Skip to content

Commit 0beec45

Browse files
mateo-berrimateo-berri
authored
[Feat] Add azure/gpt-5.5 + azure/gpt-5.5-pro entries (+ dated variants) (BerriAI#26361)
* feat(azure): add azure/gpt-5.5 + azure/gpt-5.5-pro entries (+ dated variants) Azure variants of OpenAI's GPT-5.5 family. Microsoft has not yet shipped GPT-5.5 on Azure OpenAI (latest GA on the Foundry models page is GPT-5.4 as of 2026-04-24), but adding the entries day-0 mirrors the established precedent for azure/gpt-5.4* (which were in the cost map before the Azure rollout) so cost tracking and capability flags work the moment customers deploy. Schema follows the existing azure/gpt-5.4* shape: - Same base/long-context pricing as openai/gpt-5.5*: $5/$30 chat, $60/$360 pro per 1M, with priority tier 2x base - Azure variants drop the flex/batches keys (Azure has no flex tier) but keep priority pricing, matching gpt-5.4* precedent - mode=chat for the thinking model, mode=responses for pro reasoning_effort capability flags mirror the OpenAI variants exactly since Azure proxies the same API contract: minimal rejection on both chat and pro, low/none rejection on pro. Once BerriAI#26456 (which sets supports_low_reasoning_effort + minimal=false on openai/gpt-5.5*) lands, OpenAI and Azure flag profiles align. Tests pin entry presence + pricing for all four Azure variants and verify the live-API-derived reasoning_effort flags. * test: register supports_low_reasoning_effort in cost-map JSON schema azure/gpt-5.5-pro and azure/gpt-5.5-pro-2026-04-23 added in this branch carry supports_low_reasoning_effort=false. The strict 'additionalProperties: false' schema in test_aaamodel_prices_and_context_window_json_is_valid rejected the new key. Register it alongside the other supports_*_reasoning_effort entries. Note: the runtime side of this flag (code that reads it) lands in BerriAI#26456. Until that PR merges the flag is inert for both Azure and OpenAI pro entries, but having the schema accept it lets cost-map tests pass on either merge order.
1 parent d21e90f commit 0beec45

4 files changed

Lines changed: 384 additions & 0 deletions

File tree

‎litellm/model_prices_and_context_window_backup.json‎

Lines changed: 163 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -4645,6 +4645,169 @@
46454645
"supports_vision": true,
46464646
"supports_web_search": true
46474647
},
4648+
"azure/gpt-5.5": {
4649+
"cache_read_input_token_cost": 5e-07,
4650+
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
4651+
"cache_read_input_token_cost_priority": 1e-06,
4652+
"cache_read_input_token_cost_above_272k_tokens_priority": 2e-06,
4653+
"input_cost_per_token": 5e-06,
4654+
"input_cost_per_token_above_272k_tokens": 1e-05,
4655+
"input_cost_per_token_priority": 1e-05,
4656+
"input_cost_per_token_above_272k_tokens_priority": 2e-05,
4657+
"litellm_provider": "azure",
4658+
"max_input_tokens": 1050000,
4659+
"max_output_tokens": 128000,
4660+
"max_tokens": 128000,
4661+
"mode": "chat",
4662+
"output_cost_per_token": 3e-05,
4663+
"output_cost_per_token_above_272k_tokens": 4.5e-05,
4664+
"output_cost_per_token_priority": 6e-05,
4665+
"output_cost_per_token_above_272k_tokens_priority": 9e-05,
4666+
"supported_endpoints": [
4667+
"/v1/chat/completions",
4668+
"/v1/batch",
4669+
"/v1/responses"
4670+
],
4671+
"supported_modalities": [
4672+
"text",
4673+
"image"
4674+
],
4675+
"supported_output_modalities": [
4676+
"text"
4677+
],
4678+
"supports_function_calling": true,
4679+
"supports_native_streaming": true,
4680+
"supports_parallel_function_calling": true,
4681+
"supports_pdf_input": true,
4682+
"supports_prompt_caching": true,
4683+
"supports_reasoning": true,
4684+
"supports_response_schema": true,
4685+
"supports_system_messages": true,
4686+
"supports_tool_choice": true,
4687+
"supports_service_tier": true,
4688+
"supports_vision": true,
4689+
"supports_web_search": true,
4690+
"supports_none_reasoning_effort": true,
4691+
"supports_xhigh_reasoning_effort": true,
4692+
"supports_minimal_reasoning_effort": false
4693+
},
4694+
"azure/gpt-5.5-2026-04-23": {
4695+
"cache_read_input_token_cost": 5e-07,
4696+
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
4697+
"cache_read_input_token_cost_priority": 1e-06,
4698+
"cache_read_input_token_cost_above_272k_tokens_priority": 2e-06,
4699+
"input_cost_per_token": 5e-06,
4700+
"input_cost_per_token_above_272k_tokens": 1e-05,
4701+
"input_cost_per_token_priority": 1e-05,
4702+
"input_cost_per_token_above_272k_tokens_priority": 2e-05,
4703+
"litellm_provider": "azure",
4704+
"max_input_tokens": 1050000,
4705+
"max_output_tokens": 128000,
4706+
"max_tokens": 128000,
4707+
"mode": "chat",
4708+
"output_cost_per_token": 3e-05,
4709+
"output_cost_per_token_above_272k_tokens": 4.5e-05,
4710+
"output_cost_per_token_priority": 6e-05,
4711+
"output_cost_per_token_above_272k_tokens_priority": 9e-05,
4712+
"supported_endpoints": [
4713+
"/v1/chat/completions",
4714+
"/v1/batch",
4715+
"/v1/responses"
4716+
],
4717+
"supported_modalities": [
4718+
"text",
4719+
"image"
4720+
],
4721+
"supported_output_modalities": [
4722+
"text"
4723+
],
4724+
"supports_function_calling": true,
4725+
"supports_native_streaming": true,
4726+
"supports_parallel_function_calling": true,
4727+
"supports_pdf_input": true,
4728+
"supports_prompt_caching": true,
4729+
"supports_reasoning": true,
4730+
"supports_response_schema": true,
4731+
"supports_system_messages": true,
4732+
"supports_tool_choice": true,
4733+
"supports_service_tier": true,
4734+
"supports_vision": true,
4735+
"supports_web_search": true
4736+
},
4737+
"azure/gpt-5.5-pro": {
4738+
"cache_read_input_token_cost": 6e-06,
4739+
"cache_read_input_token_cost_above_272k_tokens": 1.2e-05,
4740+
"input_cost_per_token": 6e-05,
4741+
"input_cost_per_token_above_272k_tokens": 0.00012,
4742+
"litellm_provider": "azure",
4743+
"max_input_tokens": 1050000,
4744+
"max_output_tokens": 128000,
4745+
"max_tokens": 128000,
4746+
"mode": "responses",
4747+
"output_cost_per_token": 0.00036,
4748+
"output_cost_per_token_above_272k_tokens": 0.00054,
4749+
"supported_endpoints": [
4750+
"/v1/batch",
4751+
"/v1/responses"
4752+
],
4753+
"supported_modalities": [
4754+
"text",
4755+
"image"
4756+
],
4757+
"supported_output_modalities": [
4758+
"text"
4759+
],
4760+
"supports_function_calling": true,
4761+
"supports_native_streaming": true,
4762+
"supports_parallel_function_calling": true,
4763+
"supports_pdf_input": true,
4764+
"supports_prompt_caching": true,
4765+
"supports_reasoning": true,
4766+
"supports_response_schema": false,
4767+
"supports_system_messages": true,
4768+
"supports_tool_choice": true,
4769+
"supports_vision": true,
4770+
"supports_web_search": true,
4771+
"supports_none_reasoning_effort": false,
4772+
"supports_xhigh_reasoning_effort": true,
4773+
"supports_minimal_reasoning_effort": false,
4774+
"supports_low_reasoning_effort": false
4775+
},
4776+
"azure/gpt-5.5-pro-2026-04-23": {
4777+
"cache_read_input_token_cost": 6e-06,
4778+
"cache_read_input_token_cost_above_272k_tokens": 1.2e-05,
4779+
"input_cost_per_token": 6e-05,
4780+
"input_cost_per_token_above_272k_tokens": 0.00012,
4781+
"litellm_provider": "azure",
4782+
"max_input_tokens": 1050000,
4783+
"max_output_tokens": 128000,
4784+
"max_tokens": 128000,
4785+
"mode": "responses",
4786+
"output_cost_per_token": 0.00036,
4787+
"output_cost_per_token_above_272k_tokens": 0.00054,
4788+
"supported_endpoints": [
4789+
"/v1/batch",
4790+
"/v1/responses"
4791+
],
4792+
"supported_modalities": [
4793+
"text",
4794+
"image"
4795+
],
4796+
"supported_output_modalities": [
4797+
"text"
4798+
],
4799+
"supports_function_calling": true,
4800+
"supports_native_streaming": true,
4801+
"supports_parallel_function_calling": true,
4802+
"supports_pdf_input": true,
4803+
"supports_prompt_caching": true,
4804+
"supports_reasoning": true,
4805+
"supports_response_schema": false,
4806+
"supports_system_messages": true,
4807+
"supports_tool_choice": true,
4808+
"supports_vision": true,
4809+
"supports_web_search": true
4810+
},
46484811
"azure/gpt-5.4-mini": {
46494812
"cache_read_input_token_cost": 7.5e-08,
46504813
"input_cost_per_token": 7.5e-07,

‎model_prices_and_context_window.json‎

Lines changed: 163 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -4659,6 +4659,169 @@
46594659
"supports_vision": true,
46604660
"supports_web_search": true
46614661
},
4662+
"azure/gpt-5.5": {
4663+
"cache_read_input_token_cost": 5e-07,
4664+
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
4665+
"cache_read_input_token_cost_priority": 1e-06,
4666+
"cache_read_input_token_cost_above_272k_tokens_priority": 2e-06,
4667+
"input_cost_per_token": 5e-06,
4668+
"input_cost_per_token_above_272k_tokens": 1e-05,
4669+
"input_cost_per_token_priority": 1e-05,
4670+
"input_cost_per_token_above_272k_tokens_priority": 2e-05,
4671+
"litellm_provider": "azure",
4672+
"max_input_tokens": 1050000,
4673+
"max_output_tokens": 128000,
4674+
"max_tokens": 128000,
4675+
"mode": "chat",
4676+
"output_cost_per_token": 3e-05,
4677+
"output_cost_per_token_above_272k_tokens": 4.5e-05,
4678+
"output_cost_per_token_priority": 6e-05,
4679+
"output_cost_per_token_above_272k_tokens_priority": 9e-05,
4680+
"supported_endpoints": [
4681+
"/v1/chat/completions",
4682+
"/v1/batch",
4683+
"/v1/responses"
4684+
],
4685+
"supported_modalities": [
4686+
"text",
4687+
"image"
4688+
],
4689+
"supported_output_modalities": [
4690+
"text"
4691+
],
4692+
"supports_function_calling": true,
4693+
"supports_native_streaming": true,
4694+
"supports_parallel_function_calling": true,
4695+
"supports_pdf_input": true,
4696+
"supports_prompt_caching": true,
4697+
"supports_reasoning": true,
4698+
"supports_response_schema": true,
4699+
"supports_system_messages": true,
4700+
"supports_tool_choice": true,
4701+
"supports_service_tier": true,
4702+
"supports_vision": true,
4703+
"supports_web_search": true,
4704+
"supports_none_reasoning_effort": true,
4705+
"supports_xhigh_reasoning_effort": true,
4706+
"supports_minimal_reasoning_effort": false
4707+
},
4708+
"azure/gpt-5.5-2026-04-23": {
4709+
"cache_read_input_token_cost": 5e-07,
4710+
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
4711+
"cache_read_input_token_cost_priority": 1e-06,
4712+
"cache_read_input_token_cost_above_272k_tokens_priority": 2e-06,
4713+
"input_cost_per_token": 5e-06,
4714+
"input_cost_per_token_above_272k_tokens": 1e-05,
4715+
"input_cost_per_token_priority": 1e-05,
4716+
"input_cost_per_token_above_272k_tokens_priority": 2e-05,
4717+
"litellm_provider": "azure",
4718+
"max_input_tokens": 1050000,
4719+
"max_output_tokens": 128000,
4720+
"max_tokens": 128000,
4721+
"mode": "chat",
4722+
"output_cost_per_token": 3e-05,
4723+
"output_cost_per_token_above_272k_tokens": 4.5e-05,
4724+
"output_cost_per_token_priority": 6e-05,
4725+
"output_cost_per_token_above_272k_tokens_priority": 9e-05,
4726+
"supported_endpoints": [
4727+
"/v1/chat/completions",
4728+
"/v1/batch",
4729+
"/v1/responses"
4730+
],
4731+
"supported_modalities": [
4732+
"text",
4733+
"image"
4734+
],
4735+
"supported_output_modalities": [
4736+
"text"
4737+
],
4738+
"supports_function_calling": true,
4739+
"supports_native_streaming": true,
4740+
"supports_parallel_function_calling": true,
4741+
"supports_pdf_input": true,
4742+
"supports_prompt_caching": true,
4743+
"supports_reasoning": true,
4744+
"supports_response_schema": true,
4745+
"supports_system_messages": true,
4746+
"supports_tool_choice": true,
4747+
"supports_service_tier": true,
4748+
"supports_vision": true,
4749+
"supports_web_search": true
4750+
},
4751+
"azure/gpt-5.5-pro": {
4752+
"cache_read_input_token_cost": 6e-06,
4753+
"cache_read_input_token_cost_above_272k_tokens": 1.2e-05,
4754+
"input_cost_per_token": 6e-05,
4755+
"input_cost_per_token_above_272k_tokens": 0.00012,
4756+
"litellm_provider": "azure",
4757+
"max_input_tokens": 1050000,
4758+
"max_output_tokens": 128000,
4759+
"max_tokens": 128000,
4760+
"mode": "responses",
4761+
"output_cost_per_token": 0.00036,
4762+
"output_cost_per_token_above_272k_tokens": 0.00054,
4763+
"supported_endpoints": [
4764+
"/v1/batch",
4765+
"/v1/responses"
4766+
],
4767+
"supported_modalities": [
4768+
"text",
4769+
"image"
4770+
],
4771+
"supported_output_modalities": [
4772+
"text"
4773+
],
4774+
"supports_function_calling": true,
4775+
"supports_native_streaming": true,
4776+
"supports_parallel_function_calling": true,
4777+
"supports_pdf_input": true,
4778+
"supports_prompt_caching": true,
4779+
"supports_reasoning": true,
4780+
"supports_response_schema": false,
4781+
"supports_system_messages": true,
4782+
"supports_tool_choice": true,
4783+
"supports_vision": true,
4784+
"supports_web_search": true,
4785+
"supports_none_reasoning_effort": false,
4786+
"supports_xhigh_reasoning_effort": true,
4787+
"supports_minimal_reasoning_effort": false,
4788+
"supports_low_reasoning_effort": false
4789+
},
4790+
"azure/gpt-5.5-pro-2026-04-23": {
4791+
"cache_read_input_token_cost": 6e-06,
4792+
"cache_read_input_token_cost_above_272k_tokens": 1.2e-05,
4793+
"input_cost_per_token": 6e-05,
4794+
"input_cost_per_token_above_272k_tokens": 0.00012,
4795+
"litellm_provider": "azure",
4796+
"max_input_tokens": 1050000,
4797+
"max_output_tokens": 128000,
4798+
"max_tokens": 128000,
4799+
"mode": "responses",
4800+
"output_cost_per_token": 0.00036,
4801+
"output_cost_per_token_above_272k_tokens": 0.00054,
4802+
"supported_endpoints": [
4803+
"/v1/batch",
4804+
"/v1/responses"
4805+
],
4806+
"supported_modalities": [
4807+
"text",
4808+
"image"
4809+
],
4810+
"supported_output_modalities": [
4811+
"text"
4812+
],
4813+
"supports_function_calling": true,
4814+
"supports_native_streaming": true,
4815+
"supports_parallel_function_calling": true,
4816+
"supports_pdf_input": true,
4817+
"supports_prompt_caching": true,
4818+
"supports_reasoning": true,
4819+
"supports_response_schema": false,
4820+
"supports_system_messages": true,
4821+
"supports_tool_choice": true,
4822+
"supports_vision": true,
4823+
"supports_web_search": true
4824+
},
46624825
"azure/gpt-5.4-mini": {
46634826
"cache_read_input_token_cost": 7.5e-08,
46644827
"input_cost_per_token": 7.5e-07,

0 commit comments

Comments
 (0)