6 +8385,7 @@
"cache_read_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_read_input_token_cost_priority": 5.5e-07,
"deprecation_date": "2027-09-02",
"successor_model": "azure/us/gpt-5.5",
"input_cost_per_token": 2.75e-06,
"input_cost_per_token_priority": 5.5e-06,
"output_cost_per_token": 1.65e-05,
@ -8392,6 +8435,7 @@
"cache_read_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_read_input_token_cost_priority": 5.5e-07,
"deprecation_date": "2027-09-02",
"successor_model": "azure/eu/gpt-5.5",
"input_cost_per_token": 2.75e-06,
"input_cost_per_token_priority": 5.5e-06,
"output_cost_per_token": 1.65e-05,
@ -8438,6 +8482,7 @@
},
"azure/gpt-5.4-pro": {
"deprecation_date": "2027-09-07",
"successor_model": "azure/gpt-5.5-pro",
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
"input_cost_per_token": 3e-05,
@ -8489,6 +8534,7 @@
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
"deprecation_date": "2027-09-07",
"successor_model": "azure/gpt-5.5-pro",
"input_cost_per_token": 3e-05,
"input_cost_per_token_above_272k_tokens": 6e-05,
"input_cost_per_token_above_272k_tokens_flex": 3e-05,
@ -8601,6 +8647,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06,
"cache_read_input_token_cost_flex": 2e-07,
"deprecation_date": "2028-01-11",
"successor_model": "azure/gpt-6-sol",
"input_cost_per_token": 4e-06,
"input_cost_per_token_above_272k_tokens": 8e-06,
"input_cost_per_token_above_272k_tokens_flex": 4e-06,
@ -8664,6 +8711,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06,
"cache_read_input_token_cost_flex": 2e-07,
"deprecation_date": "2028-01-11",
"successor_model": "azure/gpt-6-sol",
"input_cost_per_token": 4e-06,
"input_cost_per_token_above_272k_tokens": 8e-06,
"input_cost_per_token_above_272k_tokens_flex": 4e-06,
@ -8727,6 +8775,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
"cache_read_input_token_cost_flex": 1e-07,
"deprecation_date": "2028-01-11",
"successor_model": "azure/gpt-6.1-terra",
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"input_cost_per_token_above_272k_tokens_flex": 2e-06,
@ -8790,6 +8839,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
"cache_read_input_token_cost_flex": 1e-07,
"deprecation_date": "2028-01-11",
"successor_model": "azure/gpt-6.1-terra",
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"input_cost_per_token_above_272k_tokens_flex": 2e-06,
@ -8853,6 +8903,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-08,
"cache_read_input_token_cost_flex": 1e-08,
"deprecation_date": "2028-01-11",
"successor_model": "azure/gpt-6-luna",
"input_cost_per_token": 2e-07,
"input_cost_per_token_above_272k_tokens": 4e-07,
"input_cost_per_token_above_272k_tokens_flex": 2e-07,
@ -8916,6 +8967,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-08,
"cache_read_input_token_cost_flex": 1e-08,
"deprecation_date": "2028-01-11",
"successor_model": "azure/gpt-6-luna",
"input_cost_per_token": 2e-07,
"input_cost_per_token_above_272k_tokens": 4e-07,
"input_cost_per_token_above_272k_tokens_flex": 2e-07,
@ -9832,6 +9884,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06,
"cache_read_input_token_cost_priority": 8.8e-07,
"deprecation_date": "2028-01-11",
"successor_model": "azure/us/gpt-6-sol",
"input_cost_per_token": 4.4e-06,
"input_cost_per_token_above_272k_tokens": 8.8e-06,
"input_cost_per_token_above_272k_tokens_priority": 1.76e-05,
@ -9887,6 +9940,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07,
"cache_read_input_token_cost_priority": 4.4e-07,
"deprecation_date": "2028-01-11",
"successor_model": "azure/us/gpt-6.1-terra",
"input_cost_per_token": 2.2e-06,
"input_cost_per_token_above_272k_tokens": 4.4e-06,
"input_cost_per_token_above_272k_tokens_priority": 8.8e-06,
@ -9942,6 +9996,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-08,
"cache_read_input_token_cost_priority": 4.4e-08,
"deprecation_date": "2028-01-11",
"successor_model": "azure/us/gpt-6-luna",
"input_cost_per_token": 2.2e-07,
"input_cost_per_token_above_272k_tokens": 4.4e-07,
"input_cost_per_token_above_272k_tokens_priority": 8.8e-07,
@ -10234,6 +10289,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06,
"cache_read_input_token_cost_priority": 8.8e-07,
"deprecation_date": "2028-01-11",
"successor_model": "azure/eu/gpt-6-sol",
"input_cost_per_token": 4.4e-06,
"input_cost_per_token_above_272k_tokens": 8.8e-06,
"input_cost_per_token_above_272k_tokens_priority": 1.76e-05,
@ -10289,6 +10345,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07,
"cache_read_input_token_cost_priority": 4.4e-07,
"deprecation_date": "2028-01-11",
"successor_model": "azure/eu/gpt-6.1-terra",
"input_cost_per_token": 2.2e-06,
"input_cost_per_token_above_272k_tokens": 4.4e-06,
"input_cost_per_token_above_272k_tokens_priority": 8.8e-06,
@ -10344,6 +10401,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-08,
"cache_read_input_token_cost_priority": 4.4e-08,
"deprecation_date": "2028-01-11",
"successor_model": "azure/eu/gpt-6-luna",
"input_cost_per_token": 2.2e-07,
"input_cost_per_token_above_272k_tokens": 4.4e-07,
"input_cost_per_token_above_272k_tokens_priority": 8.8e-07,
@ -10391,6 +10449,7 @@
},
"azure/gpt-5.5": {
"deprecation_date": "2027-10-26",
"successor_model": "azure/gpt-5.6",
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_above_272k_tokens_batches": 5e-07,
@ -10451,6 +10510,7 @@
},
"azure/us/gpt-5.5": {
"deprecation_date": "2027-10-26",
"successor_model": "azure/us/gpt-5.6",
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07,
@ -10505,6 +10565,7 @@
},
"azure/eu/gpt-5.5": {
"deprecation_date": "2027-10-26",
"successor_model": "azure/eu/gpt-5.6",
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07,
@ -10606,6 +10667,7 @@
"supports_vision": true,
"supports_web_search": true,
"deprecation_date": "2027-10-26",
"successor_model": "azure/gpt-5.6",
"input_cost_per_token_above_272k_tokens_batches": 5e-06,
"input_cost_per_token_above_272k_tokens_flex": 5e-06,
"input_cost_per_token_batches": 2.5e-06,
@ -10616,6 +10678,7 @@
},
"azure/gpt-5.5-2026-04-24": {
"deprecation_date": "2027-10-26",
"successor_model": "azure/gpt-5.6",
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_priority": 1.25e-06,
@ -10719,6 +10782,7 @@
"supports_vision": true,
"supports_web_search": true,
"deprecation_date": "2027-10-26",
"successor_model": "azure/us/gpt-5.6",
"input_cost_per_token_above_272k_tokens_batches": 5.5e-06,
"input_cost_per_token_batches": 2.75e-06,
"output_cost_per_token_above_272k_tokens_batches": 2.475e-05,
@ -10727,6 +10791,7 @@
},
"azure/us/gpt-5.5-2026-04-24": {
"deprecation_date": "2027-10-26",
"successor_model": "azure/us/gpt-5.6",
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_priority": 1.375e-06,
@ -10824,6 +10889,7 @@
"supports_vision": true,
"supports_web_search": true,
"deprecation_date": "2027-10-26",
"successor_model": "azure/eu/gpt-5.6",
"input_cost_per_token_above_272k_tokens_batches": 5.5e-06,
"input_cost_per_token_batches": 2.75e-06,
"output_cost_per_token_above_272k_tokens_batches": 2.475e-05,
@ -10832,6 +10898,7 @@
},
"azure/eu/gpt-5.5-2026-04-24": {
"deprecation_date": "2027-10-26",
"successor_model": "azure/eu/gpt-5.6",
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_priority": 1.375e-06,
@ -11168,6 +11235,7 @@
"cache_read_input_image_token_cost": 2.5e-06,
"cache_read_input_token_cost": 1.25e-06,
"deprecation_date": "2026-10-23",
"successor_model": "azure/gpt-image-1.5",
"input_cost_per_image_token": 1e-05,
"input_cost_per_token": 5e-06,
"litellm_provider": "azure",
@ -11308,6 +11376,7 @@
"azure/gpt-image-1.5": {
"cache_read_input_image_token_cost": 2e-06,
"deprecation_date": "2026-12-16",
"successor_model": "azure/gpt-image-2",
"cache_read_input_token_cost": 1.25e-06,
"input_cost_per_token": 5e-06,
"input_cost_per_image_token": 8e-06,
@ -11325,6 +11394,7 @@
"cache_read_input_image_token_cost": 2e-06,
"cache_read_input_token_cost": 1.25e-06,
"deprecation_date": "2026-12-16",
"successor_model": "azure/gpt-image-2",
"input_cost_per_token": 5e-06,
"input_cost_per_image_token": 8e-06,
"litellm_provider": "azure",
@ -11963,6 +12033,7 @@
},
"azure/us/gpt-4.1-2025-04-14": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/us/gpt-5.1",
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_priority": 9.63e-07,
"input_cost_per_token": 2.2e-06,
@ -12005,6 +12076,7 @@
},
"azure/us/gpt-4.1-mini-2025-04-14": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/us/gpt-5.4-mini",
"cache_read_input_token_cost": 1.1e-07,
"cache_read_input_token_cost_priority": 1.93e-07,
"input_cost_per_token": 4.4e-07,
@ -12047,6 +12119,7 @@
},
"azure/us/gpt-4.1-nano-2025-04-14": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/us/gpt-5.4-nano",
"cache_read_input_token_cost": 2.8e-08,
"input_cost_per_token": 1.1e-07,
"input_cost_per_token_batches": 5.5e-08,
@ -12254,6 +12327,7 @@
"cache_read_input_token_cost": 1.375e-07,
"cache_read_input_token_cost_priority": 2.75e-07,
"deprecation_date": "2027-02-09",
"successor_model": "azure/us/gpt-5.1",
"input_cost_per_token": 1.375e-06,
"input_cost_per_token_batches": 6.875e-07,
"input_cost_per_token_priority": 2.75e-06,
@ -12298,6 +12372,7 @@
"cache_read_input_token_cost": 2.75e-08,
"cache_read_input_token_cost_priority": 4.95e-08,
"deprecation_date": "2027-02-09",
"successor_model": "azure/us/gpt-5.4-mini",
"input_cost_per_token": 2.75e-07,
"input_cost_per_token_batches": 1.375e-07,
"input_cost_per_token_priority": 4.95e-07,
@ -12341,6 +12416,7 @@
"azure/us/gpt-5-nano-2025-08-07": {
"cache_read_input_token_cost": 5.5e-09,
"deprecation_date": "2027-02-09",
"successor_model": "azure/us/gpt-5.4-nano",
"input_cost_per_token": 5.5e-08,
"input_cost_per_token_batches": 2.75e-08,
"litellm_provider": "azure",
@ -12381,6 +12457,7 @@
},
"azure/us/gpt-5.1": {
"deprecation_date": "2027-05-15",
"successor_model": "azure/us/gpt-5.2",
"cache_read_input_token_cost": 1.375e-07,
"cache_read_input_token_cost_batches": 6.875e-08,
"cache_read_input_token_cost_priority": 2.75e-07,
@ -12428,6 +12505,7 @@
},
"azure/us/gpt-5.1-codex": {
"deprecation_date": "2027-05-15",
"successor_model": "azure/us/gpt-5.2-codex",
"cache_read_input_token_cost": 1.375e-07,
"input_cost_per_token": 1.375e-06,
"litellm_provider": "azure",
@ -12843,6 +12921,7 @@
},
"azure_ai/FW-GLM-5": {
"deprecation_date": "2027-07-01",
"successor_model": "azure_ai/FW-GLM-5.2",
"cache_read_input_token_cost": 2.2e-07,
"input_cost_per_token": 1.1e-06,
"litellm_provider": "azure_ai",
@ -12859,6 +12938,7 @@
},
"azure_ai/FW-GLM-5.1": {
"deprecation_date": "2027-07-01",
"successor_model": "azure_ai/FW-GLM-5.2",
"cache_read_input_token_cost": 2.86e-07,
"input_cost_per_token": 1.54e-06,
"litellm_provider": "azure_ai",
@ -13116,6 +13196,7 @@
"/v1/images/edits"
],
"deprecation_date": "2026-10-01",
"successor_model": "azure_ai/MAI-Image-2.6",
"max_input_tokens": 32000
},
"azure_ai/MAI-Image-2.5-Flash": {
@ -13131,6 +13212,7 @@
"/v1/images/edits"
],
"deprecation_date": "2026-10-01",
"successor_model": "azure_ai/MAI-Image-2.6-Flash",
"max_input_tokens": 32000
},
"azure_ai/MAI-Image-2.5-Pro": {
@ -13686,6 +13768,7 @@
},
"azure_ai/grok-4": {
"deprecation_date": "2027-01-31",
"successor_model": "azure_ai/grok-4.3",
"input_cost_per_token": 3e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 262000,
@ -15660,6 +15743,7 @@
"cache_creation_input_token_cost_above_1hr": 7.2e-06,
"cache_read_input_token_cost": 3.6e-07,
"deprecation_date": "2027-04-08",
"successor_model": "bedrock/us-gov-east-1/anthropic.claude-sonnet-5-5",
"input_cost_per_token": 3.6e-06,
"litellm_provider": "bedrock",
"supports_tool_search": true,
@ -15832,6 +15916,7 @@
"cache_creation_input_token_cost_above_1hr": 7.2e-06,
"cache_read_input_token_cost": 3.6e-07,
"deprecation_date": "2027-04-08",
"successor_model": "bedrock/us-gov-west-1/anthropic.claude-sonnet-5-5",
"input_cost_per_token": 3.6e-06,
"litellm_provider": "bedrock",
"supports_tool_search": true,
@ -21951,6 +22036,7 @@
"cache_creation_input_token_cost": 3.74997e-06,
"cache_read_input_token_cost": 3.0002e-07,
"deprecation_date": "2026-10-09",
"successor_model": "databricks/databricks-claude-sonnet-5",
"input_cost_per_token": 2.99999e-06,
"input_dbu_cost_per_token": 4.2857e-05,
"litellm_provider": "databricks",
@ -22136,6 +22222,7 @@
"cache_creation_input_token_cost": 3.0002e-07,
"cache_read_input_token_cost": 3.0002e-08,
"deprecation_date": "2026-10-02",
"successor_model": "databricks/databricks-gemini-3-5-flash",
"input_cost_per_token": 3.0001999999999996e-07,
"input_dbu_cost_per_token": 4.285999999999999e-06,
"litellm_provider": "databricks",
@ -25675,6 +25762,7 @@
"cache_read_input_token_cost": 1.1e-07,
"input_cost_per_token": 1.1e-06,
"deprecation_date": "2026-10-15",
"successor_model": "eu.anthropic.claude-haiku-5-5",
"litellm_provider": "bedrock_converse",
"supports_tool_search": true,
"max_input_tokens": 200000,
@ -25826,6 +25914,7 @@
"cache_creation_input_token_cost": 3.75e-06,
"cache_read_input_token_cost": 3e-07,
"deprecation_date": "2026-10-14",
"successor_model": "eu.anthropic.claude-sonnet-5",
"input_cost_per_token": 3e-06,
"input_cost_per_token_above_200k_tokens": 6e-06,
"output_cost_per_token_above_200k_tokens": 2.25e-05,
@ -25869,6 +25958,7 @@
"cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05,
"cache_read_input_token_cost_above_200k_tokens": 6.6e-07,
"deprecation_date": "2027-04-08",
"successor_model": "eu.anthropic.claude-sonnet-5-5",
"litellm_provider": "bedrock_converse",
"supports_tool_search": true,
"max_input_tokens": 200000,
@ -28493,6 +28583,7 @@
"cache_read_input_token_cost": 1.4e-07,
"cache_read_input_token_cost_priority": 1.75e-07,
"deprecation_date": "2026-09-25",
"successor_model": "fireworks_ai/accounts/fireworks/models/glm-5p3",
"input_cost_per_token": 1.4e-06,
"input_cost_per_token_priority": 1.75e-06,
"litellm_provider": "fireworks_ai",
@ -28868,6 +28959,7 @@
"cache_read_input_token_cost": 1.4e-07,
"cache_read_input_token_cost_priority": 1.75e-07,
"deprecation_date": "2026-09-25",
"successor_model": "fireworks_ai/glm-5p3",
"input_cost_per_token": 1.4e-06,
"input_cost_per_token_priority": 1.75e-06,
"litellm_provider": "fireworks_ai",
@ -29900,6 +29992,7 @@
"gemini-3.1-flash-lite": {
"cache_read_input_audio_token_cost": 5e-08,
"deprecation_date": "2027-05-07",
"successor_model": "gemini-3.5-flash-lite",
"cache_read_input_token_cost": 2.5e-08,
"cache_read_input_token_cost_batches": 1.25e-08,
"cache_read_input_token_cost_flex": 1.25e-08,
@ -30622,6 +30715,7 @@
"vertex_ai/gemini-3.5-flash": {
"prompt_cache_min_tokens": 4096,
"deprecation_date": "2027-05-19",
"successor_model": "vertex_ai/gemini-3.8-flash",
"cache_read_input_token_cost": 1.5e-07,
"cache_read_input_token_cost_batches": 7.5e-08,
"input_cost_per_token": 1.5e-06,
@ -31210,6 +31304,7 @@
},
"gemini-embedding-001": {
"deprecation_date": "2028-05-20",
"successor_model": "gemini-embedding-2",
"input_cost_per_token": 1.5e-07,
"input_cost_per_token_batches": 1.2e-07,
"litellm_provider": "vertex_ai-embedding-models",
@ -31597,6 +31692,7 @@
"cache_read_input_token_cost_flex": 3e-08,
"cache_read_input_token_cost_priority": 5.4e-08,
"deprecation_date": "2026-12-01",
"successor_model": "gemini/gemini-3-flash-preview",
"input_cost_per_audio_token": 1e-06,
"input_cost_per_audio_token_flex": 5e-07,
"input_cost_per_token": 3e-07,
@ -32184,6 +32280,7 @@
"supports_url_context": true,
"cache_read_input_token_cost_above_200k_tokens_batches": 2.5e-07,
"deprecation_date": "2026-12-01",
"successor_model": "gemini/gemini-3.1-pro-preview",
"input_cost_per_token_above_200k_tokens_batches": 1.25e-06,
"output_cost_per_token_above_200k_tokens_batches": 7.5e-06
},
@ -32917,6 +33014,7 @@
"gemini-3.5-flash": {
"prompt_cache_min_tokens": 4096,
"deprecation_date": "2027-05-19",
"successor_model": "gemini-3.8-flash",
"cache_read_input_token_cost": 1.5e-07,
"cache_read_input_token_cost_batches": 7.5e-08,
"input_cost_per_audio_token": 1.5e-06,
@ -34917,6 +35015,7 @@
"cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05,
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
"deprecation_date": "2027-04-08",
"successor_model": "global.anthropic.claude-sonnet-5-5",
"litellm_provider": "bedrock_converse",
"supports_tool_search": true,
"max_input_tokens": 200000,
@ -34952,6 +35051,7 @@
"cache_creation_input_token_cost": 3.75e-06,
"cache_read_input_token_cost": 3e-07,
"deprecation_date": "2026-10-14",
"successor_model": "global.anthropic.claude-sonnet-5",
"input_cost_per_token": 3e-06,
"input_cost_per_token_above_200k_tokens": 6e-06,
"output_cost_per_token_above_200k_tokens": 2.25e-05,
@ -39050,6 +39150,7 @@
"gpt-5-chat": {
"cache_read_input_token_cost": 1.25e-07,
"deprecation_date": "2026-07-23",
"successor_model": "gpt-5.2-chat-latest",
"input_cost_per_token": 1.25e-06,
"litellm_provider": "openai",
"max_input_tokens": 128000,
@ -40573,6 +40674,7 @@
"cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05,
"cache_read_input_token_cost_above_200k_tokens": 6.6e-07,
"deprecation_date": "2027-04-08",
"successor_model": "jp.anthropic.claude-sonnet-5-5",
"litellm_provider": "bedrock_converse",
"supports_tool_search": true,
"max_input_tokens": 200000,
@ -49995,6 +50097,7 @@
"cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05,
"cache_read_input_token_cost_above_200k_tokens": 6.6e-07,
"deprecation_date": "2027-04-08",
"successor_model": "us.anthropic.claude-sonnet-5-5",
"litellm_provider": "bedrock_converse",
"supports_tool_search": true,
"max_input_tokens": 200000,
@ -50037,6 +50140,7 @@
"cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.44e-05,
"cache_read_input_token_cost_above_200k_tokens": 7.2e-07,
"deprecation_date": "2027-04-08",
"successor_model": "us-gov.anthropic.claude-sonnet-5-5",
"litellm_provider": "bedrock_converse",
"supports_tool_search": true,
"max_input_tokens": 200000,
@ -50545,6 +50649,7 @@
"cache_creation_input_token_cost": 3.75e-06,
"cache_read_input_token_cost": 3e-07,
"deprecation_date": "2026-10-14",
"successor_model": "us.anthropic.claude-sonnet-5",
"input_cost_per_token": 3e-06,
"input_cost_per_token_above_200k_tokens": 6e-06,
"output_cost_per_token_above_200k_tokens": 2.25e-05,
@ -52017,6 +52122,7 @@
},
"vertex_ai/claude-haiku-4-5": {
"deprecation_date": "2026-10-15",
"successor_model": "vertex_ai/claude-haiku-5-5",
"cache_creation_input_token_cost": 1.25e-06,
"cache_creation_input_token_cost_above_1hr": 2e-06,
"cache_creation_input_token_cost_batches": 6.25e-07,
@ -52188,6 +52294,7 @@
},
"vertex_ai/claude-opus-4-5": {
"deprecation_date": "2026-11-24",
"successor_model": "vertex_ai/claude-opus-5-5",
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_1hr": 1e-05,
"cache_creation_input_token_cost_batches": 3.125e-06,
@ -52797,6 +52904,7 @@
},
"vertex_ai/claude-sonnet-4-5": {
"deprecation_date": "2026-09-29",
"successor_model": "vertex_ai/claude-sonnet-5-5",
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_1hr": 6e-06,
"cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05,
@ -53362,6 +53470,7 @@
"vertex_ai/gemini-3.1-flash-lite": {
"cache_read_input_audio_token_cost": 5e-08,
"deprecation_date": "2027-05-07",
"successor_model": "vertex_ai/gemini-3.5-flash-lite",
"cache_read_input_token_cost": 2.5e-08,
"cache_read_input_token_cost_batches": 1.25e-08,
"cache_read_input_token_cost_flex": 1.25e-08,
@ -53839,6 +53948,7 @@
"vertex_ai/zai-org/glm-4.7-maas": {
"cache_read_input_token_cost": 6e-08,
"deprecation_date": "2026-10-21",
"successor_model": "vertex_ai/zai-org/glm-5.2-maas",
"input_cost_per_token": 6e-07,
"litellm_provider": "vertex_ai-zai_models",
"max_input_tokens": 200000,
@ -53857,6 +53967,7 @@
"vertex_ai/zai-org/glm-5-maas": {
"cache_read_input_token_cost": 1e-07,
"deprecation_date": "2026-10-21",
"successor_model": "vertex_ai/zai-org/glm-5.2-maas",
"input_cost_per_token": 1e-06,
"litellm_provider": "vertex_ai-zai_models",
"max_input_tokens": 200000,
@ -55205,6 +55316,7 @@
},
"zai.glm-4.7": {
"deprecation_date": "2027-03-30",
"successor_model": "zai.glm-5",
"input_cost_per_token": 6e-07,
"input_cost_per_token_batches": 3e-07,
"input_cost_per_token_flex": 3e-07,
@ -64804,6 +64916,7 @@
"fireworks_ai/glm-5p2-fast": {
"cache_read_input_token_cost": 2.1e-07,
"deprecation_date": "2026-09-25",
"successor_model": "fireworks_ai/glm-5p3-fast",
"input_cost_per_token": 2.1e-06,
"litellm_provider": "fireworks_ai",
"max_input_tokens": 1048576,
@ -65073,6 +65186,7 @@
"fireworks_ai/accounts/fireworks/routers/glm-5p2-fast": {
"cache_read_input_token_cost": 2.1e-07,
"deprecation_date": "2026-09-25",
"successor_model": "fireworks_ai/accounts/fireworks/routers/glm-5p3-fast",
"input_cost_per_token": 2.1e-06,
"litellm_provider": "fireworks_ai",
"max_input_tokens": 1048576,
@ -67527,6 +67641,7 @@
},
"xai/grok-voice-transcribe-1.0": {
"deprecation_date": "2026-10-02",
"successor_model": "xai/grok-voice-transcribe-2.0",
"input_cost_per_second": 2.778e-05,
"litellm_provider": "xai",
"metadata": {
@ -71038,6 +71153,7 @@
},
"azure/eu/gpt-4.1": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/eu/gpt-5.1",
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_priority": 9.63e-07,
"input_cost_per_token": 2.2e-06,
@ -71057,6 +71173,7 @@
},
"azure/eu/gpt-4.1-mini": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/eu/gpt-5.4-mini",
"cache_read_input_token_cost": 1.1e-07,
"cache_read_input_token_cost_priority": 1.93e-07,
"input_cost_per_token": 4.4e-07,
@ -71076,6 +71193,7 @@
},
"azure/eu/gpt-4.1-nano": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/eu/gpt-5.4-nano",
"cache_read_input_token_cost": 2.8e-08,
"input_cost_per_token": 1.1e-07,
"input_cost_per_token_batches": 5.5e-08,
@ -71100,6 +71218,7 @@
},
"azure/eu/gpt-5": {
"deprecation_date": "2027-02-09",
"successor_model": "azure/eu/gpt-5.1",
"cache_read_input_token_cost": 1.375e-07,
"cache_read_input_token_cost_batches": 6.875e-08,
"cache_read_input_token_cost_priority": 2.75e-07,
@ -71120,6 +71239,7 @@
},
"azure/eu/gpt-5-codex": {
"deprecation_date": "2027-03-17",
"successor_model": "azure/eu/gpt-5.1-codex",
"cache_read_input_token_cost": 1.38e-07,
"input_cost_per_token": 1.375e-06,
"litellm_provider": "azure",
@ -71129,6 +71249,7 @@
},
"azure/eu/gpt-5-mini": {
"deprecation_date": "2027-02-09",
"successor_model": "azure/eu/gpt-5.4-mini",
"cache_read_input_token_cost": 2.75e-08,
"cache_read_input_token_cost_batches": 1.375e-08,
"cache_read_input_token_cost_priority": 4.95e-08,
@ -71149,6 +71270,7 @@
},
"azure/eu/gpt-5-nano": {
"deprecation_date": "2027-02-09",
"successor_model": "azure/eu/gpt-5.4-nano",
"cache_read_input_token_cost": 5.5e-09,
"cache_read_input_token_cost_batches": 2.75e-09,
"input_cost_per_token": 5.5e-08,
@ -71166,6 +71288,7 @@
},
"azure/eu/gpt-5-pro": {
"deprecation_date": "2027-04-07",
"successor_model": "azure/eu/gpt-5.2-pro",
"input_cost_per_token": 1.65e-05,
"input_cost_per_token_batches": 8.25e-06,
"litellm_provider": "azure",
@ -71190,6 +71313,7 @@
},
"azure/eu/gpt-5.2": {
"deprecation_date": "2027-06-08",
"successor_model": "azure/eu/gpt-5.4",
"cache_read_input_token_cost": 1.925e-07,
"cache_read_input_token_cost_batches": 9.625e-08,
"cache_read_input_token_cost_priority": 3.85e-07,
@ -71210,6 +71334,7 @@
},
"azure/eu/gpt-5.2-codex": {
"deprecation_date": "2027-07-13",
"successor_model": "azure/eu/gpt-5.3-codex",
"cache_read_input_token_cost": 1.925e-07,
"input_cost_per_token": 1.925e-06,
"litellm_provider": "azure",
@ -71625,6 +71750,7 @@
},
"azure/us/gpt-4.1": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/us/gpt-5.1",
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_priority": 9.63e-07,
"input_cost_per_token": 2.2e-06,
@ -71644,6 +71770,7 @@
},
"azure/us/gpt-4.1-mini": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/us/gpt-5.4-mini",
"cache_read_input_token_cost": 1.1e-07,
"cache_read_input_token_cost_priority": 1.93e-07,
"input_cost_per_token": 4.4e-07,
@ -71663,6 +71790,7 @@
},
"azure/us/gpt-4.1-nano": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/us/gpt-5.4-nano",
"cache_read_input_token_cost": 2.8e-08,
"input_cost_per_token": 1.1e-07,
"input_cost_per_token_batches": 5.5e-08,
@ -71687,6 +71815,7 @@
},
"azure/us/gpt-5": {
"deprecation_date": "2027-02-09",
"successor_model": "azure/us/gpt-5.1",
"cache_read_input_token_cost": 1.375e-07,
"cache_read_input_token_cost_batches": 6.875e-08,
"cache_read_input_token_cost_priority": 2.75e-07,
@ -71707,6 +71836,7 @@
},
"azure/us/gpt-5-codex": {
"deprecation_date": "2027-03-17",
"successor_model": "azure/us/gpt-5.1-codex",
"cache_read_input_token_cost": 1.38e-07,
"input_cost_per_token": 1.375e-06,
"litellm_provider": "azure",
@ -71716,6 +71846,7 @@
},
"azure/us/gpt-5-mini": {
"deprecation_date": "2027-02-09",
"successor_model": "azure/us/gpt-5.4-mini",
"cache_read_input_token_cost": 2.75e-08,
"cache_read_input_token_cost_batches": 1.375e-08,
"cache_read_input_token_cost_priority": 4.95e-08,
@ -71736,6 +71867,7 @@
},
"azure/us/gpt-5-nano": {
"deprecation_date": "2027-02-09",
"successor_model": "azure/us/gpt-5.4-nano",
"cache_read_input_token_cost": 5.5e-09,
"cache_read_input_token_cost_batches": 2.75e-09,
"input_cost_per_token": 5.5e-08,
@ -71753,6 +71885,7 @@
},
"azure/us/gpt-5-pro": {
"deprecation_date": "2027-04-07",
"successor_model": "azure/us/gpt-5.2-pro",
"input_cost_per_token": 1.65e-05,
"input_cost_per_token_batches": 8.25e-06,
"litellm_provider": "azure",
@ -71777,6 +71910,7 @@
},
"azure/us/gpt-5.2": {
"deprecation_date": "2027-06-08",
"successor_model": "azure/us/gpt-5.4",
"cache_read_input_token_cost": 1.925e-07,
"cache_read_input_token_cost_batches": 9.625e-08,
"cache_read_input_token_cost_priority": 3.85e-07,
@ -71797,6 +71931,7 @@
},
"azure/us/gpt-5.2-codex": {
"deprecation_date": "2027-07-13",
"successor_model": "azure/us/gpt-5.3-codex",
"cache_read_input_token_cost": 1.925e-07,
"input_cost_per_token": 1.925e-06,
"litellm_provider": "azure",
@ -79247,6 +79382,7 @@
"cache_creation_input_token_cost_batches": 1.875e-06,
"cache_read_input_token_cost_batches": 1.5e-07,
"deprecation_date": "2026-11-30",
"successor_model": "bedrock/claude_platform/claude-sonnet-5-5",
"input_cost_per_token_batches": 1.5e-06,
"litellm_provider": "bedrock",
"max_input_tokens": 200000,

136
model_prices_and_context_window.json
View file

@ -3409,6 +3409,7 @@
"cache_creation_input_token_cost": 3.75e-06,
"cache_read_input_token_cost": 3e-07,
"deprecation_date": "2026-10-14",
"successor_model": "anthropic.claude-sonnet-5",
"input_cost_per_token": 3e-06,
"input_cost_per_token_above_200k_tokens": 6e-06,
"output_cost_per_token_above_200k_tokens": 2.25e-05,
@ -3452,6 +3453,7 @@
"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
"deprecation_date": "2027-04-08",
"successor_model": "anthropic.claude-sonnet-5-5",
"litellm_provider": "bedrock_converse",
"supports_tool_search": true,
"max_input_tokens": 200000,
@ -3686,6 +3688,7 @@
"cache_creation_input_token_cost": 3.75e-06,
"cache_read_input_token_cost": 3e-07,
"deprecation_date": "2026-10-14",
"successor_model": "apac.anthropic.claude-sonnet-5",
"input_cost_per_token": 3e-06,
"input_cost_per_token_above_200k_tokens": 6e-06,
"output_cost_per_token_above_200k_tokens": 2.25e-05,
@ -3741,6 +3744,7 @@
"cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05,
"cache_read_input_token_cost_above_200k_tokens": 6.6e-07,
"deprecation_date": "2027-04-08",
"successor_model": "au.anthropic.claude-sonnet-5-5",
"litellm_provider": "bedrock_converse",
"supports_tool_search": true,
"max_input_tokens": 200000,
@ -3824,6 +3828,7 @@
},
"azure_ai/claude-haiku-4-5": {
"deprecation_date": "2026-11-15",
"successor_model": "azure_ai/claude-haiku-5-5",
"cache_creation_input_token_cost": 1.25e-06,
"cache_creation_input_token_cost_above_1hr": 2e-06,
"cache_read_input_token_cost": 1e-07,
@ -3847,6 +3852,7 @@
},
"azure_ai/claude-opus-4-5": {
"deprecation_date": "2026-11-24",
"successor_model": "azure_ai/claude-opus-5-5",
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_1hr": 1e-05,
"cache_read_input_token_cost": 5e-07,
@ -4726,6 +4732,7 @@
},
"azure_ai/gpt-5.4": {
"deprecation_date": "2027-09-02",
"successor_model": "azure_ai/gpt-5.5",
"cache_read_input_token_cost": 2.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 5e-07,
"cache_read_input_token_cost_priority": 5e-07,
@ -4773,6 +4780,7 @@
},
"azure_ai/gpt-5.4-2026-03-05": {
"deprecation_date": "2027-09-02",
"successor_model": "azure_ai/gpt-5.5",
"cache_read_input_token_cost": 2.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 5e-07,
"cache_read_input_token_cost_priority": 5e-07,
@ -5270,6 +5278,7 @@
"cache_read_input_token_cost": 1.375e-07,
"cache_read_input_token_cost_priority": 2.75e-07,
"deprecation_date": "2027-02-09",
"successor_model": "azure/eu/gpt-5.1",
"input_cost_per_token": 1.375e-06,
"input_cost_per_token_batches": 6.875e-07,
"input_cost_per_token_priority": 2.75e-06,
@ -5314,6 +5323,7 @@
"cache_read_input_token_cost": 2.75e-08,
"cache_read_input_token_cost_priority": 4.95e-08,
"deprecation_date": "2027-02-09",
"successor_model": "azure/eu/gpt-5.4-mini",
"input_cost_per_token": 2.75e-07,
"input_cost_per_token_batches": 1.375e-07,
"input_cost_per_token_priority": 4.95e-07,
@ -5356,6 +5366,7 @@
},
"azure/eu/gpt-5.1": {
"deprecation_date": "2027-05-15",
"successor_model": "azure/eu/gpt-5.2",
"cache_read_input_token_cost": 1.375e-07,
"cache_read_input_token_cost_batches": 6.875e-08,
"cache_read_input_token_cost_priority": 2.75e-07,
@ -5403,6 +5414,7 @@
},
"azure/eu/gpt-5.1-codex": {
"deprecation_date": "2027-05-15",
"successor_model": "azure/eu/gpt-5.2-codex",
"cache_read_input_token_cost": 1.375e-07,
"input_cost_per_token": 1.375e-06,
"litellm_provider": "azure",
@ -5466,6 +5478,7 @@
"azure/eu/gpt-5-nano-2025-08-07": {
"cache_read_input_token_cost": 5.5e-09,
"deprecation_date": "2027-02-09",
"successor_model": "azure/eu/gpt-5.4-nano",
"input_cost_per_token": 5.5e-08,
"input_cost_per_token_batches": 2.75e-08,
"litellm_provider": "azure",
@ -5872,6 +5885,7 @@
},
"azure/gpt-4": {
"deprecation_date": "2025-06-06",
"successor_model": "azure/gpt-4.1",
"input_cost_per_token": 3e-05,
"litellm_provider": "azure",
"max_input_tokens": 8192,
@ -5895,6 +5909,7 @@
},
"azure/gpt-4-0613": {
"deprecation_date": "2025-06-06",
"successor_model": "azure/gpt-4.1",
"input_cost_per_token": 3e-05,
"litellm_provider": "azure",
"max_input_tokens": 8192,
@ -5976,6 +5991,7 @@
},
"azure/gpt-4.1": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/gpt-5.1",
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_priority": 8.75e-07,
"input_cost_per_token": 2e-06,
@ -6018,6 +6034,7 @@
},
"azure/gpt-4.1-2025-04-14": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/gpt-5.1",
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_priority": 8.75e-07,
"input_cost_per_token": 2e-06,
@ -6060,6 +6077,7 @@
},
"azure/gpt-4.1-mini": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/gpt-5.4-mini",
"cache_read_input_token_cost": 1e-07,
"cache_read_input_token_cost_priority": 1.75e-07,
"input_cost_per_token": 4e-07,
@ -6102,6 +6120,7 @@
},
"azure/gpt-4.1-mini-2025-04-14": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/gpt-5.4-mini",
"cache_read_input_token_cost": 1e-07,
"cache_read_input_token_cost_priority": 1.75e-07,
"input_cost_per_token": 4e-07,
@ -6144,6 +6163,7 @@
},
"azure/gpt-4.1-nano": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/gpt-5.4-nano",
"cache_read_input_token_cost": 2.5e-08,
"input_cost_per_token": 1e-07,
"input_cost_per_token_batches": 5e-08,
@ -6177,6 +6197,7 @@
},
"azure/gpt-4.1-nano-2025-04-14": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/gpt-5.4-nano",
"cache_read_input_token_cost": 2.5e-08,
"input_cost_per_token": 1e-07,
"input_cost_per_token_batches": 5e-08,
@ -6711,6 +6732,7 @@
"cache_read_input_audio_token_cost": 4e-07,
"cache_read_input_token_cost": 4e-07,
"deprecation_date": "2027-08-24",
"successor_model": "azure/gpt-realtime-2.1-2026-07-07",
"input_cost_per_audio_token": 3.2e-05,
"input_cost_per_image_token": 5e-06,
"input_cost_per_token": 4e-06,
@ -6748,6 +6770,7 @@
"cache_read_input_audio_token_cost": 4e-07,
"cache_read_input_token_cost": 4e-07,
"deprecation_date": "2027-08-24",
"successor_model": "azure/gpt-realtime-2.1-2026-07-07",
"input_cost_per_audio_token": 3.2e-05,
"input_cost_per_image_token": 5e-06,
"input_cost_per_token": 4e-06,
@ -7065,6 +7088,7 @@
"cache_read_input_token_cost": 1.25e-07,
"cache_read_input_token_cost_priority": 2.5e-07,
"deprecation_date": "2027-05-15",
"successor_model": "azure/gpt-5.2",
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_priority": 2.5e-06,
"litellm_provider": "azure",
@ -7112,6 +7136,7 @@
"cache_read_input_token_cost": 1.25e-07,
"cache_read_input_token_cost_priority": 2.5e-07,
"deprecation_date": "2027-05-15",
"successor_model": "azure/gpt-5.2-codex",
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_priority": 2.5e-06,
"litellm_provider": "azure",
@ -7178,6 +7203,7 @@
},
"azure/gpt-5": {
"deprecation_date": "2027-02-09",
"successor_model": "azure/gpt-5.1",
"cache_read_input_token_cost": 1.25e-07,
"cache_read_input_token_cost_batches": 6.25e-08,
"cache_read_input_token_cost_priority": 2.5e-07,
@ -7224,6 +7250,7 @@
"cache_read_input_token_cost": 1.25e-07,
"cache_read_input_token_cost_priority": 2.5e-07,
"deprecation_date": "2027-02-09",
"successor_model": "azure/gpt-5.1",
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_batches": 6.25e-07,
"input_cost_per_token_priority": 2.5e-06,
@ -7267,6 +7294,7 @@
"azure/gpt-5-codex": {
"cache_read_input_token_cost": 1.25e-07,
"deprecation_date": "2027-03-17",
"successor_model": "azure/gpt-5.1-codex",
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
@ -7297,6 +7325,7 @@
},
"azure/gpt-5-mini": {
"deprecation_date": "2027-02-09",
"successor_model": "azure/gpt-5.4-mini",
"cache_read_input_token_cost": 2.5e-08,
"cache_read_input_token_cost_batches": 1.25e-08,
"cache_read_input_token_cost_priority": 4.5e-08,
@ -7343,6 +7372,7 @@
"cache_read_input_token_cost": 2.5e-08,
"cache_read_input_token_cost_priority": 4.5e-08,
"deprecation_date": "2027-02-09",
"successor_model": "azure/gpt-5.4-mini",
"input_cost_per_token": 2.5e-07,
"input_cost_per_token_batches": 1.25e-07,
"input_cost_per_token_priority": 4.5e-07,
@ -7385,6 +7415,7 @@
},
"azure/gpt-5-nano": {
"deprecation_date": "2027-02-09",
"successor_model": "azure/gpt-5.4-nano",
"cache_read_input_token_cost": 5e-09,
"cache_read_input_token_cost_batches": 2.5e-09,
"input_cost_per_token": 5e-08,
@ -7427,6 +7458,7 @@
"azure/gpt-5-nano-2025-08-07": {
"cache_read_input_token_cost": 5e-09,
"deprecation_date": "2027-02-09",
"successor_model": "azure/gpt-5.4-nano",
"input_cost_per_token": 5e-08,
"input_cost_per_token_batches": 2.5e-08,
"litellm_provider": "azure",
@ -7467,6 +7499,7 @@
},
"azure/gpt-5-pro": {
"deprecation_date": "2027-04-07",
"successor_model": "azure/gpt-5.2-pro",
"input_cost_per_token": 1.5e-05,
"input_cost_per_token_batches": 7.5e-06,
"litellm_provider": "azure",
@ -7503,6 +7536,7 @@
},
"azure/gpt-5.1": {
"deprecation_date": "2027-05-15",
"successor_model": "azure/gpt-5.2",
"cache_read_input_token_cost": 1.25e-07,
"cache_read_input_token_cost_batches": 6.25e-08,
"cache_read_input_token_cost_priority": 2.5e-07,
@ -7799,6 +7833,7 @@
},
"azure/gpt-5.1-codex": {
"deprecation_date": "2027-05-15",
"successor_model": "azure/gpt-5.2-codex",
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
@ -7892,6 +7927,7 @@
},
"azure/gpt-5.2": {
"deprecation_date": "2027-06-08",
"successor_model": "azure/gpt-5.4",
"cache_read_input_token_cost": 1.75e-07,
"cache_read_input_token_cost_batches": 8.75e-08,
"cache_read_input_token_cost_priority": 3.5e-07,
@ -7939,6 +7975,7 @@
"cache_read_input_token_cost": 1.75e-07,
"cache_read_input_token_cost_priority": 3.5e-07,
"deprecation_date": "2027-06-08",
"successor_model": "azure/gpt-5.4",
"input_cost_per_token": 1.75e-06,
"input_cost_per_token_batches": 8.75e-07,
"input_cost_per_token_priority": 3.5e-06,
@ -7983,6 +8020,7 @@
"azure/gpt-5.2-codex": {
"cache_read_input_token_cost": 1.75e-07,
"deprecation_date": "2027-07-13",
"successor_model": "azure/gpt-5.3-codex",
"input_cost_per_token": 1.75e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
@ -8128,6 +8166,7 @@
},
"azure/gpt-5.4": {
"deprecation_date": "2027-09-02",
"successor_model": "azure/gpt-5.5",
"cache_read_input_token_cost": 2.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 5e-07,
"cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-07,
@ -8185,6 +8224,7 @@
},
"azure/us/gpt-5.4": {
"deprecation_date": "2027-09-02",
"successor_model": "azure/us/gpt-5.5",
"cache_read_input_token_cost": 2.75e-07,
"cache_read_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07,
@ -8234,6 +8274,7 @@
},
"azure/eu/gpt-5.4": {
"deprecation_date": "2027-09-02",
"successor_model": "azure/eu/gpt-5.5",
"cache_read_input_token_cost": 2.75e-07,
"cache_read_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07,
@ -8288,6 +8329,7 @@
"cache_read_input_token_cost_priority": 5e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 1e-06,
"deprecation_date": "2027-09-02",
"successor_model": "azure/gpt-5.5",
"input_cost_per_token": 2.5e-06,
"input_cost_per_token_above_272k_tokens": 5e-06,
"input_cost_per_token_priority": 5e-06,
@ -8343,6 +8385,7 @@
"cache_read_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_read_input_token_cost_priority": 5.5e-07,
"deprecation_date": "2027-09-02",
"successor_model": "azure/us/gpt-5.5",
"input_cost_per_token": 2.75e-06,
"input_cost_per_token_priority": 5.5e-06,
"output_cost_per_token": 1.65e-05,
@ -8392,6 +8435,7 @@
"cache_read_input_token_cost_above_272k_tokens": 5.5e-07,
"cache_read_input_token_cost_priority": 5.5e-07,
"deprecation_date": "2027-09-02",
"successor_model": "azure/eu/gpt-5.5",
"input_cost_per_token": 2.75e-06,
"input_cost_per_token_priority": 5.5e-06,
"output_cost_per_token": 1.65e-05,
@ -8438,6 +8482,7 @@
},
"azure/gpt-5.4-pro": {
"deprecation_date": "2027-09-07",
"successor_model": "azure/gpt-5.5-pro",
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
"input_cost_per_token": 3e-05,
@ -8489,6 +8534,7 @@
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
"deprecation_date": "2027-09-07",
"successor_model": "azure/gpt-5.5-pro",
"input_cost_per_token": 3e-05,
"input_cost_per_token_above_272k_tokens": 6e-05,
"input_cost_per_token_above_272k_tokens_flex": 3e-05,
@ -8601,6 +8647,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06,
"cache_read_input_token_cost_flex": 2e-07,
"deprecation_date": "2028-01-11",
"successor_model": "azure/gpt-6-sol",
"input_cost_per_token": 4e-06,
"input_cost_per_token_above_272k_tokens": 8e-06,
"input_cost_per_token_above_272k_tokens_flex": 4e-06,
@ -8664,6 +8711,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06,
"cache_read_input_token_cost_flex": 2e-07,
"deprecation_date": "2028-01-11",
"successor_model": "azure/gpt-6-sol",
"input_cost_per_token": 4e-06,
"input_cost_per_token_above_272k_tokens": 8e-06,
"input_cost_per_token_above_272k_tokens_flex": 4e-06,
@ -8727,6 +8775,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
"cache_read_input_token_cost_flex": 1e-07,
"deprecation_date": "2028-01-11",
"successor_model": "azure/gpt-6.1-terra",
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"input_cost_per_token_above_272k_tokens_flex": 2e-06,
@ -8790,6 +8839,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
"cache_read_input_token_cost_flex": 1e-07,
"deprecation_date": "2028-01-11",
"successor_model": "azure/gpt-6.1-terra",
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"input_cost_per_token_above_272k_tokens_flex": 2e-06,
@ -8853,6 +8903,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-08,
"cache_read_input_token_cost_flex": 1e-08,
"deprecation_date": "2028-01-11",
"successor_model": "azure/gpt-6-luna",
"input_cost_per_token": 2e-07,
"input_cost_per_token_above_272k_tokens": 4e-07,
"input_cost_per_token_above_272k_tokens_flex": 2e-07,
@ -8916,6 +8967,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-08,
"cache_read_input_token_cost_flex": 1e-08,
"deprecation_date": "2028-01-11",
"successor_model": "azure/gpt-6-luna",
"input_cost_per_token": 2e-07,
"input_cost_per_token_above_272k_tokens": 4e-07,
"input_cost_per_token_above_272k_tokens_flex": 2e-07,
@ -9832,6 +9884,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06,
"cache_read_input_token_cost_priority": 8.8e-07,
"deprecation_date": "2028-01-11",
"successor_model": "azure/us/gpt-6-sol",
"input_cost_per_token": 4.4e-06,
"input_cost_per_token_above_272k_tokens": 8.8e-06,
"input_cost_per_token_above_272k_tokens_priority": 1.76e-05,
@ -9887,6 +9940,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07,
"cache_read_input_token_cost_priority": 4.4e-07,
"deprecation_date": "2028-01-11",
"successor_model": "azure/us/gpt-6.1-terra",
"input_cost_per_token": 2.2e-06,
"input_cost_per_token_above_272k_tokens": 4.4e-06,
"input_cost_per_token_above_272k_tokens_priority": 8.8e-06,
@ -9942,6 +9996,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-08,
"cache_read_input_token_cost_priority": 4.4e-08,
"deprecation_date": "2028-01-11",
"successor_model": "azure/us/gpt-6-luna",
"input_cost_per_token": 2.2e-07,
"input_cost_per_token_above_272k_tokens": 4.4e-07,
"input_cost_per_token_above_272k_tokens_priority": 8.8e-07,
@ -10234,6 +10289,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06,
"cache_read_input_token_cost_priority": 8.8e-07,
"deprecation_date": "2028-01-11",
"successor_model": "azure/eu/gpt-6-sol",
"input_cost_per_token": 4.4e-06,
"input_cost_per_token_above_272k_tokens": 8.8e-06,
"input_cost_per_token_above_272k_tokens_priority": 1.76e-05,
@ -10289,6 +10345,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07,
"cache_read_input_token_cost_priority": 4.4e-07,
"deprecation_date": "2028-01-11",
"successor_model": "azure/eu/gpt-6.1-terra",
"input_cost_per_token": 2.2e-06,
"input_cost_per_token_above_272k_tokens": 4.4e-06,
"input_cost_per_token_above_272k_tokens_priority": 8.8e-06,
@ -10344,6 +10401,7 @@
"cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-08,
"cache_read_input_token_cost_priority": 4.4e-08,
"deprecation_date": "2028-01-11",
"successor_model": "azure/eu/gpt-6-luna",
"input_cost_per_token": 2.2e-07,
"input_cost_per_token_above_272k_tokens": 4.4e-07,
"input_cost_per_token_above_272k_tokens_priority": 8.8e-07,
@ -10391,6 +10449,7 @@
},
"azure/gpt-5.5": {
"deprecation_date": "2027-10-26",
"successor_model": "azure/gpt-5.6",
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_above_272k_tokens_batches": 5e-07,
@ -10451,6 +10510,7 @@
},
"azure/us/gpt-5.5": {
"deprecation_date": "2027-10-26",
"successor_model": "azure/us/gpt-5.6",
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07,
@ -10505,6 +10565,7 @@
},
"azure/eu/gpt-5.5": {
"deprecation_date": "2027-10-26",
"successor_model": "azure/eu/gpt-5.6",
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07,
@ -10606,6 +10667,7 @@
"supports_vision": true,
"supports_web_search": true,
"deprecation_date": "2027-10-26",
"successor_model": "azure/gpt-5.6",
"input_cost_per_token_above_272k_tokens_batches": 5e-06,
"input_cost_per_token_above_272k_tokens_flex": 5e-06,
"input_cost_per_token_batches": 2.5e-06,
@ -10616,6 +10678,7 @@
},
"azure/gpt-5.5-2026-04-24": {
"deprecation_date": "2027-10-26",
"successor_model": "azure/gpt-5.6",
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_priority": 1.25e-06,
@ -10719,6 +10782,7 @@
"supports_vision": true,
"supports_web_search": true,
"deprecation_date": "2027-10-26",
"successor_model": "azure/us/gpt-5.6",
"input_cost_per_token_above_272k_tokens_batches": 5.5e-06,
"input_cost_per_token_batches": 2.75e-06,
"output_cost_per_token_above_272k_tokens_batches": 2.475e-05,
@ -10727,6 +10791,7 @@
},
"azure/us/gpt-5.5-2026-04-24": {
"deprecation_date": "2027-10-26",
"successor_model": "azure/us/gpt-5.6",
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_priority": 1.375e-06,
@ -10824,6 +10889,7 @@
"supports_vision": true,
"supports_web_search": true,
"deprecation_date": "2027-10-26",
"successor_model": "azure/eu/gpt-5.6",
"input_cost_per_token_above_272k_tokens_batches": 5.5e-06,
"input_cost_per_token_batches": 2.75e-06,
"output_cost_per_token_above_272k_tokens_batches": 2.475e-05,
@ -10832,6 +10898,7 @@
},
"azure/eu/gpt-5.5-2026-04-24": {
"deprecation_date": "2027-10-26",
"successor_model": "azure/eu/gpt-5.6",
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
"cache_read_input_token_cost_priority": 1.375e-06,
@ -11168,6 +11235,7 @@
"cache_read_input_image_token_cost": 2.5e-06,
"cache_read_input_token_cost": 1.25e-06,
"deprecation_date": "2026-10-23",
"successor_model": "azure/gpt-image-1.5",
"input_cost_per_image_token": 1e-05,
"input_cost_per_token": 5e-06,
"litellm_provider": "azure",
@ -11308,6 +11376,7 @@
"azure/gpt-image-1.5": {
"cache_read_input_image_token_cost": 2e-06,
"deprecation_date": "2026-12-16",
"successor_model": "azure/gpt-image-2",
"cache_read_input_token_cost": 1.25e-06,
"input_cost_per_token": 5e-06,
"input_cost_per_image_token": 8e-06,
@ -11325,6 +11394,7 @@
"cache_read_input_image_token_cost": 2e-06,
"cache_read_input_token_cost": 1.25e-06,
"deprecation_date": "2026-12-16",
"successor_model": "azure/gpt-image-2",
"input_cost_per_token": 5e-06,
"input_cost_per_image_token": 8e-06,
"litellm_provider": "azure",
@ -11963,6 +12033,7 @@
},
"azure/us/gpt-4.1-2025-04-14": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/us/gpt-5.1",
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_priority": 9.63e-07,
"input_cost_per_token": 2.2e-06,
@ -12005,6 +12076,7 @@
},
"azure/us/gpt-4.1-mini-2025-04-14": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/us/gpt-5.4-mini",
"cache_read_input_token_cost": 1.1e-07,
"cache_read_input_token_cost_priority": 1.93e-07,
"input_cost_per_token": 4.4e-07,
@ -12047,6 +12119,7 @@
},
"azure/us/gpt-4.1-nano-2025-04-14": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/us/gpt-5.4-nano",
"cache_read_input_token_cost": 2.8e-08,
"input_cost_per_token": 1.1e-07,
"input_cost_per_token_batches": 5.5e-08,
@ -12254,6 +12327,7 @@
"cache_read_input_token_cost": 1.375e-07,
"cache_read_input_token_cost_priority": 2.75e-07,
"deprecation_date": "2027-02-09",
"successor_model": "azure/us/gpt-5.1",
"input_cost_per_token": 1.375e-06,
"input_cost_per_token_batches": 6.875e-07,
"input_cost_per_token_priority": 2.75e-06,
@ -12298,6 +12372,7 @@
"cache_read_input_token_cost": 2.75e-08,
"cache_read_input_token_cost_priority": 4.95e-08,
"deprecation_date": "2027-02-09",
"successor_model": "azure/us/gpt-5.4-mini",
"input_cost_per_token": 2.75e-07,
"input_cost_per_token_batches": 1.375e-07,
"input_cost_per_token_priority": 4.95e-07,
@ -12341,6 +12416,7 @@
"azure/us/gpt-5-nano-2025-08-07": {
"cache_read_input_token_cost": 5.5e-09,
"deprecation_date": "2027-02-09",
"successor_model": "azure/us/gpt-5.4-nano",
"input_cost_per_token": 5.5e-08,
"input_cost_per_token_batches": 2.75e-08,
"litellm_provider": "azure",
@ -12381,6 +12457,7 @@
},
"azure/us/gpt-5.1": {
"deprecation_date": "2027-05-15",
"successor_model": "azure/us/gpt-5.2",
"cache_read_input_token_cost": 1.375e-07,
"cache_read_input_token_cost_batches": 6.875e-08,
"cache_read_input_token_cost_priority": 2.75e-07,
@ -12428,6 +12505,7 @@
},
"azure/us/gpt-5.1-codex": {
"deprecation_date": "2027-05-15",
"successor_model": "azure/us/gpt-5.2-codex",
"cache_read_input_token_cost": 1.375e-07,
"input_cost_per_token": 1.375e-06,
"litellm_provider": "azure",
@ -12843,6 +12921,7 @@
},
"azure_ai/FW-GLM-5": {
"deprecation_date": "2027-07-01",
"successor_model": "azure_ai/FW-GLM-5.2",
"cache_read_input_token_cost": 2.2e-07,
"input_cost_per_token": 1.1e-06,
"litellm_provider": "azure_ai",
@ -12859,6 +12938,7 @@
},
"azure_ai/FW-GLM-5.1": {
"deprecation_date": "2027-07-01",
"successor_model": "azure_ai/FW-GLM-5.2",
"cache_read_input_token_cost": 2.86e-07,
"input_cost_per_token": 1.54e-06,
"litellm_provider": "azure_ai",
@ -13116,6 +13196,7 @@
"/v1/images/edits"
],
"deprecation_date": "2026-10-01",
"successor_model": "azure_ai/MAI-Image-2.6",
"max_input_tokens": 32000
},
"azure_ai/MAI-Image-2.5-Flash": {
@ -13131,6 +13212,7 @@
"/v1/images/edits"
],
"deprecation_date": "2026-10-01",
"successor_model": "azure_ai/MAI-Image-2.6-Flash",
"max_input_tokens": 32000
},
"azure_ai/MAI-Image-2.5-Pro": {
@ -13686,6 +13768,7 @@
},
"azure_ai/grok-4": {
"deprecation_date": "2027-01-31",
"successor_model": "azure_ai/grok-4.3",
"input_cost_per_token": 3e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 262000,
@ -15660,6 +15743,7 @@
"cache_creation_input_token_cost_above_1hr": 7.2e-06,
"cache_read_input_token_cost": 3.6e-07,
"deprecation_date": "2027-04-08",
"successor_model": "bedrock/us-gov-east-1/anthropic.claude-sonnet-5-5",
"input_cost_per_token": 3.6e-06,
"litellm_provider": "bedrock",
"supports_tool_search": true,
@ -15832,6 +15916,7 @@
"cache_creation_input_token_cost_above_1hr": 7.2e-06,
"cache_read_input_token_cost": 3.6e-07,
"deprecation_date": "2027-04-08",
"successor_model": "bedrock/us-gov-west-1/anthropic.claude-sonnet-5-5",
"input_cost_per_token": 3.6e-06,
"litellm_provider": "bedrock",
"supports_tool_search": true,
@ -21951,6 +22036,7 @@
"cache_creation_input_token_cost": 3.74997e-06,
"cache_read_input_token_cost": 3.0002e-07,
"deprecation_date": "2026-10-09",
"successor_model": "databricks/databricks-claude-sonnet-5",
"input_cost_per_token": 2.99999e-06,
"input_dbu_cost_per_token": 4.2857e-05,
"litellm_provider": "databricks",
@ -22136,6 +22222,7 @@
"cache_creation_input_token_cost": 3.0002e-07,
"cache_read_input_token_cost": 3.0002e-08,
"deprecation_date": "2026-10-02",
"successor_model": "databricks/databricks-gemini-3-5-flash",
"input_cost_per_token": 3.0001999999999996e-07,
"input_dbu_cost_per_token": 4.285999999999999e-06,
"litellm_provider": "databricks",
@ -25675,6 +25762,7 @@
"cache_read_input_token_cost": 1.1e-07,
"input_cost_per_token": 1.1e-06,
"deprecation_date": "2026-10-15",
"successor_model": "eu.anthropic.claude-haiku-5-5",
"litellm_provider": "bedrock_converse",
"supports_tool_search": true,
"max_input_tokens": 200000,
@ -25826,6 +25914,7 @@
"cache_creation_input_token_cost": 3.75e-06,
"cache_read_input_token_cost": 3e-07,
"deprecation_date": "2026-10-14",
"successor_model": "eu.anthropic.claude-sonnet-5",
"input_cost_per_token": 3e-06,
"input_cost_per_token_above_200k_tokens": 6e-06,
"output_cost_per_token_above_200k_tokens": 2.25e-05,
@ -25869,6 +25958,7 @@
"cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05,
"cache_read_input_token_cost_above_200k_tokens": 6.6e-07,
"deprecation_date": "2027-04-08",
"successor_model": "eu.anthropic.claude-sonnet-5-5",
"litellm_provider": "bedrock_converse",
"supports_tool_search": true,
"max_input_tokens": 200000,
@ -28493,6 +28583,7 @@
"cache_read_input_token_cost": 1.4e-07,
"cache_read_input_token_cost_priority": 1.75e-07,
"deprecation_date": "2026-09-25",
"successor_model": "fireworks_ai/accounts/fireworks/models/glm-5p3",
"input_cost_per_token": 1.4e-06,
"input_cost_per_token_priority": 1.75e-06,
"litellm_provider": "fireworks_ai",
@ -28868,6 +28959,7 @@
"cache_read_input_token_cost": 1.4e-07,
"cache_read_input_token_cost_priority": 1.75e-07,
"deprecation_date": "2026-09-25",
"successor_model": "fireworks_ai/glm-5p3",
"input_cost_per_token": 1.4e-06,
"input_cost_per_token_priority": 1.75e-06,
"litellm_provider": "fireworks_ai",
@ -29900,6 +29992,7 @@
"gemini-3.1-flash-lite": {
"cache_read_input_audio_token_cost": 5e-08,
"deprecation_date": "2027-05-07",
"successor_model": "gemini-3.5-flash-lite",
"cache_read_input_token_cost": 2.5e-08,
"cache_read_input_token_cost_batches": 1.25e-08,
"cache_read_input_token_cost_flex": 1.25e-08,
@ -30622,6 +30715,7 @@
"vertex_ai/gemini-3.5-flash": {
"prompt_cache_min_tokens": 4096,
"deprecation_date": "2027-05-19",
"successor_model": "vertex_ai/gemini-3.8-flash",
"cache_read_input_token_cost": 1.5e-07,
"cache_read_input_token_cost_batches": 7.5e-08,
"input_cost_per_token": 1.5e-06,
@ -31210,6 +31304,7 @@
},
"gemini-embedding-001": {
"deprecation_date": "2028-05-20",
"successor_model": "gemini-embedding-2",
"input_cost_per_token": 1.5e-07,
"input_cost_per_token_batches": 1.2e-07,
"litellm_provider": "vertex_ai-embedding-models",
@ -31597,6 +31692,7 @@
"cache_read_input_token_cost_flex": 3e-08,
"cache_read_input_token_cost_priority": 5.4e-08,
"deprecation_date": "2026-12-01",
"successor_model": "gemini/gemini-3-flash-preview",
"input_cost_per_audio_token": 1e-06,
"input_cost_per_audio_token_flex": 5e-07,
"input_cost_per_token": 3e-07,
@ -32184,6 +32280,7 @@
"supports_url_context": true,
"cache_read_input_token_cost_above_200k_tokens_batches": 2.5e-07,
"deprecation_date": "2026-12-01",
"successor_model": "gemini/gemini-3.1-pro-preview",
"input_cost_per_token_above_200k_tokens_batches": 1.25e-06,
"output_cost_per_token_above_200k_tokens_batches": 7.5e-06
},
@ -32917,6 +33014,7 @@
"gemini-3.5-flash": {
"prompt_cache_min_tokens": 4096,
"deprecation_date": "2027-05-19",
"successor_model": "gemini-3.8-flash",
"cache_read_input_token_cost": 1.5e-07,
"cache_read_input_token_cost_batches": 7.5e-08,
"input_cost_per_audio_token": 1.5e-06,
@ -34917,6 +35015,7 @@
"cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05,
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
"deprecation_date": "2027-04-08",
"successor_model": "global.anthropic.claude-sonnet-5-5",
"litellm_provider": "bedrock_converse",
"supports_tool_search": true,
"max_input_tokens": 200000,
@ -34952,6 +35051,7 @@
"cache_creation_input_token_cost": 3.75e-06,
"cache_read_input_token_cost": 3e-07,
"deprecation_date": "2026-10-14",
"successor_model": "global.anthropic.claude-sonnet-5",
"input_cost_per_token": 3e-06,
"input_cost_per_token_above_200k_tokens": 6e-06,
"output_cost_per_token_above_200k_tokens": 2.25e-05,
@ -39050,6 +39150,7 @@
"gpt-5-chat": {
"cache_read_input_token_cost": 1.25e-07,
"deprecation_date": "2026-07-23",
"successor_model": "gpt-5.2-chat-latest",
"input_cost_per_token": 1.25e-06,
"litellm_provider": "openai",
"max_input_tokens": 128000,
@ -40573,6 +40674,7 @@
"cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05,
"cache_read_input_token_cost_above_200k_tokens": 6.6e-07,
"deprecation_date": "2027-04-08",
"successor_model": "jp.anthropic.claude-sonnet-5-5",
"litellm_provider": "bedrock_converse",
"supports_tool_search": true,
"max_input_tokens": 200000,
@ -49995,6 +50097,7 @@
"cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05,
"cache_read_input_token_cost_above_200k_tokens": 6.6e-07,
"deprecation_date": "2027-04-08",
"successor_model": "us.anthropic.claude-sonnet-5-5",
"litellm_provider": "bedrock_converse",
"supports_tool_search": true,
"max_input_tokens": 200000,
@ -50037,6 +50140,7 @@
"cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.44e-05,
"cache_read_input_token_cost_above_200k_tokens": 7.2e-07,
"deprecation_date": "2027-04-08",
"successor_model": "us-gov.anthropic.claude-sonnet-5-5",
"litellm_provider": "bedrock_converse",
"supports_tool_search": true,
"max_input_tokens": 200000,
@ -50545,6 +50649,7 @@
"cache_creation_input_token_cost": 3.75e-06,
"cache_read_input_token_cost": 3e-07,
"deprecation_date": "2026-10-14",
"successor_model": "us.anthropic.claude-sonnet-5",
"input_cost_per_token": 3e-06,
"input_cost_per_token_above_200k_tokens": 6e-06,
"output_cost_per_token_above_200k_tokens": 2.25e-05,
@ -52017,6 +52122,7 @@
},
"vertex_ai/claude-haiku-4-5": {
"deprecation_date": "2026-10-15",
"successor_model": "vertex_ai/claude-haiku-5-5",
"cache_creation_input_token_cost": 1.25e-06,
"cache_creation_input_token_cost_above_1hr": 2e-06,
"cache_creation_input_token_cost_batches": 6.25e-07,
@ -52188,6 +52294,7 @@
},
"vertex_ai/claude-opus-4-5": {
"deprecation_date": "2026-11-24",
"successor_model": "vertex_ai/claude-opus-5-5",
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_1hr": 1e-05,
"cache_creation_input_token_cost_batches": 3.125e-06,
@ -52797,6 +52904,7 @@
},
"vertex_ai/claude-sonnet-4-5": {
"deprecation_date": "2026-09-29",
"successor_model": "vertex_ai/claude-sonnet-5-5",
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_1hr": 6e-06,
"cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05,
@ -53362,6 +53470,7 @@
"vertex_ai/gemini-3.1-flash-lite": {
"cache_read_input_audio_token_cost": 5e-08,
"deprecation_date": "2027-05-07",
"successor_model": "vertex_ai/gemini-3.5-flash-lite",
"cache_read_input_token_cost": 2.5e-08,
"cache_read_input_token_cost_batches": 1.25e-08,
"cache_read_input_token_cost_flex": 1.25e-08,
@ -53839,6 +53948,7 @@
"vertex_ai/zai-org/glm-4.7-maas": {
"cache_read_input_token_cost": 6e-08,
"deprecation_date": "2026-10-21",
"successor_model": "vertex_ai/zai-org/glm-5.2-maas",
"input_cost_per_token": 6e-07,
"litellm_provider": "vertex_ai-zai_models",
"max_input_tokens": 200000,
@ -53857,6 +53967,7 @@
"vertex_ai/zai-org/glm-5-maas": {
"cache_read_input_token_cost": 1e-07,
"deprecation_date": "2026-10-21",
"successor_model": "vertex_ai/zai-org/glm-5.2-maas",
"input_cost_per_token": 1e-06,
"litellm_provider": "vertex_ai-zai_models",
"max_input_tokens": 200000,
@ -55205,6 +55316,7 @@
},
"zai.glm-4.7": {
"deprecation_date": "2027-03-30",
"successor_model": "zai.glm-5",
"input_cost_per_token": 6e-07,
"input_cost_per_token_batches": 3e-07,
"input_cost_per_token_flex": 3e-07,
@ -64804,6 +64916,7 @@
"fireworks_ai/glm-5p2-fast": {
"cache_read_input_token_cost": 2.1e-07,
"deprecation_date": "2026-09-25",
"successor_model": "fireworks_ai/glm-5p3-fast",
"input_cost_per_token": 2.1e-06,
"litellm_provider": "fireworks_ai",
"max_input_tokens": 1048576,
@ -65073,6 +65186,7 @@
"fireworks_ai/accounts/fireworks/routers/glm-5p2-fast": {
"cache_read_input_token_cost": 2.1e-07,
"deprecation_date": "2026-09-25",
"successor_model": "fireworks_ai/accounts/fireworks/routers/glm-5p3-fast",
"input_cost_per_token": 2.1e-06,
"litellm_provider": "fireworks_ai",
"max_input_tokens": 1048576,
@ -67527,6 +67641,7 @@
},
"xai/grok-voice-transcribe-1.0": {
"deprecation_date": "2026-10-02",
"successor_model": "xai/grok-voice-transcribe-2.0",
"input_cost_per_second": 2.778e-05,
"litellm_provider": "xai",
"metadata": {
@ -71038,6 +71153,7 @@
},
"azure/eu/gpt-4.1": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/eu/gpt-5.1",
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_priority": 9.63e-07,
"input_cost_per_token": 2.2e-06,
@ -71057,6 +71173,7 @@
},
"azure/eu/gpt-4.1-mini": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/eu/gpt-5.4-mini",
"cache_read_input_token_cost": 1.1e-07,
"cache_read_input_token_cost_priority": 1.93e-07,
"input_cost_per_token": 4.4e-07,
@ -71076,6 +71193,7 @@
},
"azure/eu/gpt-4.1-nano": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/eu/gpt-5.4-nano",
"cache_read_input_token_cost": 2.8e-08,
"input_cost_per_token": 1.1e-07,
"input_cost_per_token_batches": 5.5e-08,
@ -71100,6 +71218,7 @@
},
"azure/eu/gpt-5": {
"deprecation_date": "2027-02-09",
"successor_model": "azure/eu/gpt-5.1",
"cache_read_input_token_cost": 1.375e-07,
"cache_read_input_token_cost_batches": 6.875e-08,
"cache_read_input_token_cost_priority": 2.75e-07,
@ -71120,6 +71239,7 @@
},
"azure/eu/gpt-5-codex": {
"deprecation_date": "2027-03-17",
"successor_model": "azure/eu/gpt-5.1-codex",
"cache_read_input_token_cost": 1.38e-07,
"input_cost_per_token": 1.375e-06,
"litellm_provider": "azure",
@ -71129,6 +71249,7 @@
},
"azure/eu/gpt-5-mini": {
"deprecation_date": "2027-02-09",
"successor_model": "azure/eu/gpt-5.4-mini",
"cache_read_input_token_cost": 2.75e-08,
"cache_read_input_token_cost_batches": 1.375e-08,
"cache_read_input_token_cost_priority": 4.95e-08,
@ -71149,6 +71270,7 @@
},
"azure/eu/gpt-5-nano": {
"deprecation_date": "2027-02-09",
"successor_model": "azure/eu/gpt-5.4-nano",
"cache_read_input_token_cost": 5.5e-09,
"cache_read_input_token_cost_batches": 2.75e-09,
"input_cost_per_token": 5.5e-08,
@ -71166,6 +71288,7 @@
},
"azure/eu/gpt-5-pro": {
"deprecation_date": "2027-04-07",
"successor_model": "azure/eu/gpt-5.2-pro",
"input_cost_per_token": 1.65e-05,
"input_cost_per_token_batches": 8.25e-06,
"litellm_provider": "azure",
@ -71190,6 +71313,7 @@
},
"azure/eu/gpt-5.2": {
"deprecation_date": "2027-06-08",
"successor_model": "azure/eu/gpt-5.4",
"cache_read_input_token_cost": 1.925e-07,
"cache_read_input_token_cost_batches": 9.625e-08,
"cache_read_input_token_cost_priority": 3.85e-07,
@ -71210,6 +71334,7 @@
},
"azure/eu/gpt-5.2-codex": {
"deprecation_date": "2027-07-13",
"successor_model": "azure/eu/gpt-5.3-codex",
"cache_read_input_token_cost": 1.925e-07,
"input_cost_per_token": 1.925e-06,
"litellm_provider": "azure",
@ -71625,6 +71750,7 @@
},
"azure/us/gpt-4.1": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/us/gpt-5.1",
"cache_read_input_token_cost": 5.5e-07,
"cache_read_input_token_cost_priority": 9.63e-07,
"input_cost_per_token": 2.2e-06,
@ -71644,6 +71770,7 @@
},
"azure/us/gpt-4.1-mini": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/us/gpt-5.4-mini",
"cache_read_input_token_cost": 1.1e-07,
"cache_read_input_token_cost_priority": 1.93e-07,
"input_cost_per_token": 4.4e-07,
@ -71663,6 +71790,7 @@
},
"azure/us/gpt-4.1-nano": {
"deprecation_date": "2027-04-14",
"successor_model": "azure/us/gpt-5.4-nano",
"cache_read_input_token_cost": 2.8e-08,
"input_cost_per_token": 1.1e-07,
"input_cost_per_token_batches": 5.5e-08,
@ -71687,6 +71815,7 @@
},
"azure/us/gpt-5": {
"deprecation_date": "2027-02-09",
"successor_model": "azure/us/gpt-5.1",
"cache_read_input_token_cost": 1.375e-07,
"cache_read_input_token_cost_batches": 6.875e-08,
"cache_read_input_token_cost_priority": 2.75e-07,
@ -71707,6 +71836,7 @@
},
"azure/us/gpt-5-codex": {
"deprecation_date": "2027-03-17",
"successor_model": "azure/us/gpt-5.1-codex",
"cache_read_input_token_cost": 1.38e-07,
"input_cost_per_token": 1.375e-06,
"litellm_provider": "azure",
@ -71716,6 +71846,7 @@
},
"azure/us/gpt-5-mini": {
"deprecation_date": "2027-02-09",
"successor_model": "azure/us/gpt-5.4-mini",
"cache_read_input_token_cost": 2.75e-08,
"cache_read_input_token_cost_batches": 1.375e-08,
"cache_read_input_token_cost_priority": 4.95e-08,
@ -71736,6 +71867,7 @@
},
"azure/us/gpt-5-nano": {
"deprecation_date": "2027-02-09",
"successor_model": "azure/us/gpt-5.4-nano",
"cache_read_input_token_cost": 5.5e-09,
"cache_read_input_token_cost_batches": 2.75e-09,
"input_cost_per_token": 5.5e-08,
@ -71753,6 +71885,7 @@
},
"azure/us/gpt-5-pro": {
"deprecation_date": "2027-04-07",
"successor_model": "azure/us/gpt-5.2-pro",
"input_cost_per_token": 1.65e-05,
"input_cost_per_token_batches": 8.25e-06,
"litellm_provider": "azure",
@ -71777,6 +71910,7 @@
},
"azure/us/gpt-5.2": {
"deprecation_date": "2027-06-08",
"successor_model": "azure/us/gpt-5.4",
"cache_read_input_token_cost": 1.925e-07,
"cache_read_input_token_cost_batches": 9.625e-08,
"cache_read_input_token_cost_priority": 3.85e-07,
@ -71797,6 +71931,7 @@
},
"azure/us/gpt-5.2-codex": {
"deprecation_date": "2027-07-13",
"successor_model": "azure/us/gpt-5.3-codex",
"cache_read_input_token_cost": 1.925e-07,
"input_cost_per_token": 1.925e-06,
"litellm_provider": "azure",
@ -79247,6 +79382,7 @@
"cache_creation_input_token_cost_batches": 1.875e-06,
"cache_read_input_token_cost_batches": 1.5e-07,
"deprecation_date": "2026-11-30",
"successor_model": "bedrock/claude_platform/claude-sonnet-5-5",
"input_cost_per_token_batches": 1.5e-06,
"litellm_provider": "bedrock",
"max_input_tokens": 200000,