webscout 8.3.7__py3-none-any.whl → 2025.10.11__py3-none-any.whl

webscout/Provider/OPENAI/deepinfra.py

@@ -1,315 +1,319 @@
-import requests
-import json
-import time
-import uuid
-import collections
-from typing import List, Dict, Optional, Union, Generator, Any
-
-from webscout.Provider.OPENAI.base import OpenAICompatibleProvider, BaseChat, BaseCompletions
-from webscout.Provider.OPENAI.utils import (
-    ChatCompletionChunk, ChatCompletion, Choice, ChoiceDelta,
-    ChatCompletionMessage, CompletionUsage
-)
-
-try:
-    from webscout.litagent import LitAgent
-except ImportError:
-    pass
-
-class Completions(BaseCompletions):
-    def __init__(self, client: 'DeepInfra'):
-        self._client = client
-
-    def create(
-        self,
-        *,
-        model: str,
-        messages: List[Dict[str, str]],
-        max_tokens: Optional[int] = 2049,
-        stream: bool = False,
-        temperature: Optional[float] = None,
-        top_p: Optional[float] = None,
-        timeout: Optional[int] = None,
-        proxies: Optional[Dict[str, str]] = None,
-        **kwargs: Any
-    ) -> Union[ChatCompletion, Generator[ChatCompletionChunk, None, None]]:
-        payload = {
-            "model": model,
-            "messages": messages,
-            "max_tokens": max_tokens,
-            "stream": stream,
-        }
-        if temperature is not None:
-            payload["temperature"] = temperature
-        if top_p is not None:
-            payload["top_p"] = top_p
-        payload.update(kwargs)
-        request_id = f"chatcmpl-{uuid.uuid4()}"
-        created_time = int(time.time())
-        if stream:
-            return self._create_stream(request_id, created_time, model, payload, timeout, proxies)
-        else:
-            return self._create_non_stream(request_id, created_time, model, payload, timeout, proxies)
-
-    def _create_stream(
-        self, request_id: str, created_time: int, model: str, payload: Dict[str, Any],
-        timeout: Optional[int] = None, proxies: Optional[Dict[str, str]] = None
-    ) -> Generator[ChatCompletionChunk, None, None]:
-        try:
-            response = self._client.session.post(
-                self._client.base_url,
-                headers=self._client.headers,
-                json=payload,
-                stream=True,
-                timeout=timeout or self._client.timeout,
-                proxies=proxies
-            )
-            response.raise_for_status()
-            prompt_tokens = 0
-            completion_tokens = 0
-            total_tokens = 0
-            for line in response.iter_lines(decode_unicode=True):
-                if line:
-                    if line.startswith("data: "):
-                        json_str = line[6:]
-                        if json_str == "[DONE]":
-                            break
-                        try:
-                            data = json.loads(json_str)
-                            choice_data = data.get('choices', [{}])[0]
-                            delta_data = choice_data.get('delta', {})
-                            finish_reason = choice_data.get('finish_reason')
-                            usage_data = data.get('usage', {})
-                            if usage_data:
-                                prompt_tokens = usage_data.get('prompt_tokens', prompt_tokens)
-                                completion_tokens = usage_data.get('completion_tokens', completion_tokens)
-                                total_tokens = usage_data.get('total_tokens', total_tokens)
-                            if delta_data.get('content'):
-                                completion_tokens += 1
-                                total_tokens = prompt_tokens + completion_tokens
-                            delta = ChoiceDelta(
-                                content=delta_data.get('content'),
-                                role=delta_data.get('role'),
-                                tool_calls=delta_data.get('tool_calls')
-                            )
-                            choice = Choice(
-                                index=choice_data.get('index', 0),
-                                delta=delta,
-                                finish_reason=finish_reason,
-                                logprobs=choice_data.get('logprobs')
-                            )
-                            chunk = ChatCompletionChunk(
-                                id=request_id,
-                                choices=[choice],
-                                created=created_time,
-                                model=model,
-                                system_fingerprint=data.get('system_fingerprint')
-                            )
-                            chunk.usage = {
-                                "prompt_tokens": prompt_tokens,
-                                "completion_tokens": completion_tokens,
-                                "total_tokens": total_tokens,
-                                "estimated_cost": None
-                            }
-                            yield chunk
-                        except json.JSONDecodeError:
-                            continue
-            # Final chunk with finish_reason="stop"
-            delta = ChoiceDelta(content=None, role=None, tool_calls=None)
-            choice = Choice(index=0, delta=delta, finish_reason="stop", logprobs=None)
-            chunk = ChatCompletionChunk(
-                id=request_id,
-                choices=[choice],
-                created=created_time,
-                model=model,
-                system_fingerprint=None
-            )
-            chunk.usage = {
-                "prompt_tokens": prompt_tokens,
-                "completion_tokens": completion_tokens,
-                "total_tokens": total_tokens,
-                "estimated_cost": None
-            }
-            yield chunk
-        except Exception as e:
-            print(f"Error during DeepInfra stream request: {e}")
-            raise IOError(f"DeepInfra request failed: {e}") from e
-
-    def _create_non_stream(
-        self, request_id: str, created_time: int, model: str, payload: Dict[str, Any],
-        timeout: Optional[int] = None, proxies: Optional[Dict[str, str]] = None
-    ) -> ChatCompletion:
-        try:
-            response = self._client.session.post(
-                self._client.base_url,
-                headers=self._client.headers,
-                json=payload,
-                timeout=timeout or self._client.timeout,
-                proxies=proxies
-            )
-            response.raise_for_status()
-            data = response.json()
-            choices_data = data.get('choices', [])
-            usage_data = data.get('usage', {})
-            choices = []
-            for choice_d in choices_data:
-                message_d = choice_d.get('message')
-                if not message_d and 'delta' in choice_d:
-                    delta = choice_d['delta']
-                    message_d = {
-                        'role': delta.get('role', 'assistant'),
-                        'content': delta.get('content', '')
-                    }
-                if not message_d:
-                    message_d = {'role': 'assistant', 'content': ''}
-                message = ChatCompletionMessage(
-                    role=message_d.get('role', 'assistant'),
-                    content=message_d.get('content', '')
-                )
-                choice = Choice(
-                    index=choice_d.get('index', 0),
-                    message=message,
-                    finish_reason=choice_d.get('finish_reason', 'stop')
-                )
-                choices.append(choice)
-            usage = CompletionUsage(
-                prompt_tokens=usage_data.get('prompt_tokens', 0),
-                completion_tokens=usage_data.get('completion_tokens', 0),
-                total_tokens=usage_data.get('total_tokens', 0)
-            )
-            completion = ChatCompletion(
-                id=request_id,
-                choices=choices,
-                created=created_time,
-                model=data.get('model', model),
-                usage=usage,
-            )
-            return completion
-        except Exception as e:
-            print(f"Error during DeepInfra non-stream request: {e}")
-            raise IOError(f"DeepInfra request failed: {e}") from e
-
-class Chat(BaseChat):
-    def __init__(self, client: 'DeepInfra'):
-        self.completions = Completions(client)
-
-class DeepInfra(OpenAICompatibleProvider):
-    AVAILABLE_MODELS = [
-        "moonshotai/Kimi-K2-Instruct",
-        "Qwen/Qwen3-Next-80B-A3B-Instruct",
-        "Qwen/Qwen3-Next-80B-A3B-Thinking",
-        "moonshotai/Kimi-K2-Instruct-0905",
-        "deepseek-ai/DeepSeek-R1-0528-Turbo",
-        "Qwen/Qwen3-235B-A22B-Thinking-2507",
-        "Qwen/Qwen3-Coder-480B-A35B-Instruct",
-        "Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo",
-        "Qwen/Qwen3-235B-A22B-Instruct-2507",
-        "Qwen/Qwen3-235B-A22B",
-        "Qwen/Qwen3-30B-A3B",
-        "Qwen/Qwen3-32B",
-        "Qwen/Qwen3-14B",
-        "deepseek-ai/DeepSeek-V3-0324-Turbo",
-        "deepseek-ai/DeepSeek-Prover-V2-671B",
-        "meta-llama/Llama-4-Maverick-17B-128E-Instruct-Turbo",
-        "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
-        "meta-llama/Llama-4-Scout-17B-16E-Instruct",
-        "deepseek-ai/DeepSeek-R1-0528",
-        "deepseek-ai/DeepSeek-V3-0324",
-        "mistralai/Mistral-Small-3.1-24B-Instruct-2503",
-        "microsoft/phi-4-reasoning-plus",
-        "Qwen/QwQ-32B",
-        "google/gemma-3-27b-it",
-        "google/gemma-3-12b-it",
-        "google/gemma-3-4b-it",
-        "microsoft/Phi-4-multimodal-instruct",
-        "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
-        "deepseek-ai/DeepSeek-V3",
-        "deepseek-ai/DeepSeek-V3.1",
-        "meta-llama/Llama-3.3-70B-Instruct-Turbo",
-        "meta-llama/Llama-3.3-70B-Instruct",
-        "microsoft/phi-4",
-        "Gryphe/MythoMax-L2-13b",
-        "NousResearch/Hermes-3-Llama-3.1-405B",
-        "NousResearch/Hermes-3-Llama-3.1-70B",
-        "NovaSky-AI/Sky-T1-32B-Preview",
-        "Qwen/Qwen2.5-72B-Instruct",
-        "Qwen/Qwen2.5-7B-Instruct",
-        "Qwen/Qwen2.5-Coder-32B-Instruct",
-        "Sao10K/L3-8B-Lunaris-v1-Turbo",
-        "Sao10K/L3.1-70B-Euryale-v2.2",
-        "Sao10K/L3.3-70B-Euryale-v2.3",
-        "deepseek-ai/DeepSeek-R1",
-        "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
-        "deepseek-ai/DeepSeek-R1-Turbo",
-        "google/gemini-2.0-flash-001",
-        "meta-llama/Llama-3.2-11B-Vision-Instruct",
-        "meta-llama/Llama-3.2-1B-Instruct",
-        "meta-llama/Llama-3.2-3B-Instruct",
-        "meta-llama/Llama-3.2-90B-Vision-Instruct",
-        "meta-llama/Meta-Llama-3-70B-Instruct",
-        "meta-llama/Meta-Llama-3-8B-Instruct",
-        "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
-        "meta-llama/Meta-Llama-3.1-8B-Instruct",
-        "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
-        "microsoft/WizardLM-2-8x22B",
-        "mistralai/Devstral-Small-2505",
-        "mistralai/Devstral-Small-2507",
-        "mistralai/Mistral-7B-Instruct-v0.3",
-        "mistralai/Mistral-Nemo-Instruct-2407",
-        "mistralai/Mistral-Small-24B-Instruct-2501",
-        "mistralai/Mistral-Small-3.2-24B-Instruct-2506",
-        "mistralai/Mixtral-8x7B-Instruct-v0.1",
-        "nvidia/Llama-3.1-Nemotron-70B-Instruct",
-        "zai-org/GLM-4.5-Air",
-        "zai-org/GLM-4.5",
-        "zai-org/GLM-4.5V",
-        "openai/gpt-oss-120b",
-        "openai/gpt-oss-20b",
-        "allenai/olmOCR-7B-0725-FP8",
-    ]
-
-    def __init__(self, browser: str = "chrome", api_key: str = None):
-        self.timeout = None
-        self.base_url = "https://api.deepinfra.com/v1/openai/chat/completions"
-        self.session = requests.Session()
-        agent = LitAgent()
-        fingerprint = agent.generate_fingerprint(browser)
-        self.headers = {
-            "Accept": fingerprint["accept"],
-            "Accept-Encoding": "gzip, deflate, br, zstd",
-            "Accept-Language": fingerprint["accept_language"],
-            "Content-Type": "application/json",
-            "Cache-Control": "no-cache",
-            "Connection": "keep-alive",
-            "Origin": "https://deepinfra.com",
-            "Pragma": "no-cache",
-            "Referer": "https://deepinfra.com/",
-            "Sec-Fetch-Dest": "empty",
-            "Sec-Fetch-Mode": "cors",
-            "Sec-Fetch-Site": "same-site",
-            "X-Deepinfra-Source": "web-embed",
-            "Sec-CH-UA": fingerprint["sec_ch_ua"] or '"Not)A;Brand";v="99", "Microsoft Edge";v="127", "Chromium";v="127"',
-            "Sec-CH-UA-Mobile": "?0",
-            "Sec-CH-UA-Platform": f'"{fingerprint["platform"]}"',
-            "User-Agent": fingerprint["user_agent"],
-        }
-        if api_key is not None:
-            self.headers["Authorization"] = f"Bearer {api_key}"
-        self.session.headers.update(self.headers)
-        self.chat = Chat(self)
-    @property
-    def models(self):
-        class _ModelList:
-            def list(inner_self):
-                return type(self).AVAILABLE_MODELS
-        return _ModelList()
-
-if __name__ == "__main__":
-    client = DeepInfra()
-    response = client.chat.completions.create(
-        model="deepseek-ai/DeepSeek-R1-0528",
-        messages=[{"role": "user", "content": "Hello, how are you?"}],
-        max_tokens=10000,
-        stream=False
-    )
+import requests
+import json
+import time
+import uuid
+import collections
+from typing import List, Dict, Optional, Union, Generator, Any
+
+from webscout.Provider.OPENAI.base import OpenAICompatibleProvider, BaseChat, BaseCompletions
+from webscout.Provider.OPENAI.utils import (
+    ChatCompletionChunk, ChatCompletion, Choice, ChoiceDelta,
+    ChatCompletionMessage, CompletionUsage
+)
+
+try:
+    from webscout.litagent import LitAgent
+except ImportError:
+    pass
+
+class Completions(BaseCompletions):
+    def __init__(self, client: 'DeepInfra'):
+        self._client = client
+
+    def create(
+        self,
+        *,
+        model: str,
+        messages: List[Dict[str, str]],
+        max_tokens: Optional[int] = 2049,
+        stream: bool = False,
+        temperature: Optional[float] = None,
+        top_p: Optional[float] = None,
+        timeout: Optional[int] = None,
+        proxies: Optional[Dict[str, str]] = None,
+        **kwargs: Any
+    ) -> Union[ChatCompletion, Generator[ChatCompletionChunk, None, None]]:
+        payload = {
+            "model": model,
+            "messages": messages,
+            "max_tokens": max_tokens,
+            "stream": stream,
+        }
+        if temperature is not None:
+            payload["temperature"] = temperature
+        if top_p is not None:
+            payload["top_p"] = top_p
+        payload.update(kwargs)
+        request_id = f"chatcmpl-{uuid.uuid4()}"
+        created_time = int(time.time())
+        if stream:
+            return self._create_stream(request_id, created_time, model, payload, timeout, proxies)
+        else:
+            return self._create_non_stream(request_id, created_time, model, payload, timeout, proxies)
+
+    def _create_stream(
+        self, request_id: str, created_time: int, model: str, payload: Dict[str, Any],
+        timeout: Optional[int] = None, proxies: Optional[Dict[str, str]] = None
+    ) -> Generator[ChatCompletionChunk, None, None]:
+        try:
+            response = self._client.session.post(
+                self._client.base_url,
+                headers=self._client.headers,
+                json=payload,
+                stream=True,
+                timeout=timeout or self._client.timeout,
+                proxies=proxies
+            )
+            response.raise_for_status()
+            prompt_tokens = 0
+            completion_tokens = 0
+            total_tokens = 0
+            for line in response.iter_lines(decode_unicode=True):
+                if line:
+                    if line.startswith("data: "):
+                        json_str = line[6:]
+                        if json_str == "[DONE]":
+                            break
+                        try:
+                            data = json.loads(json_str)
+                            choice_data = data.get('choices', [{}])[0]
+                            delta_data = choice_data.get('delta', {})
+                            finish_reason = choice_data.get('finish_reason')
+                            usage_data = data.get('usage', {})
+                            if usage_data:
+                                prompt_tokens = usage_data.get('prompt_tokens', prompt_tokens)
+                                completion_tokens = usage_data.get('completion_tokens', completion_tokens)
+                                total_tokens = usage_data.get('total_tokens', total_tokens)
+                            if delta_data.get('content'):
+                                completion_tokens += 1
+                                total_tokens = prompt_tokens + completion_tokens
+                            delta = ChoiceDelta(
+                                content=delta_data.get('content'),
+                                role=delta_data.get('role'),
+                                tool_calls=delta_data.get('tool_calls')
+                            )
+                            choice = Choice(
+                                index=choice_data.get('index', 0),
+                                delta=delta,
+                                finish_reason=finish_reason,
+                                logprobs=choice_data.get('logprobs')
+                            )
+                            chunk = ChatCompletionChunk(
+                                id=request_id,
+                                choices=[choice],
+                                created=created_time,
+                                model=model,
+                                system_fingerprint=data.get('system_fingerprint')
+                            )
+                            chunk.usage = {
+                                "prompt_tokens": prompt_tokens,
+                                "completion_tokens": completion_tokens,
+                                "total_tokens": total_tokens,
+                                "estimated_cost": None
+                            }
+                            yield chunk
+                        except json.JSONDecodeError:
+                            continue
+            # Final chunk with finish_reason="stop"
+            delta = ChoiceDelta(content=None, role=None, tool_calls=None)
+            choice = Choice(index=0, delta=delta, finish_reason="stop", logprobs=None)
+            chunk = ChatCompletionChunk(
+                id=request_id,
+                choices=[choice],
+                created=created_time,
+                model=model,
+                system_fingerprint=None
+            )
+            chunk.usage = {
+                "prompt_tokens": prompt_tokens,
+                "completion_tokens": completion_tokens,
+                "total_tokens": total_tokens,
+                "estimated_cost": None
+            }
+            yield chunk
+        except Exception as e:
+            print(f"Error during DeepInfra stream request: {e}")
+            raise IOError(f"DeepInfra request failed: {e}") from e
+
+    def _create_non_stream(
+        self, request_id: str, created_time: int, model: str, payload: Dict[str, Any],
+        timeout: Optional[int] = None, proxies: Optional[Dict[str, str]] = None
+    ) -> ChatCompletion:
+        try:
+            response = self._client.session.post(
+                self._client.base_url,
+                headers=self._client.headers,
+                json=payload,
+                timeout=timeout or self._client.timeout,
+                proxies=proxies
+            )
+            response.raise_for_status()
+            data = response.json()
+            choices_data = data.get('choices', [])
+            usage_data = data.get('usage', {})
+            choices = []
+            for choice_d in choices_data:
+                message_d = choice_d.get('message')
+                if not message_d and 'delta' in choice_d:
+                    delta = choice_d['delta']
+                    message_d = {
+                        'role': delta.get('role', 'assistant'),
+                        'content': delta.get('content', '')
+                    }
+                if not message_d:
+                    message_d = {'role': 'assistant', 'content': ''}
+                message = ChatCompletionMessage(
+                    role=message_d.get('role', 'assistant'),
+                    content=message_d.get('content', '')
+                )
+                choice = Choice(
+                    index=choice_d.get('index', 0),
+                    message=message,
+                    finish_reason=choice_d.get('finish_reason', 'stop')
+                )
+                choices.append(choice)
+            usage = CompletionUsage(
+                prompt_tokens=usage_data.get('prompt_tokens', 0),
+                completion_tokens=usage_data.get('completion_tokens', 0),
+                total_tokens=usage_data.get('total_tokens', 0)
+            )
+            completion = ChatCompletion(
+                id=request_id,
+                choices=choices,
+                created=created_time,
+                model=data.get('model', model),
+                usage=usage,
+            )
+            return completion
+        except Exception as e:
+            print(f"Error during DeepInfra non-stream request: {e}")
+            raise IOError(f"DeepInfra request failed: {e}") from e
+
+class Chat(BaseChat):
+    def __init__(self, client: 'DeepInfra'):
+        self.completions = Completions(client)
+
+class DeepInfra(OpenAICompatibleProvider):
+    AVAILABLE_MODELS = [
+        "moonshotai/Kimi-K2-Instruct",
+        "Qwen/Qwen3-Next-80B-A3B-Instruct",
+        "Qwen/Qwen3-Next-80B-A3B-Thinking",
+        "moonshotai/Kimi-K2-Instruct-0905",
+        "Qwen/Qwen3-Coder-30B-A3B-Instruct",
+        "deepseek-ai/DeepSeek-R1-0528-Turbo",
+        "Qwen/Qwen3-235B-A22B-Thinking-2507",
+        "deepseek-ai/DeepSeek-V3.1-Terminus",
+        "deepseek-ai/DeepSeek-V3.2-Exp",
+        "Qwen/Qwen3-Coder-480B-A35B-Instruct",
+        "Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo",
+        "Qwen/Qwen3-235B-A22B-Instruct-2507",
+        "Qwen/Qwen3-235B-A22B",
+        "Qwen/Qwen3-30B-A3B",
+        "Qwen/Qwen3-32B",
+        "Qwen/Qwen3-14B",
+        "deepseek-ai/DeepSeek-V3-0324-Turbo",
+        "deepseek-ai/DeepSeek-Prover-V2-671B",
+        "meta-llama/Llama-4-Maverick-17B-128E-Instruct-Turbo",
+        "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
+        "meta-llama/Llama-4-Scout-17B-16E-Instruct",
+        "deepseek-ai/DeepSeek-R1-0528",
+        "deepseek-ai/DeepSeek-V3-0324",
+        "mistralai/Mistral-Small-3.1-24B-Instruct-2503",
+        "microsoft/phi-4-reasoning-plus",
+        "Qwen/QwQ-32B",
+        "google/gemma-3-27b-it",
+        "google/gemma-3-12b-it",
+        "google/gemma-3-4b-it",
+        "microsoft/Phi-4-multimodal-instruct",
+        "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
+        "deepseek-ai/DeepSeek-V3",
+        "deepseek-ai/DeepSeek-V3.1",
+        "meta-llama/Llama-3.3-70B-Instruct-Turbo",
+        "meta-llama/Llama-3.3-70B-Instruct",
+        "microsoft/phi-4",
+        "Gryphe/MythoMax-L2-13b",
+        "NousResearch/Hermes-3-Llama-3.1-405B",
+        "NousResearch/Hermes-3-Llama-3.1-70B",
+        "NovaSky-AI/Sky-T1-32B-Preview",
+        "Qwen/Qwen2.5-72B-Instruct",
+        "Qwen/Qwen2.5-7B-Instruct",
+        "Qwen/Qwen2.5-Coder-32B-Instruct",
+        "Sao10K/L3-8B-Lunaris-v1-Turbo",
+        "Sao10K/L3.1-70B-Euryale-v2.2",
+        "Sao10K/L3.3-70B-Euryale-v2.3",
+        "deepseek-ai/DeepSeek-R1",
+        "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
+        "deepseek-ai/DeepSeek-R1-Turbo",
+        "google/gemini-2.0-flash-001",
+        "meta-llama/Llama-3.2-11B-Vision-Instruct",
+        "meta-llama/Llama-3.2-1B-Instruct",
+        "meta-llama/Llama-3.2-3B-Instruct",
+        "meta-llama/Llama-3.2-90B-Vision-Instruct",
+        "meta-llama/Meta-Llama-3-70B-Instruct",
+        "meta-llama/Meta-Llama-3-8B-Instruct",
+        "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
+        "meta-llama/Meta-Llama-3.1-8B-Instruct",
+        "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
+        "microsoft/WizardLM-2-8x22B",
+        "mistralai/Devstral-Small-2505",
+        "mistralai/Devstral-Small-2507",
+        "mistralai/Mistral-7B-Instruct-v0.3",
+        "mistralai/Mistral-Nemo-Instruct-2407",
+        "mistralai/Mistral-Small-24B-Instruct-2501",
+        "mistralai/Mistral-Small-3.2-24B-Instruct-2506",
+        "mistralai/Mixtral-8x7B-Instruct-v0.1",
+        "nvidia/Llama-3.1-Nemotron-70B-Instruct",
+        "zai-org/GLM-4.5-Air",
+        "zai-org/GLM-4.5",
+        "zai-org/GLM-4.5V",
+        "zai-org/GLM-4.6",
+        "openai/gpt-oss-120b",
+        "openai/gpt-oss-20b",
+        "allenai/olmOCR-7B-0725-FP8",
+    ]
+
+    def __init__(self, browser: str = "chrome", api_key: str = None):
+        self.timeout = None
+        self.base_url = "https://api.deepinfra.com/v1/openai/chat/completions"
+        self.session = requests.Session()
+        agent = LitAgent()
+        fingerprint = agent.generate_fingerprint(browser)
+        self.headers = {
+            "Accept": fingerprint["accept"],
+            "Accept-Encoding": "gzip, deflate, br, zstd",
+            "Accept-Language": fingerprint["accept_language"],
+            "Content-Type": "application/json",
+            "Cache-Control": "no-cache",
+            "Connection": "keep-alive",
+            "Origin": "https://deepinfra.com",
+            "Pragma": "no-cache",
+            "Referer": "https://deepinfra.com/",
+            "Sec-Fetch-Dest": "empty",
+            "Sec-Fetch-Mode": "cors",
+            "Sec-Fetch-Site": "same-site",
+            "X-Deepinfra-Source": "web-embed",
+            "Sec-CH-UA": fingerprint["sec_ch_ua"] or '"Not)A;Brand";v="99", "Microsoft Edge";v="127", "Chromium";v="127"',
+            "Sec-CH-UA-Mobile": "?0",
+            "Sec-CH-UA-Platform": f'"{fingerprint["platform"]}"',
+            "User-Agent": fingerprint["user_agent"],
+        }
+        if api_key is not None:
+            self.headers["Authorization"] = f"Bearer {api_key}"
+        self.session.headers.update(self.headers)
+        self.chat = Chat(self)
+    @property
+    def models(self):
+        class _ModelList:
+            def list(inner_self):
+                return type(self).AVAILABLE_MODELS
+        return _ModelList()
+
+if __name__ == "__main__":
+    client = DeepInfra()
+    response = client.chat.completions.create(
+        model="deepseek-ai/DeepSeek-R1-0528",
+        messages=[{"role": "user", "content": "Hello, how are you?"}],
+        max_tokens=10000,
+        stream=False
+    )
     print(response.choices[0].message.content)