mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-07 02:59:05 +00:00
feat: add Pinstripes as an OpenAI-compatible provider (#30567)
* feat: add Pinstripes as an OpenAI-compatible provider Pinstripes (https://pinstripes.io) is an OpenAI-compatible inference provider serving open-source models (GLM-4.5-Air, Qwen3, DeepSeek, etc.) with per-token pricing and no subscriptions. Changes: - `litellm/llms/openai_like/providers.json`: register pinstripes with base_url, api_key_env, and max_completion_tokens→max_tokens mapping - `litellm/types/utils.py`: add `PINSTRIPES = "pinstripes"` to LlmProviders - `litellm/constants.py`: add to openai_compatible_providers and openai_compatible_endpoints lists - `litellm/litellm_core_utils/get_llm_provider_logic.py`: auto-detect provider when api_base is "https://pinstripes.io/v1" - `provider_endpoints_support.json`: document supported endpoints - `tests/`: 7 unit tests covering provider registration, resolution, URL auto-detection, api_base override, and Router config Usage: import litellm response = litellm.completion( model="pinstripes/ps/glm-4.5-air", messages=[{"role": "user", "content": "Hello"}], api_key=os.environ["PINSTRIPES_API_KEY"], ) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(pinstripes): resolve Greptile P1 review comments - Add api_base_env: PINSTRIPES_API_BASE to providers.json so env var override works - Set responses: false in provider_endpoints_support.json — not actually wired up - Remove docs/my-website/docs/providers/pinstripes.md — belongs in litellm-docs repo Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(pinstripes): add api_base_env and correct responses capability - Add api_base_env: PINSTRIPES_API_BASE to providers.json - Set responses: false in provider_endpoints_support.json Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(pinstripes): wire up Responses API — add supported_endpoints Adds supported_endpoints: ["/v1/chat/completions", "/v1/responses"] so JSONProviderRegistry.supports_responses_api returns true correctly, matching what provider_endpoints_support.json advertises. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * feat(pinstripes): enable embeddings endpoint Pinstripes serves nomic-embed-text-v1.5 and bge-m3 via /v1/embeddings. Add /v1/embeddings to supported_endpoints and set embeddings: true. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(pinstripes): use 4-space indentation in model_prices_and_context_window.json Matches the file's existing convention. Flagged by Greptile review. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(pinstripes): set a2a: false — A2A protocol not implemented All comparable JSON-configured providers (tensormesh, parasail, empiriolabs, libertai, neosantara) have a2a: false. Pinstripes does not implement the Google A2A protocol, so this should be false to match. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: inference_provider <max@redactedlab.com> Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
max-amos
GitHub
parent
cd4bd92c0a
commit
1fda0db66b
9 changed files with 277 additions and 0 deletions
|
|
@ -345,6 +345,7 @@ curl -X POST 'http://0.0.0.0:4000/v1/chat/completions' \
|
|||
| [OVHCloud AI Endpoints (`ovhcloud`)](https://docs.litellm.ai/docs/providers/ovhcloud) | ✅ | ✅ | ✅ | | | | | | | |
|
||||
| [Perplexity AI (`perplexity`)](https://docs.litellm.ai/docs/providers/perplexity) | ✅ | ✅ | ✅ | | | | | | | |
|
||||
| [Petals (`petals`)](https://docs.litellm.ai/docs/providers/petals) | ✅ | ✅ | ✅ | | | | | | | |
|
||||
| [Pinstripes (`pinstripes`)](https://docs.litellm.ai/docs/providers/pinstripes) | ✅ | ✅ | ✅ | | | | | | | |
|
||||
| [Predibase (`predibase`)](https://docs.litellm.ai/docs/providers/predibase) | ✅ | ✅ | ✅ | | | | | | | |
|
||||
| [Recraft (`recraft`)](https://docs.litellm.ai/docs/providers/recraft) | | | | | ✅ | | | | | |
|
||||
| [Replicate (`replicate`)](https://docs.litellm.ai/docs/providers/replicate) | ✅ | ✅ | ✅ | | | | | | | |
|
||||
|
|
|
|||
|
|
@ -802,6 +802,7 @@ openai_compatible_endpoints: List = [
|
|||
"https://api.inference.wandb.ai/v1",
|
||||
"https://api.clarifai.com/v2/ext/openai/v1",
|
||||
"https://api.libertai.io/v1",
|
||||
"https://pinstripes.io/v1",
|
||||
]
|
||||
|
||||
|
||||
|
|
@ -865,6 +866,7 @@ openai_compatible_providers: List = [
|
|||
"clarifai",
|
||||
"docker_model_runner",
|
||||
"ragflow",
|
||||
"pinstripes", # Pinstripes - JSON-configured provider
|
||||
]
|
||||
openai_text_completion_compatible_providers: List = (
|
||||
[ # providers that support `/v1/completions`
|
||||
|
|
|
|||
|
|
@ -388,6 +388,9 @@ def get_llm_provider(
|
|||
elif endpoint == "https://api.inference.wandb.ai/v1":
|
||||
custom_llm_provider = "wandb"
|
||||
dynamic_api_key = get_secret_str("WANDB_API_KEY")
|
||||
elif endpoint == "https://pinstripes.io/v1":
|
||||
custom_llm_provider = "pinstripes"
|
||||
dynamic_api_key = get_secret_str("PINSTRIPES_API_KEY")
|
||||
|
||||
if api_base is not None and not isinstance(api_base, str):
|
||||
raise Exception(
|
||||
|
|
|
|||
|
|
@ -159,5 +159,14 @@
|
|||
"max_completion_tokens": "max_tokens"
|
||||
},
|
||||
"supported_endpoints": ["/v1/chat/completions", "/v1/responses"]
|
||||
},
|
||||
"pinstripes": {
|
||||
"base_url": "https://pinstripes.io/v1",
|
||||
"api_key_env": "PINSTRIPES_API_KEY",
|
||||
"api_base_env": "PINSTRIPES_API_BASE",
|
||||
"param_mappings": {
|
||||
"max_completion_tokens": "max_tokens"
|
||||
},
|
||||
"supported_endpoints": ["/v1/chat/completions", "/v1/responses", "/v1/embeddings"]
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -3439,6 +3439,7 @@ class LlmProviders(str, Enum):
|
|||
XIAOMI_MIMO = "xiaomi_mimo"
|
||||
TENSORMESH = "tensormesh"
|
||||
LIBERTAI = "libertai"
|
||||
PINSTRIPES = "pinstripes"
|
||||
LITELLM_AGENT = "litellm_agent"
|
||||
CURSOR = "cursor"
|
||||
BEDROCK_MANTLE = "bedrock_mantle"
|
||||
|
|
|
|||
|
|
@ -43446,5 +43446,83 @@
|
|||
"supports_system_messages": true,
|
||||
"supports_tool_choice": true,
|
||||
"supports_vision": false
|
||||
},
|
||||
"pinstripes/ps/glm-4.5-air": {
|
||||
"max_tokens": 128000,
|
||||
"max_input_tokens": 128000,
|
||||
"max_output_tokens": 128000,
|
||||
"input_cost_per_token": 0.000000125,
|
||||
"output_cost_per_token": 0.00000045,
|
||||
"litellm_provider": "pinstripes",
|
||||
"mode": "chat",
|
||||
"supports_function_calling": true,
|
||||
"supports_assistant_prefill": true,
|
||||
"supports_reasoning": true,
|
||||
"source": "https://pinstripes.io/pricing"
|
||||
},
|
||||
"pinstripes/ps/qwen3.6-35b-a3b": {
|
||||
"max_tokens": 131072,
|
||||
"max_input_tokens": 131072,
|
||||
"max_output_tokens": 131072,
|
||||
"input_cost_per_token": 0.00000014,
|
||||
"output_cost_per_token": 0.00000045,
|
||||
"litellm_provider": "pinstripes",
|
||||
"mode": "chat",
|
||||
"supports_function_calling": true,
|
||||
"supports_assistant_prefill": true,
|
||||
"supports_reasoning": true,
|
||||
"source": "https://pinstripes.io/pricing"
|
||||
},
|
||||
"pinstripes/ps/qwen3-30b-a3b": {
|
||||
"max_tokens": 131072,
|
||||
"max_input_tokens": 131072,
|
||||
"max_output_tokens": 131072,
|
||||
"input_cost_per_token": 0.00000009,
|
||||
"output_cost_per_token": 0.0000002,
|
||||
"litellm_provider": "pinstripes",
|
||||
"mode": "chat",
|
||||
"supports_function_calling": true,
|
||||
"supports_assistant_prefill": true,
|
||||
"supports_reasoning": true,
|
||||
"source": "https://pinstripes.io/pricing"
|
||||
},
|
||||
"pinstripes/ps/qwen3-coder-30b-a3b": {
|
||||
"max_tokens": 131072,
|
||||
"max_input_tokens": 131072,
|
||||
"max_output_tokens": 131072,
|
||||
"input_cost_per_token": 0.0000003,
|
||||
"output_cost_per_token": 0.0000006,
|
||||
"litellm_provider": "pinstripes",
|
||||
"mode": "chat",
|
||||
"supports_function_calling": true,
|
||||
"supports_assistant_prefill": true,
|
||||
"supports_reasoning": false,
|
||||
"source": "https://pinstripes.io/pricing"
|
||||
},
|
||||
"pinstripes/ps/deepseek-v4-flash": {
|
||||
"max_tokens": 163840,
|
||||
"max_input_tokens": 163840,
|
||||
"max_output_tokens": 163840,
|
||||
"input_cost_per_token": 0.0000001,
|
||||
"output_cost_per_token": 0.0000002,
|
||||
"litellm_provider": "pinstripes",
|
||||
"mode": "chat",
|
||||
"supports_function_calling": true,
|
||||
"supports_assistant_prefill": true,
|
||||
"supports_reasoning": true,
|
||||
"source": "https://pinstripes.io/pricing"
|
||||
},
|
||||
"pinstripes/ps/minimax-m2.7": {
|
||||
"max_tokens": 1000192,
|
||||
"max_input_tokens": 1000192,
|
||||
"max_output_tokens": 1000192,
|
||||
"input_cost_per_token": 0.000000255,
|
||||
"output_cost_per_token": 0.00000055,
|
||||
"litellm_provider": "pinstripes",
|
||||
"mode": "chat",
|
||||
"supports_function_calling": true,
|
||||
"supports_assistant_prefill": true,
|
||||
"supports_reasoning": false,
|
||||
"source": "https://pinstripes.io/pricing"
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1940,6 +1940,23 @@
|
|||
"interactions": true
|
||||
}
|
||||
},
|
||||
"pinstripes": {
|
||||
"display_name": "Pinstripes (`pinstripes`)",
|
||||
"url": "https://docs.litellm.ai/docs/providers/pinstripes",
|
||||
"endpoints": {
|
||||
"chat_completions": true,
|
||||
"messages": true,
|
||||
"responses": true,
|
||||
"embeddings": true,
|
||||
"image_generations": false,
|
||||
"audio_transcriptions": false,
|
||||
"audio_speech": false,
|
||||
"moderations": false,
|
||||
"batches": false,
|
||||
"rerank": false,
|
||||
"a2a": false
|
||||
}
|
||||
},
|
||||
"poe": {
|
||||
"display_name": "Poe (`poe`)",
|
||||
"endpoints": {
|
||||
|
|
|
|||
|
|
@ -175,6 +175,75 @@ class TestJSONProviderLoader:
|
|||
assert config.custom_llm_provider == "publicai"
|
||||
|
||||
|
||||
class TestPinstripes:
|
||||
"""Tests for Pinstripes JSON-configured provider"""
|
||||
|
||||
def test_pinstripes_json_config_exists(self):
|
||||
"""Test that pinstripes is configured in providers.json"""
|
||||
from litellm.llms.openai_like.json_loader import JSONProviderRegistry
|
||||
|
||||
assert JSONProviderRegistry.exists("pinstripes")
|
||||
|
||||
pinstripes = JSONProviderRegistry.get("pinstripes")
|
||||
assert pinstripes is not None
|
||||
assert pinstripes.base_url == "https://pinstripes.io/v1"
|
||||
assert pinstripes.api_key_env == "PINSTRIPES_API_KEY"
|
||||
assert pinstripes.param_mappings.get("max_completion_tokens") == "max_tokens"
|
||||
|
||||
def test_pinstripes_provider_resolution(self):
|
||||
"""Test that provider resolution finds pinstripes and returns the default base URL"""
|
||||
from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
|
||||
|
||||
model, provider, api_key, api_base = get_llm_provider(
|
||||
model="pinstripes/ps/glm-4.5-air",
|
||||
custom_llm_provider=None,
|
||||
api_base=None,
|
||||
api_key=None,
|
||||
)
|
||||
|
||||
assert model == "ps/glm-4.5-air"
|
||||
assert provider == "pinstripes"
|
||||
assert api_base == "https://pinstripes.io/v1"
|
||||
|
||||
def test_pinstripes_dynamic_config(self):
|
||||
"""Test dynamic config class creation for pinstripes"""
|
||||
from litellm.llms.openai_like.dynamic_config import create_config_class
|
||||
from litellm.llms.openai_like.json_loader import JSONProviderRegistry
|
||||
|
||||
provider = JSONProviderRegistry.get("pinstripes")
|
||||
config_class = create_config_class(provider)
|
||||
config = config_class()
|
||||
|
||||
api_base, api_key = config._get_openai_compatible_provider_info(None, None)
|
||||
assert api_base == "https://pinstripes.io/v1"
|
||||
|
||||
api_base, api_key = config._get_openai_compatible_provider_info(
|
||||
"https://custom.pinstripes.io/v1", "test-key"
|
||||
)
|
||||
assert api_base == "https://custom.pinstripes.io/v1"
|
||||
assert api_key == "test-key"
|
||||
|
||||
def test_pinstripes_parameter_mapping(self):
|
||||
"""Test that max_completion_tokens is mapped to max_tokens for pinstripes"""
|
||||
from litellm.llms.openai_like.dynamic_config import create_config_class
|
||||
from litellm.llms.openai_like.json_loader import JSONProviderRegistry
|
||||
|
||||
provider = JSONProviderRegistry.get("pinstripes")
|
||||
config_class = create_config_class(provider)
|
||||
config = config_class()
|
||||
|
||||
optional_params = {}
|
||||
non_default_params = {"max_completion_tokens": 100, "temperature": 0.7}
|
||||
result = config.map_openai_params(
|
||||
non_default_params, optional_params, "ps/glm-4.5-air", False
|
||||
)
|
||||
|
||||
assert "max_tokens" in result
|
||||
assert result["max_tokens"] == 100
|
||||
assert "max_completion_tokens" not in result
|
||||
assert result["temperature"] == 0.7
|
||||
|
||||
|
||||
class TestPublicAIIntegration:
|
||||
"""Integration tests for PublicAI provider"""
|
||||
|
||||
|
|
|
|||
|
|
@ -0,0 +1,97 @@
|
|||
"""
|
||||
Tests for Pinstripes provider configuration and integration.
|
||||
"""
|
||||
|
||||
import litellm
|
||||
|
||||
|
||||
class TestPinstripeProviderConfig:
|
||||
"""Test Pinstripes provider configuration"""
|
||||
|
||||
def test_pinstripes_in_provider_list(self):
|
||||
"""Test that pinstripes is in the provider list"""
|
||||
from litellm import LlmProviders
|
||||
|
||||
assert hasattr(LlmProviders, "PINSTRIPES")
|
||||
assert LlmProviders.PINSTRIPES.value == "pinstripes"
|
||||
assert "pinstripes" in litellm.provider_list
|
||||
|
||||
def test_pinstripes_json_config_exists(self):
|
||||
"""Test that pinstripes is configured in providers.json"""
|
||||
from litellm.llms.openai_like.json_loader import JSONProviderRegistry
|
||||
|
||||
assert JSONProviderRegistry.exists("pinstripes")
|
||||
|
||||
pinstripes = JSONProviderRegistry.get("pinstripes")
|
||||
assert pinstripes is not None
|
||||
assert pinstripes.base_url == "https://pinstripes.io/v1"
|
||||
assert pinstripes.api_key_env == "PINSTRIPES_API_KEY"
|
||||
assert pinstripes.param_mappings.get("max_completion_tokens") == "max_tokens"
|
||||
|
||||
def test_pinstripes_in_openai_compatible_providers(self):
|
||||
"""Test that pinstripes is in the openai_compatible_providers list"""
|
||||
from litellm.constants import openai_compatible_providers
|
||||
|
||||
assert "pinstripes" in openai_compatible_providers
|
||||
|
||||
def test_pinstripes_provider_resolution(self):
|
||||
"""Test that provider resolution finds pinstripes and returns the default base URL"""
|
||||
from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
|
||||
|
||||
model, provider, api_key, api_base = get_llm_provider(
|
||||
model="pinstripes/ps/glm-4.5-air",
|
||||
custom_llm_provider=None,
|
||||
api_base=None,
|
||||
api_key=None,
|
||||
)
|
||||
|
||||
assert model == "ps/glm-4.5-air"
|
||||
assert provider == "pinstripes"
|
||||
assert api_base == "https://pinstripes.io/v1"
|
||||
|
||||
def test_pinstripes_api_base_override(self):
|
||||
"""Test that an explicit api_base / api_key overrides the default"""
|
||||
from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
|
||||
|
||||
model, provider, api_key, api_base = get_llm_provider(
|
||||
model="pinstripes/ps/glm-4.5-air",
|
||||
custom_llm_provider=None,
|
||||
api_base="https://custom.pinstripes.io/v1",
|
||||
api_key="sk-test",
|
||||
)
|
||||
|
||||
assert provider == "pinstripes"
|
||||
assert api_base == "https://custom.pinstripes.io/v1"
|
||||
assert api_key == "sk-test"
|
||||
|
||||
def test_pinstripes_url_autodetection(self):
|
||||
"""Test that api_base=pinstripes.io/v1 auto-sets custom_llm_provider=pinstripes"""
|
||||
from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
|
||||
|
||||
model, provider, api_key, api_base = get_llm_provider(
|
||||
model="ps/glm-4.5-air",
|
||||
custom_llm_provider=None,
|
||||
api_base="https://pinstripes.io/v1",
|
||||
api_key=None,
|
||||
)
|
||||
assert provider == "pinstripes"
|
||||
assert api_base == "https://pinstripes.io/v1"
|
||||
|
||||
def test_pinstripes_router_config(self):
|
||||
"""Test that pinstripes can be used in Router configuration"""
|
||||
from litellm import Router
|
||||
|
||||
router = Router(
|
||||
model_list=[
|
||||
{
|
||||
"model_name": "pinstripes-chat",
|
||||
"litellm_params": {
|
||||
"model": "pinstripes/ps/glm-4.5-air",
|
||||
"api_key": "test-key",
|
||||
},
|
||||
}
|
||||
]
|
||||
)
|
||||
|
||||
assert len(router.model_list) == 1
|
||||
assert router.model_list[0]["model_name"] == "pinstripes-chat"
|
||||
Loading…
Add table
Reference in a new issue