added gpt-4.1 models and gemini-2.0 and 2.5 pro models (#2609)
Some checks failed
Notify Downstream / notify-downstream (push) Has been cancelled

* added gpt4.1 models and gemini 2.0 and 2.5 models

* added flash model

* Updated test fun to all models

* Added Gemma3 test cases and passed all google test case

* added gemini 2.5 flash

* added gpt4.1 models and gemini 2.0 and 2.5 models

* added flash model

* Updated test fun to all models

* Added Gemma3 test cases and passed all google test case

* added gemini 2.5 flash

* added gpt4.1 models and gemini 2.0 and 2.5 models

* added flash model

* Updated test fun to all models

* Added Gemma3 test cases and passed all google test case

* added gemini 2.5 flash

* test: add missing cassettes

* test: ignore authorization key from gemini/gemma3 request

---------

Co-authored-by: Lucas Gomide <lucaslg200@gmail.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
This commit is contained in:
Kunal Lunia
2025-04-23 23:50:32 +05:30
committed by GitHub
parent 9ebf3aa043
commit 685d20f46c
15 changed files with 913 additions and 1 deletions

View File

@@ -122,7 +122,16 @@ PROVIDERS = [
]
MODELS = {
"openai": ["gpt-4", "gpt-4o", "gpt-4o-mini", "o1-mini", "o1-preview"],
"openai": [
"gpt-4",
"gpt-4.1",
"gpt-4.1-mini-2025-04-14",
"gpt-4.1-nano-2025-04-14",
"gpt-4o",
"gpt-4o-mini",
"o1-mini",
"o1-preview",
],
"anthropic": [
"claude-3-5-sonnet-20240620",
"claude-3-sonnet-20240229",
@@ -132,8 +141,17 @@ MODELS = {
"gemini": [
"gemini/gemini-1.5-flash",
"gemini/gemini-1.5-pro",
"gemini/gemini-2.0-flash-lite-001",
"gemini/gemini-2.0-flash-001",
"gemini/gemini-2.0-flash-thinking-exp-01-21",
"gemini/gemini-2.5-flash-preview-04-17",
"gemini/gemini-2.5-pro-exp-03-25",
"gemini/gemini-gemma-2-9b-it",
"gemini/gemini-gemma-2-27b-it",
"gemini/gemma-3-1b-it",
"gemini/gemma-3-4b-it",
"gemini/gemma-3-12b-it",
"gemini/gemma-3-27b-it",
],
"nvidia_nim": [
"nvidia_nim/nvidia/mistral-nemo-minitron-8b-8k-instruct",

View File

@@ -81,14 +81,26 @@ LLM_CONTEXT_WINDOW_SIZES = {
"gpt-4o": 128000,
"gpt-4o-mini": 128000,
"gpt-4-turbo": 128000,
"gpt-4.1": 1047576, # Based on official docs
"gpt-4.1-mini-2025-04-14": 1047576,
"gpt-4.1-nano-2025-04-14": 1047576,
"o1-preview": 128000,
"o1-mini": 128000,
"o3-mini": 200000, # Based on official o3-mini specifications
# gemini
"gemini-2.0-flash": 1048576,
"gemini-2.0-flash-thinking-exp-01-21": 32768,
"gemini-2.0-flash-lite-001": 1048576,
"gemini-2.0-flash-001": 1048576,
"gemini-2.5-flash-preview-04-17": 1048576,
"gemini-2.5-pro-exp-03-25": 1048576,
"gemini-1.5-pro": 2097152,
"gemini-1.5-flash": 1048576,
"gemini-1.5-flash-8b": 1048576,
"gemini/gemma-3-1b-it": 32000,
"gemini/gemma-3-4b-it": 128000,
"gemini/gemma-3-12b-it": 128000,
"gemini/gemma-3-27b-it": 128000,
# deepseek
"deepseek-chat": 128000,
# groq

View File

@@ -0,0 +1,59 @@
interactions:
- request:
body: '{"contents": [{"role": "user", "parts": [{"text": "What is the capital
of France?"}]}], "generationConfig": {"stop_sequences": []}}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '131'
content-type:
- application/json
host:
- generativelanguage.googleapis.com
user-agent:
- litellm/1.60.2
method: POST
uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-001:generateContent
response:
body:
string: !!binary |
H4sIAAAAAAAC/62RTU+EMBCG7/0VTY9kIQUT1vXqx0njRokxUQ8jDNAILaFdoyH8dwssbNGrTdo0
807nnT7TEUpZCjITGRjU7IK+2Ail3XgOmpIGpbHCHLLBBlpzyp1W59xtisGv4RFLSqQpNMJARVVO
b1qQKVKhqeftoRXa84JXyZy3/XJ/25wcW1XhUK5WGVZzej8nsFxIocsHBK3kkPaY3O/ZosJncauK
plXvQ9M+D3gUxiE/tzs6i+JtyHdkth5N2UFDgXdowFKB5e/Mlqgbk6gPlJfqMFLZTi4Ow5W8O8pG
WQArJYw3f4rqK2spKhetQ93+HSphvkes188Jc/iYVU8zH+Jg/N3hP3nt1l7kOJVpUE/YajFNpMDa
zsiPAu7nFejS5zxkpCc/6so6tIECAAA=
headers:
Alt-Svc:
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Content-Encoding:
- gzip
Content-Type:
- application/json; charset=UTF-8
Date:
- Tue, 22 Apr 2025 14:25:05 GMT
Server:
- scaffolding on HTTPServer2
Server-Timing:
- gfet4t7; dur=1219
Transfer-Encoding:
- chunked
Vary:
- Origin
- X-Origin
- Referer
X-Content-Type-Options:
- nosniff
X-Frame-Options:
- SAMEORIGIN
X-XSS-Protection:
- '0'
status:
code: 200
message: OK
version: 1

View File

@@ -0,0 +1,59 @@
interactions:
- request:
body: '{"contents": [{"role": "user", "parts": [{"text": "What is the capital
of France?"}]}], "generationConfig": {"stop_sequences": []}}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '131'
content-type:
- application/json
host:
- generativelanguage.googleapis.com
user-agent:
- litellm/1.60.2
method: POST
uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-lite-001:generateContent
response:
body:
string: !!binary |
H4sIAAAAAAAC/61RTU+EMBC98yuanhdSiMjq1Y+Txo0SY6J7GGGARmhJ2zUawn+3wMIWvdpDM5n3
Zt7Mm84jhGYgcp6DQU0vyavNENKN/4BJYVAYC8wpm2xBmRN3ep0TW4rBr6GIphWSDFpuoCayILcK
RIaEa7IDxXXwJqhT1y/xfnNSU7LGoVUjc6xnej8TaMEF19UjgpZioD2lDzu6oPBZ3smyVfJ9GNhn
AQuTMIpjFl/EZyxKwuTcm6VHUXrQUOI9GrCOwLI3tS2a1qTyA8WVPIyOJJOK498K3h5hI+3yKySM
N3+a6msryWvXVsdxuzvU3HyPlt68pNTxx6xmmv3xHBt/T/hPWtu1lne8ynSoZ1SaTxcpsbE38qOA
+UUNuvJtd/QZC6nXez+t5iqFggIAAA==
headers:
Alt-Svc:
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Content-Encoding:
- gzip
Content-Type:
- application/json; charset=UTF-8
Date:
- Tue, 22 Apr 2025 14:25:06 GMT
Server:
- scaffolding on HTTPServer2
Server-Timing:
- gfet4t7; dur=1090
Transfer-Encoding:
- chunked
Vary:
- Origin
- X-Origin
- Referer
X-Content-Type-Options:
- nosniff
X-Frame-Options:
- SAMEORIGIN
X-XSS-Protection:
- '0'
status:
code: 200
message: OK
version: 1

View File

@@ -0,0 +1,58 @@
interactions:
- request:
body: '{"contents": [{"role": "user", "parts": [{"text": "What is the capital
of France?"}]}], "generationConfig": {"stop_sequences": []}}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '131'
content-type:
- application/json
host:
- generativelanguage.googleapis.com
user-agent:
- litellm/1.60.2
method: POST
uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-thinking-exp-01-21:generateContent
response:
body:
string: !!binary |
H4sIAAAAAAAC/22QQWuEMBCF7/6KkKNsFt1DKb2221vp0koplD0M66jDxkSSWbCI/71Rq+vS5pCE
eW9meF8XCSFPYHLKgdHLB/EVKkJ04z1o1jAaDsJcCsUGHF+90+lW/2BhbIcmmVUoTtAQgxa2EM8O
zAkFeRHHB3Dk43grV5398j9urvuc1TgMq22Oerb3s0EWZMhXbwjemsH2nr0e5KKSybEN5SSaF4yj
5cVDiS/IEJLDkk82ztYNZ/aM5tFexuT306wVp39ltiHkjZLebf4M9U9hJek1vhXZkBA08feIbv+Z
yRUFvlk6UxjfY/TLY0L0gc7TxKLEOtBRu22iCg2+UlyROZMpFbaNSlK1S2XURz/Fy1P+CAIAAA==
headers:
Alt-Svc:
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Content-Encoding:
- gzip
Content-Type:
- application/json; charset=UTF-8
Date:
- Tue, 22 Apr 2025 14:25:04 GMT
Server:
- scaffolding on HTTPServer2
Server-Timing:
- gfet4t7; dur=764
Transfer-Encoding:
- chunked
Vary:
- Origin
- X-Origin
- Referer
X-Content-Type-Options:
- nosniff
X-Frame-Options:
- SAMEORIGIN
X-XSS-Protection:
- '0'
status:
code: 200
message: OK
version: 1

View File

@@ -0,0 +1,59 @@
interactions:
- request:
body: '{"contents": [{"role": "user", "parts": [{"text": "What is the capital
of France?"}]}], "generationConfig": {"stop_sequences": []}}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '131'
content-type:
- application/json
host:
- generativelanguage.googleapis.com
user-agent:
- litellm/1.60.2
method: POST
uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-preview-04-17:generateContent
response:
body:
string: !!binary |
H4sIAAAAAAAC/2WQT0+EMBDF7/0UTY9k2ewaDerVPzfjRokxMR4mMEBjaUk76BrCd7fAslvcHppm
5s2bvl/HOBcZ6FzmQOjELf/wFc678R56RhNq8o255IsNWDppp9MFby8h3A9DIq2QZ9BIAsVNwR8t
6Ay5dDyKdmCli6K1CCb74/tzddpnjcLBrDY5qlnezwJRSC1d9YLgjB5kr+nzThy7Uue49+UNmxeM
1qJ1UOITEvjkcMwnGmvqhlLzhfrOtGPy68kr4LRoJzeHPhmfcjmZrM5c3b3fKVXIL0DrI4KS9Duy
e3hPRYCBFtYzBhbQElSZtqzo3we37IBrIviG1skJVYm1hxdfrK/iQoGr4sbit8SfeHMZbxPBevYH
O2bXiSICAAA=
headers:
Alt-Svc:
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Content-Encoding:
- gzip
Content-Type:
- application/json; charset=UTF-8
Date:
- Tue, 22 Apr 2025 14:25:28 GMT
Server:
- scaffolding on HTTPServer2
Server-Timing:
- gfet4t7; dur=20971
Transfer-Encoding:
- chunked
Vary:
- Origin
- X-Origin
- Referer
X-Content-Type-Options:
- nosniff
X-Frame-Options:
- SAMEORIGIN
X-XSS-Protection:
- '0'
status:
code: 200
message: OK
version: 1

View File

@@ -0,0 +1,59 @@
interactions:
- request:
body: '{"contents": [{"role": "user", "parts": [{"text": "What is the capital
of France?"}]}], "generationConfig": {"stop_sequences": []}}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '131'
content-type:
- application/json
host:
- generativelanguage.googleapis.com
user-agent:
- litellm/1.60.2
method: POST
uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-pro-exp-03-25:generateContent
response:
body:
string: !!binary |
H4sIAAAAAAAC/12QT2uEMBDF7/kUIUepi2tZaHttu7fSpZVSKD0MOquhmkgygkX87o26cWM9SJj3
5s/7DYxzkYMqZAGEVjzwL1fhfJj/k6YVoSIn+JIrtmDo6l2+IXg7C2E/NYmsQp5DKwlqrs/8aEDl
yKXlUXQCI20U7UTQOa7v75vrPqNrnIY1usDa20dvEGeppK3eEKxWk+09ez2JVZWqwN6VE+YXzKNF
Z6HEFyRwyWHNJ1qjm5Yy/YPqUXdz8rtlVsBpI++T5GIg7WL+03xzMNc+ua2yDgkGcF1IqCX9zvSe
PzMRgKDNWR4EC3gJqnRXVrQ98T5lF2ALww80Vi6wSmwcvjjdHWJ3Yox9Gye3cXoQbGR/TedYqx4C
AAA=
headers:
Alt-Svc:
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Content-Encoding:
- gzip
Content-Type:
- application/json; charset=UTF-8
Date:
- Tue, 22 Apr 2025 14:25:30 GMT
Server:
- scaffolding on HTTPServer2
Server-Timing:
- gfet4t7; dur=2418
Transfer-Encoding:
- chunked
Vary:
- Origin
- X-Origin
- Referer
X-Content-Type-Options:
- nosniff
X-Frame-Options:
- SAMEORIGIN
X-XSS-Protection:
- '0'
status:
code: 200
message: OK
version: 1

View File

@@ -0,0 +1,59 @@
interactions:
- request:
body: '{"contents": [{"role": "user", "parts": [{"text": "What is the capital
of France?"}]}], "generationConfig": {"stop_sequences": []}}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '131'
content-type:
- application/json
host:
- generativelanguage.googleapis.com
user-agent:
- litellm/1.60.2
method: POST
uri: https://generativelanguage.googleapis.com/v1beta/models/gemma-3-12b-it:generateContent
response:
body:
string: !!binary |
H4sIAAAAAAAC/2WRTWvDMAyG7/kVwpdBSEvX7jB23QfsMFa2MAZbD2qipGaOFWwFWkr/+5ykaVPq
gGP0SvLrR/sIQGVoc52jkFcP8BMiAPtubzW2QlaCMIRCsEYn59x+7UfnkCK0bYtUuiHIsNaCBriA
F4c2I9Ae4niJTvs4nv7a/nuVGw9oPIOEIoOuJC+QadmBtkNlsAoIpeF1aJgFZ+SgYAfBUQIF+o1m
m0CJXhxbrnZJV5E1RhpHUzUyeTidV8n5aY4Ntb4rzskM6YchQRXaar/5IPRs27TP9H2pTqq2OW1D
eBYNF3StVeOxpDcSDJDxhFLVjqtaUv4j+8hNB/m+7zUayYW8mB914QD0QrqbJVdd/VO4U5vxqEZT
DE9EE+h2Y3r+TtUIg1yYGjB0/1V0BNIz+iLndQ+jpKrCyWJyO19PtKjoEP0DlZtdIF8CAAA=
headers:
Alt-Svc:
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Content-Encoding:
- gzip
Content-Type:
- application/json; charset=UTF-8
Date:
- Tue, 22 Apr 2025 14:25:39 GMT
Server:
- scaffolding on HTTPServer2
Server-Timing:
- gfet4t7; dur=3835
Transfer-Encoding:
- chunked
Vary:
- Origin
- X-Origin
- Referer
X-Content-Type-Options:
- nosniff
X-Frame-Options:
- SAMEORIGIN
X-XSS-Protection:
- '0'
status:
code: 200
message: OK
version: 1

View File

@@ -0,0 +1,60 @@
interactions:
- request:
body: '{"contents": [{"role": "user", "parts": [{"text": "What is the capital
of France?"}]}], "generationConfig": {"stop_sequences": []}}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '131'
content-type:
- application/json
host:
- generativelanguage.googleapis.com
user-agent:
- litellm/1.60.2
method: POST
uri: https://generativelanguage.googleapis.com/v1beta/models/gemma-3-1b-it:generateContent
response:
body:
string: !!binary |
H4sIAAAAAAAC/2VRy07DQAy85yusPUZtBSoIxJWHxAFRQYSQKAc3cVqL7DrKuqKlqsRv8Ht8CZuk
aVOxh314xuP1eBMBmBRdxhkqeXMFbyECsGn2GhOn5DQAXSgES6z0wG3XpncPFKVVnWSSBUGKJSsW
IDncVehSAvYQxxOs2MfxCKZu6u719/vHA0Iq1ooDyz6UTqlUDi9doELDr1M1aMbiinXcSQ9gtlTg
VqOGJc855VAztAZWvMInZ1SsoaJU5o6/KANxNDK9X2/39/fBoddKCqobsRLyO/q2I5icHfvFE6EX
V9Oek8eJ2aPsMlqF8EnUFWikzdLjnB5IMbiOe29NWYktNZEPcteybFy/bLV6MzqCxxc7XCXYcASd
nQ/+qfqbUJOL/ux6Yw0tYsG6buZ2+5qYng169KnOhuZ8j3aGtB69UOW5NWNO1uJwPDydDVlNtI3+
AD6XWQdvAgAA
headers:
Alt-Svc:
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Content-Encoding:
- gzip
Content-Type:
- application/json; charset=UTF-8
Date:
- Tue, 22 Apr 2025 14:25:32 GMT
Server:
- scaffolding on HTTPServer2
Server-Timing:
- gfet4t7; dur=1535
Transfer-Encoding:
- chunked
Vary:
- Origin
- X-Origin
- Referer
X-Content-Type-Options:
- nosniff
X-Frame-Options:
- SAMEORIGIN
X-XSS-Protection:
- '0'
status:
code: 200
message: OK
version: 1

View File

@@ -0,0 +1,60 @@
interactions:
- request:
body: '{"contents": [{"role": "user", "parts": [{"text": "What is the capital
of France?"}]}], "generationConfig": {"stop_sequences": []}}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '131'
content-type:
- application/json
host:
- generativelanguage.googleapis.com
user-agent:
- litellm/1.60.2
method: POST
uri: https://generativelanguage.googleapis.com/v1beta/models/gemma-3-27b-it:generateContent
response:
body:
string: !!binary |
H4sIAAAAAAAC/2VRXUvDMBR976+45EUo3RDnUHwTnSA4HFpEcHuI7e16aZqU5NZNxv67abtuHTbQ
hHPu5zm7AEAkUqeUSkYn7uDLIwC79t9wRjNq9kQPebCSlk+x3bcbvH0I47ZJEnGOkMiKWCowGTxZ
qRMEchCGC2nJheEYlnqpn/nCQaHNRkNmLJDvSwkoP1kpbeFAUYHAvtiMsgwVxGaDNmqRF1P/WIR5
7bAuI/ApLXxvE0gRYkumrHL0hIMNKtXcxA4y6XIyOoKkJkcau8ykVlxbHDczNUcM1tof36voJIY1
CptNS5Oi6sP3fYDISJPL31A6o5uw9/h1IY4s6RS3Hr4M+gZtaVE7ucY5svS2yKP4orJ+F45NgfrB
1K0tt12tgYln9PX0wLPxFpxR00n0r6p79D1JDc0d+O5XlIr4tzV29hmLgQx8NlQvQ3uvgoMgnUYf
aB11YqyxLOVoMrq6+R4Ri2Af/AEDrXcbkQIAAA==
headers:
Alt-Svc:
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Content-Encoding:
- gzip
Content-Type:
- application/json; charset=UTF-8
Date:
- Tue, 22 Apr 2025 14:25:41 GMT
Server:
- scaffolding on HTTPServer2
Server-Timing:
- gfet4t7; dur=2447
Transfer-Encoding:
- chunked
Vary:
- Origin
- X-Origin
- Referer
X-Content-Type-Options:
- nosniff
X-Frame-Options:
- SAMEORIGIN
X-XSS-Protection:
- '0'
status:
code: 200
message: OK
version: 1

View File

@@ -0,0 +1,60 @@
interactions:
- request:
body: '{"contents": [{"role": "user", "parts": [{"text": "What is the capital
of France?"}]}], "generationConfig": {"stop_sequences": []}}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '131'
content-type:
- application/json
host:
- generativelanguage.googleapis.com
user-agent:
- litellm/1.60.2
method: POST
uri: https://generativelanguage.googleapis.com/v1beta/models/gemma-3-4b-it:generateContent
response:
body:
string: !!binary |
H4sIAAAAAAAC/2WRzUrDQBDH73mKYY+lLUKLiBcPfoAHsWhQwXqYJtNk6WYn7E6woRQ8+wR68t18
Ah/BbWraFPeQXeb/z3z8ZhUBqARtqlMU8uoUnkMEYNV8NxpbIStBaEMhWKKTvXd7Vp13sAgtNz+p
OCdIsNSCBngOVw5tQqA99HoTdNr3ekOY2qm9lu+3Tw8ImeFZ8CahKDmYs4NQrA9z9Llm24cMvTi2
XNQQ2oakMlI5GsLP18d7k+mRK5NCzRUYvSAQhoXl12CuJdc2g4IdAc64Emg6OFOdzte790t/P69j
Q5thCk7JtPZ1a1BzbbXP7wg9243tPr6dqJ2qbUrLED6K2gJNalV5zOiGBAN53PFVpeOilJgXZM+5
asifbHN19nQgj1pdOFA+kMbH/X9Z/UWoqU13f53VhhHRaKmb3V0+xaqDQQ6aajE090v0B2TL6IGc
11sYGRUFDkaD8WygRUXr6BcxmBLccwIAAA==
headers:
Alt-Svc:
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Content-Encoding:
- gzip
Content-Type:
- application/json; charset=UTF-8
Date:
- Tue, 22 Apr 2025 14:25:35 GMT
Server:
- scaffolding on HTTPServer2
Server-Timing:
- gfet4t7; dur=2349
Transfer-Encoding:
- chunked
Vary:
- Origin
- X-Origin
- Referer
X-Content-Type-Options:
- nosniff
X-Frame-Options:
- SAMEORIGIN
X-XSS-Protection:
- '0'
status:
code: 200
message: OK
version: 1

View File

@@ -0,0 +1,101 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "What is the capital of France?"}],
"model": "gpt-4.1-mini-2025-04-14", "stop": []}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '125'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.68.2
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.68.2
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.12
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAAwAAAP//jJJPb9swDMXv/hSCznEQe+7S5LgAGzDs0P3paSgMRqJtZrIkSPTQoch3
H2Snsbt1wC4+8MdHv0fxKRNCkpZ7IVUHrHpv8nd3t4eIH77w4ePX+/b+8XP56bTdHE7dgb2Sq6Rw
xxMqflatleu9QSZnJ6wCAmOaWmyrmzflrqrejqB3Gk2StZ7zal3kPVnKy015k2+qvKgu8s6Rwij3
4nsmhBBP4zcZtRof5V5sVs+VHmOEFuX+2iSEDM6kioQYKTJYlqsZKmcZ7ej9W4dCgScGI1wj3gew
CgVFcQeB4nqpCtgMEZJ1OxizAGCtY0jRR78PF3K+OjSu9cEd4x9S2ZCl2NUBITqb3ER2Xo70nAnx
MG5ieBFO+uB6zzW7Hzj+rqimcXJ+gBneXhg7BjOXy3L1yrBaIwOZuFikVKA61LNy3joMmtwCZIvI
f3t5bfYUm2z7P+NnoBR6Rl37gJrUy7xzW8B0nf9qu654NCwjhp+ksGbCkJ5BYwODmU5Gxl+Rsa8b
si0GH2i6m8bX291xuztiVTQyO2e/AQAA//8DAP7WRo9GAwAA
headers:
CF-RAY:
- 93458dcf6d0ef53b-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 22 Apr 2025 13:44:07 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1391'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999989'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_74408ec81f430b6e9795cf5332262b8d
status:
code: 200
message: OK
version: 1

View File

@@ -0,0 +1,101 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "What is the capital of France?"}],
"model": "gpt-4.1-nano-2025-04-14", "stop": []}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '125'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.68.2
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.68.2
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.12
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAAwAAAP//jJJPb9swDMXv/hSCznEQuwrq5bgNBbZTh7aHYigMRqJtbbKkSXT/oMh3
L2Snsdt1wC4+8MdHv0fxOWOMa8V3jMsOSPbe5J8vqy/D96K/+PPjSn/Fh5szMewfb/eiar/d8lVS
uP0vlPSqWkvXe4OknZ2wDAiEaWpxLrZn5SchqhH0TqFJstZTLtZFbsG6vNyU23wj8kIc5Z3TEiPf
sZ8ZY4w9j99k1Cp85Du2Wb1WeowRWuS7UxNjPDiTKhxi1JHAEl/NUDpLaEfv1x0yCV4TGOYadhHA
SmQ6sksIOq6XqoDNECFZt4MxCwDWOoIUffR7dySHk0PjWh/cPr6T8kZbHbs6IERnk5tIzvORHjLG
7sZNDG/CcR9c76km9xvH3xViGsfnB5hhdWTkCMxcLsvVB8NqhQTaxMUiuQTZoZqV89ZhUNotQLaI
/LeXj2ZPsbVt/2f8DKRET6hqH1Bp+Tbv3BYwXee/2k4rHg3ziOFeS6xJY0jPoLCBwUwnw+NTJOzr
RtsWgw96upvG14gKq2ajxJZnh+wFAAD//wMATWCJPkYDAAA=
headers:
CF-RAY:
- 93458dd9aebff53b-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 22 Apr 2025 13:44:08 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '134'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999990'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_0ba738662e063fb55ea01793aafdcecc
status:
code: 200
message: OK
version: 1

View File

@@ -0,0 +1,101 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "What is the capital of France?"}],
"model": "gpt-4.1", "stop": []}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '109'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.68.2
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.68.2
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.12
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA4xSwYrbMBC9+yvEHEMcHMeh3dx2SwttoYTSW1nMRB7b2pUlIY27XZb8e5GdxM5u
C734MG/e83tP85IIAaqCnQDZIsvO6fRu//6Db26fnvTtx8/5t7v95rmT3y1+pc0XDcvIsIcHknxm
raTtnCZW1oyw9IRMUXX9rthu8pui2A5AZyvSkdY4TovVOs2zfJtmRbouTszWKkkBduJnIoQQL8M3
ejQV/YadyJbnSUchYEOwuywJAd7qOAEMQQVGw7CcQGkNkxls/2hJSHSKUQtbi08ejSShglgs9uhV
WCxWc6anug8YnZte6xmAxljGmHzwfH9CjheX2jbO20N4RYVaGRXa0hMGa6KjwNbBgB4TIe6HNvqr
gOC87RyXbB9p+N26GOVg6n8GnpoCtox6mudn0pVaWRGj0mHWJkiULVUTc6oe+0rZGZDMMr818zft
Mbcyzf/IT4CU5Jiq0nmqlLwOPK15itf5r7VLx4NhCOR/KUklK/LxHSqqsdfj3UB4DkxdWSvTkHde
jcdTuxJllh2yLMskJMfkDwAAAP//AwC4aq9JRgMAAA==
headers:
CF-RAY:
- 93458dcc1b9df53b-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 22 Apr 2025 13:44:06 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '296'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999989'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_7b4e1628a0608e9547e71e7857a29b58
status:
code: 200
message: OK
version: 1

View File

@@ -256,6 +256,52 @@ def test_validate_call_params_no_response_format():
llm._validate_call_params()
@pytest.mark.vcr(filter_headers=["authorization"], filter_query_parameters=["key"])
@pytest.mark.parametrize(
"model",
[
"gemini/gemini-2.0-flash-thinking-exp-01-21",
"gemini/gemini-2.0-flash-001",
"gemini/gemini-2.0-flash-lite-001",
"gemini/gemini-2.5-flash-preview-04-17",
"gemini/gemini-2.5-pro-exp-03-25",
],
)
def test_gemini_models(model):
llm = LLM(model=model)
result = llm.call("What is the capital of France?")
assert isinstance(result, str)
assert "Paris" in result
@pytest.mark.vcr(filter_headers=["authorization"], filter_query_parameters=["key"])
@pytest.mark.parametrize(
"model",
[
"gemini/gemma-3-1b-it",
"gemini/gemma-3-4b-it",
"gemini/gemma-3-12b-it",
"gemini/gemma-3-27b-it",
],
)
def test_gemma3(model):
llm = LLM(model=model)
result = llm.call("What is the capital of France?")
assert isinstance(result, str)
assert "Paris" in result
@pytest.mark.vcr(filter_headers=["authorization"])
@pytest.mark.parametrize(
"model", ["gpt-4.1", "gpt-4.1-mini-2025-04-14", "gpt-4.1-nano-2025-04-14"]
)
def test_gpt_4_1(model):
llm = LLM(model=model)
result = llm.call("What is the capital of France?")
assert isinstance(result, str)
assert "Paris" in result
@pytest.mark.vcr(filter_headers=["authorization"])
def test_o3_mini_reasoning_effort_high():
llm = LLM(