tau-coding-agent 0.1.0__py3-none-any.whl

tau/builtins/models/text.py

@@ -0,0 +1,482 @@
+from tau.inference.model.types import Cost, Model, Modality
+
+_TEXT            = [Modality.Text]
+_TEXT_IMAGE      = [Modality.Text, Modality.Image]
+_TEXT_IMAGE_VIDEO = [Modality.Text, Modality.Image, Modality.Video]
+
+models = [
+    # OpenAI Codex (OAuth)
+    Model(id="gpt-5.5",              name="GPT-5.5",              provider="openai-codex", cost=Cost(), thinking=True, context_window=400_000, input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="gpt-5.4",              name="GPT-5.4",              provider="openai-codex", cost=Cost(), thinking=True, context_window=400_000, input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="gpt-5.4-mini",         name="GPT-5.4 Mini",         provider="openai-codex", cost=Cost(), thinking=True, context_window=400_000, input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="gpt-5.3-codex",        name="GPT-5.3 Codex",        provider="openai-codex", cost=Cost(), thinking=True, context_window=400_000, input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="gpt-5.3-codex-spark",  name="GPT-5.3 Codex Spark",  provider="openai-codex", cost=Cost(), thinking=True, context_window=400_000, input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="gpt-5.2",              name="GPT-5.2",              provider="openai-codex", cost=Cost(), thinking=True, context_window=400_000, input=_TEXT_IMAGE, output=_TEXT),
+    # Anthropic Claude Code (OAuth)
+    Model(id="claude-opus-4-7",           name="Claude Opus 4.7",   provider="anthropic-claude-code", cost=Cost(), thinking=True, context_window=200_000, input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="claude-sonnet-4-6",         name="Claude Sonnet 4.6", provider="anthropic-claude-code", cost=Cost(), thinking=True, context_window=200_000, input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="claude-haiku-4-5-20251001", name="Claude Haiku 4.5",  provider="anthropic-claude-code", cost=Cost(),               context_window=200_000, input=_TEXT_IMAGE, output=_TEXT),
+    # Google Antigravity (OAuth — free IDE quota)
+    Model(id="gemini-3-flash",         name="Gemini 3 Flash",         provider="google-antigravity", cost=Cost(), thinking=True, context_window=1_048_576, input=_TEXT_IMAGE_VIDEO, output=_TEXT),
+    Model(id="gemini-3.1-pro-preview", name="Gemini 3.1 Pro",         provider="google-antigravity", cost=Cost(), thinking=True, context_window=1_048_576, input=_TEXT_IMAGE_VIDEO, output=_TEXT),
+    Model(id="gemini-3-flash-preview", name="Gemini 3 Flash Preview",  provider="google-antigravity", cost=Cost(), thinking=True, context_window=1_048_576, input=_TEXT_IMAGE_VIDEO, output=_TEXT),
+    Model(id="gemini-3.1-flash-lite",  name="Gemini 3.1 Flash Lite",   provider="google-antigravity", cost=Cost(),               context_window=1_048_576, input=_TEXT_IMAGE_VIDEO, output=_TEXT),
+    Model(id="gemini-2.5-pro",         name="Gemini 2.5 Pro",          provider="google-antigravity", cost=Cost(), thinking=True, context_window=1_048_576, input=_TEXT_IMAGE_VIDEO, output=_TEXT),
+    Model(id="gemini-2.5-flash",       name="Gemini 2.5 Flash",        provider="google-antigravity", cost=Cost(), thinking=True, context_window=1_048_576, input=_TEXT_IMAGE_VIDEO, output=_TEXT),
+    Model(id="gemini-2.5-flash-lite",  name="Gemini 2.5 Flash Lite",   provider="google-antigravity", cost=Cost(),               context_window=1_048_576, input=_TEXT_IMAGE_VIDEO, output=_TEXT),
+    # GitHub Copilot
+    Model(id="gpt-4o",               name="GPT-4o",             provider="github-copilot", cost=Cost(),               context_window=128_000,   input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="gpt-4o-mini",          name="GPT-4o Mini",        provider="github-copilot", cost=Cost(),               context_window=128_000,   input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="o3-mini",              name="O3 Mini",            provider="github-copilot", cost=Cost(), thinking=True, context_window=200_000,   input=_TEXT,       output=_TEXT),
+    Model(id="claude-3.5-sonnet",    name="Claude 3.5 Sonnet",  provider="github-copilot", cost=Cost(),               context_window=200_000,   input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="claude-3.7-sonnet",    name="Claude 3.7 Sonnet",  provider="github-copilot", cost=Cost(), thinking=True, context_window=200_000,   input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="gemini-2.0-flash-001", name="Gemini 2.0 Flash",   provider="github-copilot", cost=Cost(),               context_window=1_000_000, input=_TEXT_IMAGE_VIDEO, output=_TEXT),
+    Model(id="grok-3",               name="Grok 3",             provider="github-copilot", cost=Cost(),               context_window=131_072,   input=_TEXT,       output=_TEXT),
+    # OpenAI (API key)
+    Model(id="gpt-5.5",      name="GPT-5.5",      provider="openai", cost=Cost(input=5.0,  output=30.0, cache_read=0.50),  thinking=True, context_window=1_050_000, input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="gpt-5.4",      name="GPT-5.4",      provider="openai", cost=Cost(input=2.5,  output=15.0, cache_read=0.25),  thinking=True, context_window=1_000_000, input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="gpt-5.4-mini", name="GPT-5.4 Mini", provider="openai", cost=Cost(input=0.75, output=4.5,  cache_read=0.075), thinking=True, context_window=1_000_000, input=_TEXT_IMAGE, output=_TEXT),
+    # Anthropic (API key)
+    Model(id="claude-opus-4-7",           name="Claude Opus 4.7",   provider="anthropic", cost=Cost(input=15.0, output=75.0, cache_read=1.5,  cache_write=3.75), thinking=True, context_window=200_000, input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="claude-sonnet-4-6",         name="Claude Sonnet 4.6", provider="anthropic", cost=Cost(input=3.0,  output=15.0, cache_read=0.30, cache_write=3.75), thinking=True, context_window=200_000, input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="claude-haiku-4-5-20251001", name="Claude Haiku 4.5",  provider="anthropic", cost=Cost(input=0.80, output=4.0,  cache_read=0.08, cache_write=1.0),               context_window=200_000, input=_TEXT_IMAGE, output=_TEXT),
+    # NVIDIA NIM
+    Model(id="nvidia/llama-3.3-nemotron-super-49b-v1.5",  name="Nemotron Super 49B v1.5", provider="nvidia", cost=Cost(), thinking=True, context_window=128_000,   input=_TEXT, output=_TEXT),
+    Model(id="meta/llama-3.3-70b-instruct",               name="Llama 3.3 70B Instruct",  provider="nvidia", cost=Cost(),               context_window=128_000,   input=_TEXT, output=_TEXT),
+    Model(id="meta/llama-3.1-8b-instruct",                name="Llama 3.1 8B Instruct",   provider="nvidia", cost=Cost(),               context_window=128_000,   input=_TEXT, output=_TEXT),
+    Model(id="qwen/qwen3-next-80b-a3b-thinking",          name="Qwen3 Next 80B Thinking", provider="nvidia", cost=Cost(), thinking=True, context_window=131_072,   input=_TEXT, output=_TEXT),
+    Model(id="qwen/qwen3-next-80b-a3b-instruct",          name="Qwen3 Next 80B Instruct", provider="nvidia", cost=Cost(),               context_window=131_072,   input=_TEXT, output=_TEXT),
+    Model(id="qwen/qwen3.5-397b-a17b",                    name="Qwen3.5 397B A17B",       provider="nvidia", cost=Cost(), thinking=True, context_window=131_072,   input=_TEXT, output=_TEXT),
+    Model(id="qwen/qwen3.5-122b-a10b",                    name="Qwen3.5 122B A10B",       provider="nvidia", cost=Cost(), thinking=True, context_window=131_072,   input=_TEXT, output=_TEXT),
+    Model(id="qwen/qwen3-coder-480b-a35b-instruct",       name="Qwen3 Coder 480B",        provider="nvidia", cost=Cost(),               context_window=256_000,   input=_TEXT, output=_TEXT),
+    Model(id="deepseek-ai/deepseek-v4-pro",               name="DeepSeek V4 Pro",         provider="nvidia", cost=Cost(), thinking=True, context_window=1_000_000, input=_TEXT, output=_TEXT),
+    Model(id="deepseek-ai/deepseek-v4-flash",             name="DeepSeek V4 Flash",       provider="nvidia", cost=Cost(), thinking=True, context_window=1_000_000, input=_TEXT, output=_TEXT),
+    Model(id="z-ai/glm-5.1",                              name="GLM-5.1",                 provider="nvidia", cost=Cost(), thinking=True, context_window=131_072,   input=_TEXT, output=_TEXT),
+    Model(id="mistralai/mistral-medium-3.5-128b",         name="Mistral Medium 3.5 128B", provider="nvidia", cost=Cost(),               context_window=128_000,   input=_TEXT, output=_TEXT),
+    Model(id="mistralai/mistral-small-4-119b-2603",       name="Mistral Small 4 119B",    provider="nvidia", cost=Cost(),               context_window=256_000,   input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="google/gemma-4-31b-it",                     name="Gemma 4 31B IT",          provider="nvidia", cost=Cost(),               context_window=131_072,   input=_TEXT_IMAGE_VIDEO, output=_TEXT),
+    Model(id="minimaxai/minimax-m2.7",                    name="MiniMax M2.7",            provider="nvidia", cost=Cost(),               context_window=131_072,   input=_TEXT, output=_TEXT),
+    Model(id="moonshotai/kimi-k2.6",                      name="Kimi K2.6",               provider="nvidia", cost=Cost(),               context_window=131_072,   input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="nvidia/nemotron-3-nano-omni-30b-a3b-reasoning", name="Nemotron 3 Nano Omni", provider="nvidia", cost=Cost(),              context_window=131_072,   input=_TEXT_IMAGE_VIDEO, output=_TEXT),
+    Model(id="nvidia/nemotron-3-super-120b-a12b",         name="Nemotron 3 Super 120B",   provider="nvidia", cost=Cost(),               context_window=1_000_000, input=_TEXT, output=_TEXT),
+    # Groq (caps max_completion_tokens at 8192)
+    Model(id="openai/gpt-oss-120b",                       name="GPT-OSS 120B",          provider="groq", cost=Cost(input=0.15,  output=0.60), thinking=True, context_window=131_072, max_tokens=8192, input=_TEXT, output=_TEXT),
+    Model(id="openai/gpt-oss-20b",                        name="GPT-OSS 20B",           provider="groq", cost=Cost(input=0.075, output=0.30), thinking=True, context_window=131_072, max_tokens=8192, input=_TEXT, output=_TEXT),
+    Model(id="qwen/qwen3-32b",                            name="Qwen3 32B",             provider="groq", cost=Cost(input=0.29,  output=0.59), thinking=True, context_window=131_072, max_tokens=8192, input=_TEXT, output=_TEXT),
+    Model(id="llama-3.3-70b-versatile",                   name="Llama 3.3 70B",         provider="groq", cost=Cost(input=0.59,  output=0.79),               context_window=131_072, max_tokens=8192, input=_TEXT, output=_TEXT),
+    Model(id="llama-3.1-8b-instant",                      name="Llama 3.1 8B Instant",  provider="groq", cost=Cost(input=0.05,  output=0.08),               context_window=131_072, max_tokens=8192, input=_TEXT, output=_TEXT),
+    Model(id="meta-llama/llama-4-scout-17b-16e-instruct", name="Llama 4 Scout 17Bx16E", provider="groq", cost=Cost(input=0.11,  output=0.34),               context_window=131_072, max_tokens=8192, input=_TEXT_IMAGE, output=_TEXT),
+    # Perplexity
+    Model(id="perplexity/sonar",              name="Sonar",              provider="perplexity", cost=Cost(input=1.0, output=1.0),                              context_window=128_000, input=_TEXT, output=_TEXT),
+    Model(id="perplexity/sonar-pro",          name="Sonar Pro",          provider="perplexity", cost=Cost(input=3.0, output=15.0),                             context_window=200_000, input=_TEXT, output=_TEXT),
+    Model(id="perplexity/sonar-reasoning-pro", name="Sonar Reasoning Pro", provider="perplexity", cost=Cost(input=2.0, output=8.0), thinking=True,             context_window=128_000, input=_TEXT, output=_TEXT),
+    Model(id="perplexity/sonar-deep-research", name="Sonar Deep Research", provider="perplexity", cost=Cost(input=2.0, output=8.0), thinking=True,             context_window=128_000, input=_TEXT, output=_TEXT),
+    # xAI
+    Model(id="grok-4.3",       name="Grok 4.3",       provider="xai", cost=Cost(input=1.25, output=2.50, cache_read=0.20), thinking=True, context_window=1_000_000, input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="grok-build-0.1", name="Grok Build 0.1", provider="xai", cost=Cost(input=1.00, output=2.00, cache_read=0.20), thinking=True, context_window=256_000,   input=_TEXT_IMAGE, output=_TEXT),
+    # AWS Bedrock
+    Model(id="openai.gpt-oss-120b",        name="GPT-OSS 120B",        provider="bedrock", cost=Cost(), thinking=True, context_window=131_072, input=_TEXT,       output=_TEXT),
+    Model(id="openai.gpt-oss-20b",         name="GPT-OSS 20B",         provider="bedrock", cost=Cost(), thinking=True, context_window=131_072, input=_TEXT,       output=_TEXT),
+    Model(id="anthropic.claude-opus-4-7",  name="Claude Opus 4.7",     provider="bedrock", cost=Cost(), thinking=True, context_window=200_000, input=_TEXT_IMAGE, output=_TEXT, api="anthropic_messages", base_url="https://bedrock-mantle.us-east-1.api.aws/anthropic"),
+    Model(id="anthropic.claude-sonnet-4-6", name="Claude Sonnet 4.6",  provider="bedrock", cost=Cost(), thinking=True, context_window=200_000, input=_TEXT_IMAGE, output=_TEXT, api="anthropic_messages", base_url="https://bedrock-mantle.us-east-1.api.aws/anthropic"),
+    # Kimi / Moonshot
+    Model(id="kimi-k2.6",                name="Kimi K2.6",             provider="kimi", cost=Cost(input=0.95, output=4.0, cache_read=0.16), thinking=True, context_window=256_000, input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="kimi-k2.5",                name="Kimi K2.5",             provider="kimi", cost=Cost(), thinking=True, context_window=256_000, input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="kimi-k2-thinking",         name="Kimi K2 Thinking",      provider="kimi", cost=Cost(), thinking=True, context_window=256_000, input=_TEXT,       output=_TEXT),
+    Model(id="moonshot-v1-128k",         name="Moonshot v1 128K",      provider="kimi", cost=Cost(),                context_window=128_000, input=_TEXT,       output=_TEXT),
+    Model(id="moonshot-v1-128k-vision-preview", name="Moonshot v1 128K Vision", provider="kimi", cost=Cost(),       context_window=128_000, input=_TEXT_IMAGE, output=_TEXT),
+    # MiniMax
+    Model(id="MiniMax-M2.7",           name="MiniMax M2.7",            provider="minimax", cost=Cost(), thinking=True, context_window=204_800, max_tokens=196_608, input=_TEXT, output=_TEXT),
+    Model(id="MiniMax-M2.7-highspeed", name="MiniMax M2.7 Highspeed",  provider="minimax", cost=Cost(), thinking=True, context_window=204_800, max_tokens=196_608, input=_TEXT, output=_TEXT),
+    Model(id="MiniMax-M2.5",           name="MiniMax M2.5",            provider="minimax", cost=Cost(), thinking=True, context_window=204_800, max_tokens=196_608, input=_TEXT, output=_TEXT),
+    Model(id="MiniMax-M2.1",           name="MiniMax M2.1",            provider="minimax", cost=Cost(), thinking=True, context_window=204_800, max_tokens=196_608, input=_TEXT, output=_TEXT),
+    # DeepSeek
+    Model(id="deepseek-v4-pro",      name="DeepSeek V4 Pro",           provider="deepseek", cost=Cost(), thinking=True, context_window=1_000_000, input=_TEXT, output=_TEXT),
+    Model(id="deepseek-v4-flash",    name="DeepSeek V4 Flash",         provider="deepseek", cost=Cost(), thinking=True, context_window=1_000_000, input=_TEXT, output=_TEXT),
+    Model(id="deepseek-chat",        name="DeepSeek Chat",             provider="deepseek", cost=Cost(),               context_window=1_000_000, input=_TEXT, output=_TEXT),
+    Model(id="deepseek-reasoner",    name="DeepSeek Reasoner",         provider="deepseek", cost=Cost(), thinking=True, context_window=1_000_000, input=_TEXT, output=_TEXT),
+    # Kilo Code Gateway
+    Model(id="kilo-auto/frontier",           name="Kilo Auto Frontier", provider="kilocode", cost=Cost(), thinking=True, context_window=200_000, input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="kilo-auto/balanced",           name="Kilo Auto Balanced", provider="kilocode", cost=Cost(), thinking=True, context_window=256_000, input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="kilo-auto/free",               name="Kilo Auto Free",     provider="kilocode", cost=Cost(), thinking=True, context_window=128_000, input=_TEXT,       output=_TEXT),
+    Model(id="kilo-auto/small",              name="Kilo Auto Small",    provider="kilocode", cost=Cost(),               context_window=128_000, input=_TEXT,       output=_TEXT),
+    Model(id="anthropic/claude-sonnet-4.6",  name="Claude Sonnet 4.6",  provider="kilocode", cost=Cost(), thinking=True, context_window=200_000, input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="deepseek/deepseek-v3.2",       name="DeepSeek V3.2",      provider="kilocode", cost=Cost(), thinking=True, context_window=131_072, input=_TEXT,       output=_TEXT),
+    Model(id="moonshotai/kimi-k2.5",         name="Kimi K2.5",          provider="kilocode", cost=Cost(), thinking=True, context_window=256_000, input=_TEXT,       output=_TEXT),
+    Model(id="minimax/minimax-m2.7",         name="MiniMax M2.7",       provider="kilocode", cost=Cost(), thinking=True, context_window=204_800, input=_TEXT,       output=_TEXT),
+    # Mistral
+    Model(id="mistral-large-latest",    name="Mistral Large 3",      provider="mistral", cost=Cost(input=0.50, output=1.50),                context_window=262_144, input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="mistral-medium-latest",   name="Mistral Medium 3.5",   provider="mistral", cost=Cost(input=0.40, output=2.0),                 context_window=131_072, input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="mistral-small-latest",    name="Mistral Small 4",      provider="mistral", cost=Cost(input=0.10, output=0.30), thinking=True, context_window=131_072, input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="magistral-medium-latest", name="Magistral Medium 1.2", provider="mistral", cost=Cost(input=2.0,  output=5.0),  thinking=True, context_window=131_072, input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="devstral-latest",         name="Devstral 2",           provider="mistral", cost=Cost(input=0.40, output=2.0),                 context_window=262_144, input=_TEXT,       output=_TEXT),
+    Model(id="codestral-latest",        name="Codestral",            provider="mistral", cost=Cost(input=0.30, output=0.90),                context_window=262_144, input=_TEXT,       output=_TEXT),
+    # Ollama
+    Model(id="deepseek-v4-pro:cloud",    name="DeepSeek V4 Pro Cloud", provider="ollama", cost=Cost(), thinking=True, context_window=1_000_000, input=_TEXT,       output=_TEXT),
+    Model(id="deepseek-v4-flash:cloud",  name="DeepSeek V4 Flash Cloud", provider="ollama", cost=Cost(), thinking=True, context_window=1_000_000, input=_TEXT,       output=_TEXT),
+    Model(id="deepseek-v3.2:cloud",      name="DeepSeek V3.2 Cloud",  provider="ollama", cost=Cost(), thinking=True, context_window=160_000,   input=_TEXT,       output=_TEXT),
+    Model(id="gemma4:31b-cloud",         name="Gemma 4 31B Cloud",    provider="ollama", cost=Cost(), thinking=True, context_window=256_000,   input=_TEXT_IMAGE_VIDEO, output=_TEXT),
+    Model(id="glm-5.1:cloud",            name="GLM 5.1 Cloud",        provider="ollama", cost=Cost(), thinking=True, context_window=198_000,   input=_TEXT,       output=_TEXT),
+    Model(id="minimax-m2.7:cloud",       name="MiniMax M2.7 Cloud",   provider="ollama", cost=Cost(), thinking=True, context_window=200_000,   input=_TEXT,       output=_TEXT),
+    Model(id="kimi-k2.6:cloud",          name="Kimi K2.6 Cloud",      provider="ollama", cost=Cost(), thinking=True, context_window=256_000,   input=_TEXT_IMAGE, output=_TEXT),
+    Model(id="qwen3.5:397b-cloud",       name="Qwen 3.5 397B Cloud",  provider="ollama", cost=Cost(), thinking=True, context_window=256_000,   input=_TEXT_IMAGE, output=_TEXT),
+    # OpenRouter
+    Model(id='qwen/qwen3.7-max', name='Qwen: Qwen3.7 Max', provider='openrouter', cost=Cost(input=2.5, output=7.5, cache_read=0.0, cache_write=3.125), thinking=True, context_window=1000000, max_tokens=65536, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='x-ai/grok-build-0.1', name='xAI: Grok Build 0.1', provider='openrouter', cost=Cost(input=1.0, output=2.0, cache_read=0.19999999999999998, cache_write=0.0), thinking=True, context_window=256000, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemini-3.5-flash', name='Google: Gemini 3.5 Flash', provider='openrouter', cost=Cost(input=1.5, output=9.0, cache_read=0.15, cache_write=0.08333333333333334), thinking=True, context_window=1048576, max_tokens=65536, input=[Modality.Text, Modality.Image, Modality.Video, Modality.Audio], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='anthropic/claude-opus-4.7-fast', name='Anthropic: Claude Opus 4.7 (Fast)', provider='openrouter', cost=Cost(input=30.0, output=150.0, cache_read=3.0, cache_write=37.5), thinking=True, context_window=1000000, max_tokens=128000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='perceptron/perceptron-mk1', name='Perceptron: Perceptron Mk1', provider='openrouter', cost=Cost(input=0.15, output=1.5, cache_read=0.0, cache_write=0.0), thinking=True, context_window=32768, max_tokens=8192, input=[Modality.Text, Modality.Image, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='inclusionai/ring-2.6-1t', name='inclusionAI: Ring-2.6-1T', provider='openrouter', cost=Cost(input=0.075, output=0.625, cache_read=0.015, cache_write=0.0), thinking=True, context_window=262144, max_tokens=65536, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemini-3.1-flash-lite', name='Google: Gemini 3.1 Flash Lite', provider='openrouter', cost=Cost(input=0.25, output=1.5, cache_read=0.024999999999999998, cache_write=0.08333333333333334), thinking=True, context_window=1048576, max_tokens=65536, input=[Modality.Text, Modality.Image, Modality.Video, Modality.Audio], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='baidu/cobuddy:free', name='Baidu Qianfan: CoBuddy (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=65536, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-chat-latest', name='OpenAI: GPT Chat Latest', provider='openrouter', cost=Cost(input=5.0, output=30.0, cache_read=0.5, cache_write=0.0), thinking=False, context_window=400000, max_tokens=128000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='x-ai/grok-4.3', name='xAI: Grok 4.3', provider='openrouter', cost=Cost(input=1.25, output=2.5, cache_read=0.19999999999999998, cache_write=0.0), thinking=True, context_window=1000000, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='ibm-granite/granite-4.1-8b', name='IBM: Granite 4.1 8B', provider='openrouter', cost=Cost(input=0.049999999999999996, output=0.09999999999999999, cache_read=0.049999999999999996, cache_write=0.0), thinking=False, context_window=131072, max_tokens=131072, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/mistral-medium-3-5', name='Mistral: Mistral Medium 3.5', provider='openrouter', cost=Cost(input=1.5, output=7.5, cache_read=0.0, cache_write=0.0), thinking=True, context_window=262144, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openrouter/owl-alpha', name='Owl Alpha', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=1048756, max_tokens=262144, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free', name='NVIDIA: Nemotron 3 Nano Omni (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=256000, max_tokens=65536, input=[Modality.Text, Modality.Audio, Modality.Image, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='poolside/laguna-xs.2:free', name='Poolside: Laguna XS.2 (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=8192, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='poolside/laguna-m.1:free', name='Poolside: Laguna M.1 (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=8192, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='~anthropic/claude-haiku-latest', name='Anthropic Claude Haiku Latest', provider='openrouter', cost=Cost(input=1.0, output=5.0, cache_read=0.09999999999999999, cache_write=1.25), thinking=True, context_window=200000, max_tokens=64000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='~openai/gpt-mini-latest', name='OpenAI GPT Mini Latest', provider='openrouter', cost=Cost(input=0.75, output=4.5, cache_read=0.075, cache_write=0.0), thinking=True, context_window=400000, max_tokens=128000, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='~google/gemini-pro-latest', name='Google Gemini Pro Latest', provider='openrouter', cost=Cost(input=2.0, output=12.0, cache_read=0.19999999999999998, cache_write=0.375), thinking=True, context_window=1048576, max_tokens=65536, input=[Modality.Audio, Modality.Image, Modality.Text, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='~moonshotai/kimi-latest', name='MoonshotAI Kimi Latest', provider='openrouter', cost=Cost(input=0.73, output=3.49, cache_read=0.25, cache_write=0.0), thinking=True, context_window=262144, max_tokens=262142, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='~google/gemini-flash-latest', name='Google Gemini Flash Latest', provider='openrouter', cost=Cost(input=1.5, output=9.0, cache_read=0.15, cache_write=0.08333333333333334), thinking=True, context_window=1048576, max_tokens=65536, input=[Modality.Text, Modality.Image, Modality.Video, Modality.Audio], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='~anthropic/claude-sonnet-latest', name='Anthropic Claude Sonnet Latest', provider='openrouter', cost=Cost(input=3.0, output=15.0, cache_read=0.3, cache_write=3.75), thinking=True, context_window=1000000, max_tokens=128000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='~openai/gpt-latest', name='OpenAI GPT Latest', provider='openrouter', cost=Cost(input=5.0, output=30.0, cache_read=0.5, cache_write=0.0), thinking=True, context_window=1050000, max_tokens=128000, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3.5-plus-20260420', name='Qwen: Qwen3.5 Plus 2026-04-20', provider='openrouter', cost=Cost(input=0.3, output=1.7999999999999998, cache_read=0.0, cache_write=0.0), thinking=True, context_window=1000000, max_tokens=65536, input=[Modality.Text, Modality.Image, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3.6-flash', name='Qwen: Qwen3.6 Flash', provider='openrouter', cost=Cost(input=0.1875, output=1.125, cache_read=0.0, cache_write=0.234375), thinking=True, context_window=1000000, max_tokens=65536, input=[Modality.Text, Modality.Image, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3.6-35b-a3b', name='Qwen: Qwen3.6 35B A3B', provider='openrouter', cost=Cost(input=0.15, output=1.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=262144, max_tokens=262140, input=[Modality.Text, Modality.Image, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3.6-max-preview', name='Qwen: Qwen3.6 Max Preview', provider='openrouter', cost=Cost(input=1.04, output=6.24, cache_read=0.0, cache_write=1.3), thinking=True, context_window=262144, max_tokens=65536, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3.6-27b', name='Qwen: Qwen3.6 27B', provider='openrouter', cost=Cost(input=0.3, output=3.1999999999999997, cache_read=0.0, cache_write=0.0), thinking=True, context_window=262144, max_tokens=262144, input=[Modality.Text, Modality.Image, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5.5-pro', name='OpenAI: GPT-5.5 Pro', provider='openrouter', cost=Cost(input=30.0, output=180.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=1050000, max_tokens=128000, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5.5', name='OpenAI: GPT-5.5', provider='openrouter', cost=Cost(input=5.0, output=30.0, cache_read=0.5, cache_write=0.0), thinking=True, context_window=1050000, max_tokens=128000, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='deepseek/deepseek-v4-pro', name='DeepSeek: DeepSeek V4 Pro', provider='openrouter', cost=Cost(input=0.435, output=0.87, cache_read=0.003625, cache_write=0.0), thinking=True, context_window=1048576, max_tokens=384000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='deepseek/deepseek-v4-flash:free', name='DeepSeek: DeepSeek V4 Flash (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=1048576, max_tokens=384000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='deepseek/deepseek-v4-flash', name='DeepSeek: DeepSeek V4 Flash', provider='openrouter', cost=Cost(input=0.09999999999999999, output=0.19999999999999998, cache_read=0.02, cache_write=0.0), thinking=True, context_window=1048576, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='inclusionai/ling-2.6-1t', name='inclusionAI: Ling-2.6-1T', provider='openrouter', cost=Cost(input=0.075, output=0.625, cache_read=0.015, cache_write=0.0), thinking=False, context_window=262144, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='tencent/hy3-preview', name='Tencent: Hy3 preview', provider='openrouter', cost=Cost(input=0.06599999999999999, output=0.26, cache_read=0.029, cache_write=0.0), thinking=True, context_window=262144, max_tokens=262144, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='xiaomi/mimo-v2.5-pro', name='Xiaomi: MiMo-V2.5-Pro', provider='openrouter', cost=Cost(input=1.0, output=3.0, cache_read=0.19999999999999998, cache_write=0.0), thinking=True, context_window=1048576, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='xiaomi/mimo-v2.5', name='Xiaomi: MiMo-V2.5', provider='openrouter', cost=Cost(input=0.39999999999999997, output=2.0, cache_read=0.08, cache_write=0.0), thinking=True, context_window=1048576, max_tokens=131072, input=[Modality.Text, Modality.Audio, Modality.Image, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5.4-image-2', name='OpenAI: GPT-5.4 Image 2', provider='openrouter', cost=Cost(input=8.0, output=15.0, cache_read=2.0, cache_write=0.0), thinking=True, context_window=272000, max_tokens=128000, input=[Modality.Image, Modality.Text], output=[Modality.Image, Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='inclusionai/ling-2.6-flash', name='inclusionAI: Ling-2.6-flash', provider='openrouter', cost=Cost(input=0.01, output=0.03, cache_read=0.002, cache_write=0.0), thinking=False, context_window=262144, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='~anthropic/claude-opus-latest', name='Anthropic: Claude Opus Latest', provider='openrouter', cost=Cost(input=5.0, output=25.0, cache_read=0.5, cache_write=6.25), thinking=True, context_window=1000000, max_tokens=128000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openrouter/pareto-code', name='Pareto Code Router', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=2000000, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='baidu/qianfan-ocr-fast', name='Baidu: Qianfan-OCR-Fast', provider='openrouter', cost=Cost(input=0.6799999999999999, output=2.81, cache_read=0.0, cache_write=0.0), thinking=True, context_window=65536, max_tokens=28672, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='moonshotai/kimi-k2.6', name='MoonshotAI: Kimi K2.6', provider='openrouter', cost=Cost(input=0.73, output=3.49, cache_read=0.25, cache_write=0.0), thinking=True, context_window=262144, max_tokens=262142, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='anthropic/claude-opus-4.7', name='Anthropic: Claude Opus 4.7', provider='openrouter', cost=Cost(input=5.0, output=25.0, cache_read=0.5, cache_write=6.25), thinking=True, context_window=1000000, max_tokens=128000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='anthropic/claude-opus-4.6-fast', name='Anthropic: Claude Opus 4.6 (Fast)', provider='openrouter', cost=Cost(input=30.0, output=150.0, cache_read=3.0, cache_write=37.5), thinking=True, context_window=1000000, max_tokens=128000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='z-ai/glm-5.1', name='Z.ai: GLM 5.1', provider='openrouter', cost=Cost(input=0.98, output=3.08, cache_read=0.182, cache_write=0.0), thinking=True, context_window=202752, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemma-4-26b-a4b-it:free', name='Google: Gemma 4 26B A4B  (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=262144, max_tokens=32768, input=[Modality.Image, Modality.Text, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemma-4-26b-a4b-it', name='Google: Gemma 4 26B A4B ', provider='openrouter', cost=Cost(input=0.06, output=0.33, cache_read=0.0, cache_write=0.0), thinking=True, context_window=262144, max_tokens=16384, input=[Modality.Image, Modality.Text, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemma-4-31b-it:free', name='Google: Gemma 4 31B (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=262144, max_tokens=32768, input=[Modality.Image, Modality.Text, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemma-4-31b-it', name='Google: Gemma 4 31B', provider='openrouter', cost=Cost(input=0.12, output=0.37, cache_read=0.0, cache_write=0.0), thinking=True, context_window=262144, max_tokens=16384, input=[Modality.Image, Modality.Text, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3.6-plus', name='Qwen: Qwen3.6 Plus', provider='openrouter', cost=Cost(input=0.325, output=1.95, cache_read=0.0, cache_write=0.40625), thinking=True, context_window=1000000, max_tokens=65536, input=[Modality.Text, Modality.Image, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='z-ai/glm-5v-turbo', name='Z.ai: GLM 5V Turbo', provider='openrouter', cost=Cost(input=1.2, output=4.0, cache_read=0.24, cache_write=0.0), thinking=True, context_window=202752, max_tokens=131072, input=[Modality.Image, Modality.Text, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='arcee-ai/trinity-large-thinking:free', name='Arcee AI: Trinity Large Thinking (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=262144, max_tokens=80000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='arcee-ai/trinity-large-thinking', name='Arcee AI: Trinity Large Thinking', provider='openrouter', cost=Cost(input=0.22, output=0.85, cache_read=0.06, cache_write=0.0), thinking=True, context_window=262144, max_tokens=262144, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='x-ai/grok-4.20-multi-agent', name='xAI: Grok 4.20 Multi-Agent', provider='openrouter', cost=Cost(input=2.0, output=6.0, cache_read=0.19999999999999998, cache_write=0.0), thinking=True, context_window=2000000, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='x-ai/grok-4.20', name='xAI: Grok 4.20', provider='openrouter', cost=Cost(input=1.25, output=2.5, cache_read=0.19999999999999998, cache_write=0.0), thinking=True, context_window=2000000, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/lyria-3-pro-preview', name='Google: Lyria 3 Pro Preview', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=1048576, max_tokens=65536, input=[Modality.Text, Modality.Image], output=[Modality.Text, Modality.Audio], api=None, base_url=None, voices=[]),
+    Model(id='google/lyria-3-clip-preview', name='Google: Lyria 3 Clip Preview', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=1048576, max_tokens=65536, input=[Modality.Text, Modality.Image], output=[Modality.Text, Modality.Audio], api=None, base_url=None, voices=[]),
+    Model(id='kwaipilot/kat-coder-pro-v2', name='Kwaipilot: KAT-Coder-Pro V2', provider='openrouter', cost=Cost(input=0.3, output=1.2, cache_read=0.06, cache_write=0.0), thinking=False, context_window=256000, max_tokens=80000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='rekaai/reka-edge', name='Reka Edge', provider='openrouter', cost=Cost(input=0.09999999999999999, output=0.09999999999999999, cache_read=0.0, cache_write=0.0), thinking=False, context_window=16384, max_tokens=16384, input=[Modality.Image, Modality.Text, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='xiaomi/mimo-v2-omni', name='Xiaomi: MiMo-V2-Omni', provider='openrouter', cost=Cost(input=0.39999999999999997, output=2.0, cache_read=0.08, cache_write=0.0), thinking=True, context_window=262144, max_tokens=65536, input=[Modality.Text, Modality.Audio, Modality.Image, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='xiaomi/mimo-v2-pro', name='Xiaomi: MiMo-V2-Pro', provider='openrouter', cost=Cost(input=1.0, output=3.0, cache_read=0.19999999999999998, cache_write=0.0), thinking=True, context_window=1048576, max_tokens=131072, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='minimax/minimax-m2.7', name='MiniMax: MiniMax M2.7', provider='openrouter', cost=Cost(input=0.27899999999999997, output=1.2, cache_read=0.0, cache_write=0.0), thinking=True, context_window=204800, max_tokens=131072, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5.4-nano', name='OpenAI: GPT-5.4 Nano', provider='openrouter', cost=Cost(input=0.19999999999999998, output=1.25, cache_read=0.02, cache_write=0.0), thinking=True, context_window=400000, max_tokens=128000, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5.4-mini', name='OpenAI: GPT-5.4 Mini', provider='openrouter', cost=Cost(input=0.75, output=4.5, cache_read=0.075, cache_write=0.0), thinking=True, context_window=400000, max_tokens=128000, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/mistral-small-2603', name='Mistral: Mistral Small 4', provider='openrouter', cost=Cost(input=0.15, output=0.6, cache_read=0.015, cache_write=0.0), thinking=True, context_window=262144, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='z-ai/glm-5-turbo', name='Z.ai: GLM 5 Turbo', provider='openrouter', cost=Cost(input=1.2, output=4.0, cache_read=0.24, cache_write=0.0), thinking=True, context_window=202752, max_tokens=131072, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='nvidia/nemotron-3-super-120b-a12b:free', name='NVIDIA: Nemotron 3 Super (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=1000000, max_tokens=262144, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='nvidia/nemotron-3-super-120b-a12b', name='NVIDIA: Nemotron 3 Super', provider='openrouter', cost=Cost(input=0.09, output=0.44999999999999996, cache_read=0.0, cache_write=0.0), thinking=True, context_window=1000000, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='bytedance-seed/seed-2.0-lite', name='ByteDance Seed: Seed-2.0-Lite', provider='openrouter', cost=Cost(input=0.25, output=2.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=262144, max_tokens=131072, input=[Modality.Text, Modality.Image, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3.5-9b', name='Qwen: Qwen3.5-9B', provider='openrouter', cost=Cost(input=0.04, output=0.15, cache_read=0.0, cache_write=0.0), thinking=True, context_window=262144, max_tokens=81920, input=[Modality.Text, Modality.Image, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5.4-pro', name='OpenAI: GPT-5.4 Pro', provider='openrouter', cost=Cost(input=30.0, output=180.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=1050000, max_tokens=128000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5.4', name='OpenAI: GPT-5.4', provider='openrouter', cost=Cost(input=2.5, output=15.0, cache_read=0.25, cache_write=0.0), thinking=True, context_window=1050000, max_tokens=128000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='inception/mercury-2', name='Inception: Mercury 2', provider='openrouter', cost=Cost(input=0.25, output=0.75, cache_read=0.024999999999999998, cache_write=0.0), thinking=True, context_window=128000, max_tokens=50000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5.3-chat', name='OpenAI: GPT-5.3 Chat', provider='openrouter', cost=Cost(input=1.75, output=14.0, cache_read=0.175, cache_write=0.0), thinking=False, context_window=128000, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemini-3.1-flash-lite-preview', name='Google: Gemini 3.1 Flash Lite Preview', provider='openrouter', cost=Cost(input=0.25, output=1.5, cache_read=0.024999999999999998, cache_write=0.08333333333333334), thinking=True, context_window=1048576, max_tokens=65536, input=[Modality.Text, Modality.Image, Modality.Video, Modality.Audio], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='bytedance-seed/seed-2.0-mini', name='ByteDance Seed: Seed-2.0-Mini', provider='openrouter', cost=Cost(input=0.09999999999999999, output=0.39999999999999997, cache_read=0.0, cache_write=0.0), thinking=True, context_window=262144, max_tokens=131072, input=[Modality.Text, Modality.Image, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemini-3.1-flash-image-preview', name='Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)', provider='openrouter', cost=Cost(input=0.5, output=3.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=65536, input=[Modality.Image, Modality.Text], output=[Modality.Image, Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3.5-35b-a3b', name='Qwen: Qwen3.5-35B-A3B', provider='openrouter', cost=Cost(input=0.13899999999999998, output=1.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=262144, max_tokens=16384, input=[Modality.Text, Modality.Image, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3.5-27b', name='Qwen: Qwen3.5-27B', provider='openrouter', cost=Cost(input=0.195, output=1.56, cache_read=0.0, cache_write=0.0), thinking=True, context_window=262144, max_tokens=65536, input=[Modality.Text, Modality.Image, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3.5-122b-a10b', name='Qwen: Qwen3.5-122B-A10B', provider='openrouter', cost=Cost(input=0.26, output=2.08, cache_read=0.0, cache_write=0.0), thinking=True, context_window=262144, max_tokens=262144, input=[Modality.Text, Modality.Image, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3.5-flash-02-23', name='Qwen: Qwen3.5-Flash', provider='openrouter', cost=Cost(input=0.065, output=0.26, cache_read=0.0, cache_write=0.08125), thinking=True, context_window=1000000, max_tokens=65536, input=[Modality.Text, Modality.Image, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='liquid/lfm-2-24b-a2b', name='LiquidAI: LFM2-24B-A2B', provider='openrouter', cost=Cost(input=0.03, output=0.12, cache_read=0.0, cache_write=0.0), thinking=False, context_window=128000, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemini-3.1-pro-preview-customtools', name='Google: Gemini 3.1 Pro Preview Custom Tools', provider='openrouter', cost=Cost(input=2.0, output=12.0, cache_read=0.19999999999999998, cache_write=0.375), thinking=True, context_window=1048756, max_tokens=65536, input=[Modality.Text, Modality.Audio, Modality.Image, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5.3-codex', name='OpenAI: GPT-5.3-Codex', provider='openrouter', cost=Cost(input=1.75, output=14.0, cache_read=0.175, cache_write=0.0), thinking=True, context_window=400000, max_tokens=128000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='aion-labs/aion-2.0', name='AionLabs: Aion-2.0', provider='openrouter', cost=Cost(input=0.7999999999999999, output=1.5999999999999999, cache_read=0.19999999999999998, cache_write=0.0), thinking=True, context_window=131072, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemini-3.1-pro-preview', name='Google: Gemini 3.1 Pro Preview', provider='openrouter', cost=Cost(input=2.0, output=12.0, cache_read=0.19999999999999998, cache_write=0.375), thinking=True, context_window=1048576, max_tokens=65536, input=[Modality.Audio, Modality.Image, Modality.Text, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='anthropic/claude-sonnet-4.6', name='Anthropic: Claude Sonnet 4.6', provider='openrouter', cost=Cost(input=3.0, output=15.0, cache_read=0.3, cache_write=3.75), thinking=True, context_window=1000000, max_tokens=128000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3.5-plus-02-15', name='Qwen: Qwen3.5 Plus 2026-02-15', provider='openrouter', cost=Cost(input=0.26, output=1.56, cache_read=0.0, cache_write=0.325), thinking=True, context_window=1000000, max_tokens=65536, input=[Modality.Text, Modality.Image, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3.5-397b-a17b', name='Qwen: Qwen3.5 397B A17B', provider='openrouter', cost=Cost(input=0.39, output=2.34, cache_read=0.0, cache_write=0.0), thinking=True, context_window=262144, max_tokens=65536, input=[Modality.Text, Modality.Image, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='minimax/minimax-m2.5:free', name='MiniMax: MiniMax M2.5 (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=204800, max_tokens=8192, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='minimax/minimax-m2.5', name='MiniMax: MiniMax M2.5', provider='openrouter', cost=Cost(input=0.15, output=1.15, cache_read=0.0, cache_write=0.0), thinking=True, context_window=204800, max_tokens=196608, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='z-ai/glm-5', name='Z.ai: GLM 5', provider='openrouter', cost=Cost(input=0.6, output=1.92, cache_read=0.12, cache_write=0.0), thinking=True, context_window=202752, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-max-thinking', name='Qwen: Qwen3 Max Thinking', provider='openrouter', cost=Cost(input=0.78, output=3.9, cache_read=0.0, cache_write=0.0), thinking=True, context_window=262144, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='anthropic/claude-opus-4.6', name='Anthropic: Claude Opus 4.6', provider='openrouter', cost=Cost(input=5.0, output=25.0, cache_read=0.5, cache_write=6.25), thinking=True, context_window=1000000, max_tokens=128000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-coder-next', name='Qwen: Qwen3 Coder Next', provider='openrouter', cost=Cost(input=0.11, output=0.7999999999999999, cache_read=0.07, cache_write=0.0), thinking=False, context_window=262144, max_tokens=262144, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openrouter/free', name='Free Models Router', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=200000, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='stepfun/step-3.5-flash', name='StepFun: Step 3.5 Flash', provider='openrouter', cost=Cost(input=0.09, output=0.3, cache_read=0.02, cache_write=0.0), thinking=True, context_window=262144, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='moonshotai/kimi-k2.5', name='MoonshotAI: Kimi K2.5', provider='openrouter', cost=Cost(input=0.39999999999999997, output=1.9, cache_read=0.09, cache_write=0.0), thinking=True, context_window=262144, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='upstage/solar-pro-3', name='Upstage: Solar Pro 3', provider='openrouter', cost=Cost(input=0.15, output=0.6, cache_read=0.015, cache_write=0.0), thinking=True, context_window=128000, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='minimax/minimax-m2-her', name='MiniMax: MiniMax M2-her', provider='openrouter', cost=Cost(input=0.3, output=1.2, cache_read=0.03, cache_write=0.0), thinking=False, context_window=65536, max_tokens=2048, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='writer/palmyra-x5', name='Writer: Palmyra X5', provider='openrouter', cost=Cost(input=0.6, output=6.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=1040000, max_tokens=8192, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='liquid/lfm-2.5-1.2b-thinking:free', name='LiquidAI: LFM2.5-1.2B-Thinking (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=32768, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='liquid/lfm-2.5-1.2b-instruct:free', name='LiquidAI: LFM2.5-1.2B-Instruct (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=32768, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-audio', name='OpenAI: GPT Audio', provider='openrouter', cost=Cost(input=2.5, output=10.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=128000, max_tokens=16384, input=[Modality.Text, Modality.Audio], output=[Modality.Text, Modality.Audio], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-audio-mini', name='OpenAI: GPT Audio Mini', provider='openrouter', cost=Cost(input=0.6, output=2.4, cache_read=0.0, cache_write=0.0), thinking=False, context_window=128000, max_tokens=16384, input=[Modality.Text, Modality.Audio], output=[Modality.Text, Modality.Audio], api=None, base_url=None, voices=[]),
+    Model(id='z-ai/glm-4.7-flash', name='Z.ai: GLM 4.7 Flash', provider='openrouter', cost=Cost(input=0.06, output=0.39999999999999997, cache_read=0.01, cache_write=0.0), thinking=True, context_window=202752, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5.2-codex', name='OpenAI: GPT-5.2-Codex', provider='openrouter', cost=Cost(input=1.75, output=14.0, cache_read=0.175, cache_write=0.0), thinking=True, context_window=400000, max_tokens=128000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='bytedance-seed/seed-1.6-flash', name='ByteDance Seed: Seed 1.6 Flash', provider='openrouter', cost=Cost(input=0.075, output=0.3, cache_read=0.0, cache_write=0.0), thinking=True, context_window=262144, max_tokens=32768, input=[Modality.Image, Modality.Text, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='bytedance-seed/seed-1.6', name='ByteDance Seed: Seed 1.6', provider='openrouter', cost=Cost(input=0.25, output=2.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=262144, max_tokens=32768, input=[Modality.Image, Modality.Text, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='minimax/minimax-m2.1', name='MiniMax: MiniMax M2.1', provider='openrouter', cost=Cost(input=0.29, output=0.95, cache_read=0.03, cache_write=0.0), thinking=True, context_window=204800, max_tokens=196608, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='z-ai/glm-4.7', name='Z.ai: GLM 4.7', provider='openrouter', cost=Cost(input=0.39999999999999997, output=1.75, cache_read=0.08, cache_write=0.0), thinking=True, context_window=202752, max_tokens=131072, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemini-3-flash-preview', name='Google: Gemini 3 Flash Preview', provider='openrouter', cost=Cost(input=0.5, output=3.0, cache_read=0.049999999999999996, cache_write=0.08333333333333334), thinking=True, context_window=1048576, max_tokens=65536, input=[Modality.Text, Modality.Image, Modality.Audio, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='xiaomi/mimo-v2-flash', name='Xiaomi: MiMo-V2-Flash', provider='openrouter', cost=Cost(input=0.09999999999999999, output=0.3, cache_read=0.01, cache_write=0.0), thinking=True, context_window=262144, max_tokens=65536, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='nvidia/nemotron-3-nano-30b-a3b:free', name='NVIDIA: Nemotron 3 Nano 30B A3B (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=256000, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='nvidia/nemotron-3-nano-30b-a3b', name='NVIDIA: Nemotron 3 Nano 30B A3B', provider='openrouter', cost=Cost(input=0.049999999999999996, output=0.19999999999999998, cache_read=0.0, cache_write=0.0), thinking=True, context_window=262144, max_tokens=228000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5.2-chat', name='OpenAI: GPT-5.2 Chat', provider='openrouter', cost=Cost(input=1.75, output=14.0, cache_read=0.175, cache_write=0.0), thinking=False, context_window=128000, max_tokens=32000, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5.2-pro', name='OpenAI: GPT-5.2 Pro', provider='openrouter', cost=Cost(input=21.0, output=168.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=400000, max_tokens=128000, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5.2', name='OpenAI: GPT-5.2', provider='openrouter', cost=Cost(input=1.75, output=14.0, cache_read=0.175, cache_write=0.0), thinking=True, context_window=400000, max_tokens=128000, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/devstral-2512', name='Mistral: Devstral 2 2512', provider='openrouter', cost=Cost(input=0.39999999999999997, output=2.0, cache_read=0.04, cache_write=0.0), thinking=False, context_window=262144, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='relace/relace-search', name='Relace: Relace Search', provider='openrouter', cost=Cost(input=1.0, output=3.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=256000, max_tokens=128000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='z-ai/glm-4.6v', name='Z.ai: GLM 4.6V', provider='openrouter', cost=Cost(input=0.3, output=0.8999999999999999, cache_read=0.049999999999999996, cache_write=0.0), thinking=True, context_window=131072, max_tokens=24000, input=[Modality.Image, Modality.Text, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='nex-agi/deepseek-v3.1-nex-n1', name='Nex AGI: DeepSeek V3.1 Nex N1', provider='openrouter', cost=Cost(input=0.135, output=0.5, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=163840, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='essentialai/rnj-1-instruct', name='EssentialAI: Rnj 1 Instruct', provider='openrouter', cost=Cost(input=0.15, output=0.15, cache_read=0.0, cache_write=0.0), thinking=False, context_window=32768, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openrouter/bodybuilder', name='Body Builder (beta)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=128000, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5.1-codex-max', name='OpenAI: GPT-5.1-Codex-Max', provider='openrouter', cost=Cost(input=1.25, output=10.0, cache_read=0.125, cache_write=0.0), thinking=True, context_window=400000, max_tokens=128000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='amazon/nova-2-lite-v1', name='Amazon: Nova 2 Lite', provider='openrouter', cost=Cost(input=0.3, output=2.5, cache_read=0.0, cache_write=0.0), thinking=True, context_window=1000000, max_tokens=65535, input=[Modality.Text, Modality.Image, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/ministral-14b-2512', name='Mistral: Ministral 3 14B 2512', provider='openrouter', cost=Cost(input=0.19999999999999998, output=0.19999999999999998, cache_read=0.02, cache_write=0.0), thinking=False, context_window=262144, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/ministral-8b-2512', name='Mistral: Ministral 3 8B 2512', provider='openrouter', cost=Cost(input=0.15, output=0.15, cache_read=0.015, cache_write=0.0), thinking=False, context_window=262144, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/ministral-3b-2512', name='Mistral: Ministral 3 3B 2512', provider='openrouter', cost=Cost(input=0.09999999999999999, output=0.09999999999999999, cache_read=0.01, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/mistral-large-2512', name='Mistral: Mistral Large 3 2512', provider='openrouter', cost=Cost(input=0.5, output=1.5, cache_read=0.049999999999999996, cache_write=0.0), thinking=False, context_window=262144, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='arcee-ai/trinity-mini', name='Arcee AI: Trinity Mini', provider='openrouter', cost=Cost(input=0.045, output=0.15, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=131072, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='deepseek/deepseek-v3.2-speciale', name='DeepSeek: DeepSeek V3.2 Speciale', provider='openrouter', cost=Cost(input=0.28700000000000003, output=0.431, cache_read=0.058, cache_write=0.0), thinking=True, context_window=163840, max_tokens=163840, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='deepseek/deepseek-v3.2', name='DeepSeek: DeepSeek V3.2', provider='openrouter', cost=Cost(input=0.252, output=0.378, cache_read=0.0252, cache_write=0.0), thinking=True, context_window=131072, max_tokens=65536, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='prime-intellect/intellect-3', name='Prime Intellect: INTELLECT-3', provider='openrouter', cost=Cost(input=0.19999999999999998, output=1.1, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=131072, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='anthropic/claude-opus-4.5', name='Anthropic: Claude Opus 4.5', provider='openrouter', cost=Cost(input=5.0, output=25.0, cache_read=0.5, cache_write=6.25), thinking=True, context_window=200000, max_tokens=64000, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='allenai/olmo-3-32b-think', name='AllenAI: Olmo 3 32B Think', provider='openrouter', cost=Cost(input=0.15, output=0.5, cache_read=0.0, cache_write=0.0), thinking=True, context_window=65536, max_tokens=65536, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemini-3-pro-image-preview', name='Google: Nano Banana Pro (Gemini 3 Pro Image Preview)', provider='openrouter', cost=Cost(input=2.0, output=12.0, cache_read=0.19999999999999998, cache_write=0.375), thinking=True, context_window=65536, max_tokens=32768, input=[Modality.Image, Modality.Text], output=[Modality.Image, Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='deepcogito/cogito-v2.1-671b', name='Deep Cogito: Cogito v2.1 671B', provider='openrouter', cost=Cost(input=1.25, output=1.25, cache_read=0.0, cache_write=0.0), thinking=True, context_window=128000, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5.1', name='OpenAI: GPT-5.1', provider='openrouter', cost=Cost(input=1.25, output=10.0, cache_read=0.13, cache_write=0.0), thinking=True, context_window=400000, max_tokens=128000, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5.1-chat', name='OpenAI: GPT-5.1 Chat', provider='openrouter', cost=Cost(input=1.25, output=10.0, cache_read=0.125, cache_write=0.0), thinking=False, context_window=128000, max_tokens=16384, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5.1-codex', name='OpenAI: GPT-5.1-Codex', provider='openrouter', cost=Cost(input=1.25, output=10.0, cache_read=0.125, cache_write=0.0), thinking=True, context_window=400000, max_tokens=128000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5.1-codex-mini', name='OpenAI: GPT-5.1-Codex-Mini', provider='openrouter', cost=Cost(input=0.25, output=2.0, cache_read=0.03, cache_write=0.0), thinking=True, context_window=400000, max_tokens=128000, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='moonshotai/kimi-k2-thinking', name='MoonshotAI: Kimi K2 Thinking', provider='openrouter', cost=Cost(input=0.6, output=2.5, cache_read=0.0, cache_write=0.0), thinking=True, context_window=262144, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='amazon/nova-premier-v1', name='Amazon: Nova Premier 1.0', provider='openrouter', cost=Cost(input=2.5, output=12.5, cache_read=0.625, cache_write=0.0), thinking=False, context_window=1000000, max_tokens=32000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='perplexity/sonar-pro-search', name='Perplexity: Sonar Pro Search', provider='openrouter', cost=Cost(input=3.0, output=15.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=200000, max_tokens=8000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/voxtral-small-24b-2507', name='Mistral: Voxtral Small 24B 2507', provider='openrouter', cost=Cost(input=0.09999999999999999, output=0.3, cache_read=0.01, cache_write=0.0), thinking=False, context_window=32000, max_tokens=16384, input=[Modality.Text, Modality.Audio], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-oss-safeguard-20b', name='OpenAI: gpt-oss-safeguard-20b', provider='openrouter', cost=Cost(input=0.075, output=0.3, cache_read=0.037, cache_write=0.0), thinking=True, context_window=131072, max_tokens=65536, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='nvidia/nemotron-nano-12b-v2-vl:free', name='NVIDIA: Nemotron Nano 12B 2 VL (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=128000, max_tokens=128000, input=[Modality.Image, Modality.Text, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='minimax/minimax-m2', name='MiniMax: MiniMax M2', provider='openrouter', cost=Cost(input=0.255, output=1.0, cache_read=0.03, cache_write=0.0), thinking=True, context_window=204800, max_tokens=196608, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-vl-32b-instruct', name='Qwen: Qwen3 VL 32B Instruct', provider='openrouter', cost=Cost(input=0.10400000000000001, output=0.41600000000000004, cache_read=0.0, cache_write=0.0), thinking=False, context_window=262144, max_tokens=32768, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='ibm-granite/granite-4.0-h-micro', name='IBM: Granite 4.0 Micro', provider='openrouter', cost=Cost(input=0.017, output=0.112, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131000, max_tokens=131000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='microsoft/phi-4-mini-instruct', name='Microsoft: Phi 4 Mini Instruct', provider='openrouter', cost=Cost(input=0.08, output=0.35, cache_read=0.08, cache_write=0.0), thinking=False, context_window=131072, max_tokens=128000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5-image-mini', name='OpenAI: GPT-5 Image Mini', provider='openrouter', cost=Cost(input=2.5, output=2.0, cache_read=0.25, cache_write=0.0), thinking=True, context_window=400000, max_tokens=128000, input=[Modality.Image, Modality.Text], output=[Modality.Image, Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='anthropic/claude-haiku-4.5', name='Anthropic: Claude Haiku 4.5', provider='openrouter', cost=Cost(input=1.0, output=5.0, cache_read=0.09999999999999999, cache_write=1.25), thinking=True, context_window=200000, max_tokens=64000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-vl-8b-thinking', name='Qwen: Qwen3 VL 8B Thinking', provider='openrouter', cost=Cost(input=0.117, output=1.365, cache_read=0.0, cache_write=0.0), thinking=True, context_window=256000, max_tokens=32768, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-vl-8b-instruct', name='Qwen: Qwen3 VL 8B Instruct', provider='openrouter', cost=Cost(input=0.08, output=0.5, cache_read=0.0, cache_write=0.0), thinking=False, context_window=256000, max_tokens=32768, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5-image', name='OpenAI: GPT-5 Image', provider='openrouter', cost=Cost(input=10.0, output=10.0, cache_read=1.25, cache_write=0.0), thinking=True, context_window=400000, max_tokens=128000, input=[Modality.Image, Modality.Text], output=[Modality.Image, Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/o3-deep-research', name='OpenAI: o3 Deep Research', provider='openrouter', cost=Cost(input=10.0, output=40.0, cache_read=2.5, cache_write=0.0), thinking=True, context_window=200000, max_tokens=100000, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/o4-mini-deep-research', name='OpenAI: o4 Mini Deep Research', provider='openrouter', cost=Cost(input=2.0, output=8.0, cache_read=0.5, cache_write=0.0), thinking=True, context_window=200000, max_tokens=100000, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='nvidia/llama-3.3-nemotron-super-49b-v1.5', name='NVIDIA: Llama 3.3 Nemotron Super 49B V1.5', provider='openrouter', cost=Cost(input=0.09999999999999999, output=0.39999999999999997, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='baidu/ernie-4.5-21b-a3b-thinking', name='Baidu: ERNIE 4.5 21B A3B Thinking', provider='openrouter', cost=Cost(input=0.07, output=0.28, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=65536, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemini-2.5-flash-image', name='Google: Nano Banana (Gemini 2.5 Flash Image)', provider='openrouter', cost=Cost(input=0.3, output=2.5, cache_read=0.03, cache_write=0.08333333333333334), thinking=False, context_window=32768, max_tokens=32768, input=[Modality.Image, Modality.Text], output=[Modality.Image, Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-vl-30b-a3b-thinking', name='Qwen: Qwen3 VL 30B A3B Thinking', provider='openrouter', cost=Cost(input=0.13, output=1.56, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=32768, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-vl-30b-a3b-instruct', name='Qwen: Qwen3 VL 30B A3B Instruct', provider='openrouter', cost=Cost(input=0.13, output=0.52, cache_read=0.0, cache_write=0.0), thinking=False, context_window=262144, max_tokens=32768, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5-pro', name='OpenAI: GPT-5 Pro', provider='openrouter', cost=Cost(input=15.0, output=120.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=400000, max_tokens=128000, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='z-ai/glm-4.6', name='Z.ai: GLM 4.6', provider='openrouter', cost=Cost(input=0.43, output=1.74, cache_read=0.08, cache_write=0.0), thinking=True, context_window=202752, max_tokens=131072, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='anthropic/claude-sonnet-4.5', name='Anthropic: Claude Sonnet 4.5', provider='openrouter', cost=Cost(input=3.0, output=15.0, cache_read=0.3, cache_write=3.75), thinking=True, context_window=1000000, max_tokens=64000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='deepseek/deepseek-v3.2-exp', name='DeepSeek: DeepSeek V3.2 Exp', provider='openrouter', cost=Cost(input=0.27, output=0.41, cache_read=0.0, cache_write=0.0), thinking=True, context_window=163840, max_tokens=65536, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='thedrummer/cydonia-24b-v4.1', name='TheDrummer: Cydonia 24B V4.1', provider='openrouter', cost=Cost(input=0.3, output=0.5, cache_read=0.15, cache_write=0.0), thinking=False, context_window=131072, max_tokens=131072, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='relace/relace-apply-3', name='Relace: Relace Apply 3', provider='openrouter', cost=Cost(input=0.85, output=1.25, cache_read=0.0, cache_write=0.0), thinking=False, context_window=256000, max_tokens=128000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemini-2.5-flash-lite-preview-09-2025', name='Google: Gemini 2.5 Flash Lite Preview 09-2025', provider='openrouter', cost=Cost(input=0.09999999999999999, output=0.39999999999999997, cache_read=0.01, cache_write=0.08333333333333334), thinking=True, context_window=1048576, max_tokens=65535, input=[Modality.Text, Modality.Image, Modality.Audio, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-vl-235b-a22b-thinking', name='Qwen: Qwen3 VL 235B A22B Thinking', provider='openrouter', cost=Cost(input=0.26, output=2.6, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=32768, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-vl-235b-a22b-instruct', name='Qwen: Qwen3 VL 235B A22B Instruct', provider='openrouter', cost=Cost(input=0.19999999999999998, output=0.88, cache_read=0.11, cache_write=0.0), thinking=False, context_window=262144, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-max', name='Qwen: Qwen3 Max', provider='openrouter', cost=Cost(input=0.78, output=3.9, cache_read=0.156, cache_write=0.975), thinking=False, context_window=262144, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-coder-plus', name='Qwen: Qwen3 Coder Plus', provider='openrouter', cost=Cost(input=0.65, output=3.25, cache_read=0.13, cache_write=0.8125), thinking=False, context_window=1000000, max_tokens=65536, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5-codex', name='OpenAI: GPT-5 Codex', provider='openrouter', cost=Cost(input=1.25, output=10.0, cache_read=0.125, cache_write=0.0), thinking=True, context_window=400000, max_tokens=128000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='deepseek/deepseek-v3.1-terminus', name='DeepSeek: DeepSeek V3.1 Terminus', provider='openrouter', cost=Cost(input=0.27, output=0.95, cache_read=0.13, cache_write=0.0), thinking=True, context_window=163840, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='alibaba/tongyi-deepresearch-30b-a3b', name='Tongyi DeepResearch 30B A3B', provider='openrouter', cost=Cost(input=0.09, output=0.44999999999999996, cache_read=0.09, cache_write=0.0), thinking=True, context_window=131072, max_tokens=131072, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-coder-flash', name='Qwen: Qwen3 Coder Flash', provider='openrouter', cost=Cost(input=0.195, output=0.975, cache_read=0.039, cache_write=0.24375), thinking=False, context_window=1000000, max_tokens=65536, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-next-80b-a3b-thinking', name='Qwen: Qwen3 Next 80B A3B Thinking', provider='openrouter', cost=Cost(input=0.0975, output=0.78, cache_read=0.0, cache_write=0.0), thinking=True, context_window=262144, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-next-80b-a3b-instruct:free', name='Qwen: Qwen3 Next 80B A3B Instruct (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=262144, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-next-80b-a3b-instruct', name='Qwen: Qwen3 Next 80B A3B Instruct', provider='openrouter', cost=Cost(input=0.09, output=1.1, cache_read=0.0, cache_write=0.0), thinking=False, context_window=262144, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen-plus-2025-07-28:thinking', name='Qwen: Qwen Plus 0728 (thinking)', provider='openrouter', cost=Cost(input=0.26, output=0.78, cache_read=0.0, cache_write=0.325), thinking=True, context_window=1000000, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen-plus-2025-07-28', name='Qwen: Qwen Plus 0728', provider='openrouter', cost=Cost(input=0.26, output=0.78, cache_read=0.0, cache_write=0.325), thinking=False, context_window=1000000, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='nvidia/nemotron-nano-9b-v2:free', name='NVIDIA: Nemotron Nano 9B V2 (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=128000, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='nvidia/nemotron-nano-9b-v2', name='NVIDIA: Nemotron Nano 9B V2', provider='openrouter', cost=Cost(input=0.04, output=0.16, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='moonshotai/kimi-k2-0905', name='MoonshotAI: Kimi K2 0905', provider='openrouter', cost=Cost(input=0.6, output=2.5, cache_read=0.0, cache_write=0.0), thinking=False, context_window=262144, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-30b-a3b-thinking-2507', name='Qwen: Qwen3 30B A3B Thinking 2507', provider='openrouter', cost=Cost(input=0.08, output=0.39999999999999997, cache_read=0.08, cache_write=0.0), thinking=True, context_window=131072, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='nousresearch/hermes-4-70b', name='Nous: Hermes 4 70B', provider='openrouter', cost=Cost(input=0.13, output=0.39999999999999997, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='nousresearch/hermes-4-405b', name='Nous: Hermes 4 405B', provider='openrouter', cost=Cost(input=1.0, output=3.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='deepseek/deepseek-chat-v3.1', name='DeepSeek: DeepSeek V3.1', provider='openrouter', cost=Cost(input=0.21, output=0.7899999999999999, cache_read=0.13, cache_write=0.0), thinking=True, context_window=163840, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-4o-audio-preview', name='OpenAI: GPT-4o Audio', provider='openrouter', cost=Cost(input=2.5, output=10.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=128000, max_tokens=16384, input=[Modality.Audio, Modality.Text], output=[Modality.Text, Modality.Audio], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/mistral-medium-3.1', name='Mistral: Mistral Medium 3.1', provider='openrouter', cost=Cost(input=0.39999999999999997, output=2.0, cache_read=0.04, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='baidu/ernie-4.5-21b-a3b', name='Baidu: ERNIE 4.5 21B A3B', provider='openrouter', cost=Cost(input=0.07, output=0.28, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=8000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='baidu/ernie-4.5-vl-28b-a3b', name='Baidu: ERNIE 4.5 VL 28B A3B', provider='openrouter', cost=Cost(input=0.14, output=0.56, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=8000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='z-ai/glm-4.5v', name='Z.ai: GLM 4.5V', provider='openrouter', cost=Cost(input=0.6, output=1.7999999999999998, cache_read=0.11, cache_write=0.0), thinking=True, context_window=65536, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='ai21/jamba-large-1.7', name='AI21: Jamba Large 1.7', provider='openrouter', cost=Cost(input=2.0, output=8.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=256000, max_tokens=4096, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5-chat', name='OpenAI: GPT-5 Chat', provider='openrouter', cost=Cost(input=1.25, output=10.0, cache_read=0.125, cache_write=0.0), thinking=False, context_window=128000, max_tokens=16384, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5', name='OpenAI: GPT-5', provider='openrouter', cost=Cost(input=1.25, output=10.0, cache_read=0.125, cache_write=0.0), thinking=True, context_window=400000, max_tokens=128000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5-mini', name='OpenAI: GPT-5 Mini', provider='openrouter', cost=Cost(input=0.25, output=2.0, cache_read=0.024999999999999998, cache_write=0.0), thinking=True, context_window=400000, max_tokens=128000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-5-nano', name='OpenAI: GPT-5 Nano', provider='openrouter', cost=Cost(input=0.049999999999999996, output=0.39999999999999997, cache_read=0.01, cache_write=0.0), thinking=True, context_window=400000, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-oss-120b:free', name='OpenAI: gpt-oss-120b (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=131072, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-oss-120b', name='OpenAI: gpt-oss-120b', provider='openrouter', cost=Cost(input=0.039, output=0.18, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-oss-20b:free', name='OpenAI: gpt-oss-20b (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=8192, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-oss-20b', name='OpenAI: gpt-oss-20b', provider='openrouter', cost=Cost(input=0.03, output=0.14, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=131072, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='anthropic/claude-opus-4.1', name='Anthropic: Claude Opus 4.1', provider='openrouter', cost=Cost(input=15.0, output=75.0, cache_read=1.5, cache_write=18.75), thinking=True, context_window=200000, max_tokens=32000, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/codestral-2508', name='Mistral: Codestral 2508', provider='openrouter', cost=Cost(input=0.3, output=0.8999999999999999, cache_read=0.03, cache_write=0.0), thinking=False, context_window=256000, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-coder-30b-a3b-instruct', name='Qwen: Qwen3 Coder 30B A3B Instruct', provider='openrouter', cost=Cost(input=0.07, output=0.27, cache_read=0.0, cache_write=0.0), thinking=False, context_window=160000, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-30b-a3b-instruct-2507', name='Qwen: Qwen3 30B A3B Instruct 2507', provider='openrouter', cost=Cost(input=0.09, output=0.3, cache_read=0.0, cache_write=0.0), thinking=False, context_window=262144, max_tokens=262144, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='z-ai/glm-4.5', name='Z.ai: GLM 4.5', provider='openrouter', cost=Cost(input=0.6, output=2.2, cache_read=0.11, cache_write=0.0), thinking=True, context_window=131072, max_tokens=98304, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='z-ai/glm-4.5-air:free', name='Z.ai: GLM 4.5 Air (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=96000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='z-ai/glm-4.5-air', name='Z.ai: GLM 4.5 Air', provider='openrouter', cost=Cost(input=0.13, output=0.85, cache_read=0.024999999999999998, cache_write=0.0), thinking=True, context_window=131072, max_tokens=98304, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-235b-a22b-thinking-2507', name='Qwen: Qwen3 235B A22B Thinking 2507', provider='openrouter', cost=Cost(input=0.14950000000000002, output=1.495, cache_read=0.0, cache_write=0.0), thinking=True, context_window=262144, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='z-ai/glm-4-32b', name='Z.ai: GLM 4 32B ', provider='openrouter', cost=Cost(input=0.09999999999999999, output=0.09999999999999999, cache_read=0.0, cache_write=0.0), thinking=False, context_window=128000, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-coder:free', name='Qwen: Qwen3 Coder 480B A35B (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=1048576, max_tokens=262000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-coder', name='Qwen: Qwen3 Coder 480B A35B', provider='openrouter', cost=Cost(input=0.22, output=1.7999999999999998, cache_read=0.0, cache_write=0.0), thinking=False, context_window=1048576, max_tokens=65536, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='bytedance/ui-tars-1.5-7b', name='ByteDance: UI-TARS 7B ', provider='openrouter', cost=Cost(input=0.09999999999999999, output=0.19999999999999998, cache_read=0.09999999999999999, cache_write=0.0), thinking=False, context_window=128000, max_tokens=2048, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemini-2.5-flash-lite', name='Google: Gemini 2.5 Flash Lite', provider='openrouter', cost=Cost(input=0.09999999999999999, output=0.39999999999999997, cache_read=0.01, cache_write=0.08333333333333334), thinking=True, context_window=1048576, max_tokens=65535, input=[Modality.Text, Modality.Image, Modality.Audio, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-235b-a22b-2507', name='Qwen: Qwen3 235B A22B Instruct 2507', provider='openrouter', cost=Cost(input=0.071, output=0.09999999999999999, cache_read=0.0, cache_write=0.0), thinking=False, context_window=262144, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='switchpoint/router', name='Switchpoint Router', provider='openrouter', cost=Cost(input=0.85, output=3.4, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='moonshotai/kimi-k2', name='MoonshotAI: Kimi K2 0711', provider='openrouter', cost=Cost(input=0.5700000000000001, output=2.3, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/devstral-medium', name='Mistral: Devstral Medium', provider='openrouter', cost=Cost(input=0.39999999999999997, output=2.0, cache_read=0.04, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/devstral-small', name='Mistral: Devstral Small 1.1', provider='openrouter', cost=Cost(input=0.09999999999999999, output=0.3, cache_read=0.01, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='cognitivecomputations/dolphin-mistral-24b-venice-edition:free', name='Venice: Uncensored (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=32768, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='tencent/hunyuan-a13b-instruct', name='Tencent: Hunyuan A13B Instruct', provider='openrouter', cost=Cost(input=0.14, output=0.5700000000000001, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=131072, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='morph/morph-v3-large', name='Morph: Morph V3 Large', provider='openrouter', cost=Cost(input=0.8999999999999999, output=1.9, cache_read=0.0, cache_write=0.0), thinking=False, context_window=262144, max_tokens=131072, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='morph/morph-v3-fast', name='Morph: Morph V3 Fast', provider='openrouter', cost=Cost(input=0.7999999999999999, output=1.2, cache_read=0.0, cache_write=0.0), thinking=False, context_window=81920, max_tokens=38000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='baidu/ernie-4.5-vl-424b-a47b', name='Baidu: ERNIE 4.5 VL 424B A47B ', provider='openrouter', cost=Cost(input=0.42, output=1.25, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=16000, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='baidu/ernie-4.5-300b-a47b', name='Baidu: ERNIE 4.5 300B A47B ', provider='openrouter', cost=Cost(input=0.28, output=1.1, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=12000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/mistral-small-3.2-24b-instruct', name='Mistral: Mistral Small 3.2 24B', provider='openrouter', cost=Cost(input=0.075, output=0.19999999999999998, cache_read=0.0, cache_write=0.0), thinking=False, context_window=128000, max_tokens=16384, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='minimax/minimax-m1', name='MiniMax: MiniMax M1', provider='openrouter', cost=Cost(input=0.39999999999999997, output=2.2, cache_read=0.0, cache_write=0.0), thinking=True, context_window=1000000, max_tokens=40000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemini-2.5-flash', name='Google: Gemini 2.5 Flash', provider='openrouter', cost=Cost(input=0.3, output=2.5, cache_read=0.03, cache_write=0.08333333333333334), thinking=True, context_window=1048576, max_tokens=65535, input=[Modality.Image, Modality.Text, Modality.Audio, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemini-2.5-pro', name='Google: Gemini 2.5 Pro', provider='openrouter', cost=Cost(input=1.25, output=10.0, cache_read=0.125, cache_write=0.375), thinking=True, context_window=1048576, max_tokens=65536, input=[Modality.Text, Modality.Image, Modality.Audio, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/o3-pro', name='OpenAI: o3 Pro', provider='openrouter', cost=Cost(input=20.0, output=80.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=200000, max_tokens=100000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemini-2.5-pro-preview', name='Google: Gemini 2.5 Pro Preview 06-05', provider='openrouter', cost=Cost(input=1.25, output=10.0, cache_read=0.125, cache_write=0.375), thinking=True, context_window=1048576, max_tokens=65536, input=[Modality.Image, Modality.Text, Modality.Audio], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='deepseek/deepseek-r1-0528', name='DeepSeek: R1 0528', provider='openrouter', cost=Cost(input=0.5, output=2.1500000000000004, cache_read=0.35, cache_write=0.0), thinking=True, context_window=163840, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='anthropic/claude-opus-4', name='Anthropic: Claude Opus 4', provider='openrouter', cost=Cost(input=15.0, output=75.0, cache_read=1.5, cache_write=18.75), thinking=True, context_window=200000, max_tokens=32000, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='anthropic/claude-sonnet-4', name='Anthropic: Claude Sonnet 4', provider='openrouter', cost=Cost(input=3.0, output=15.0, cache_read=0.3, cache_write=3.75), thinking=True, context_window=1000000, max_tokens=64000, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemma-3n-e4b-it', name='Google: Gemma 3n 4B', provider='openrouter', cost=Cost(input=0.06, output=0.12, cache_read=0.0, cache_write=0.0), thinking=False, context_window=32768, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/mistral-medium-3', name='Mistral: Mistral Medium 3', provider='openrouter', cost=Cost(input=0.39999999999999997, output=2.0, cache_read=0.04, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemini-2.5-pro-preview-05-06', name='Google: Gemini 2.5 Pro Preview 05-06', provider='openrouter', cost=Cost(input=1.25, output=10.0, cache_read=0.125, cache_write=0.375), thinking=True, context_window=1048576, max_tokens=65535, input=[Modality.Text, Modality.Image, Modality.Audio, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='arcee-ai/spotlight', name='Arcee AI: Spotlight', provider='openrouter', cost=Cost(input=0.18, output=0.18, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=65537, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='arcee-ai/maestro-reasoning', name='Arcee AI: Maestro Reasoning', provider='openrouter', cost=Cost(input=0.8999999999999999, output=3.3000000000000003, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=32000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='arcee-ai/virtuoso-large', name='Arcee AI: Virtuoso Large', provider='openrouter', cost=Cost(input=0.75, output=1.2, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=64000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='arcee-ai/coder-large', name='Arcee AI: Coder Large', provider='openrouter', cost=Cost(input=0.5, output=0.7999999999999999, cache_read=0.0, cache_write=0.0), thinking=False, context_window=32768, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='meta-llama/llama-guard-4-12b', name='Meta: Llama Guard 4 12B', provider='openrouter', cost=Cost(input=0.18, output=0.18, cache_read=0.0, cache_write=0.0), thinking=False, context_window=163840, max_tokens=16384, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-30b-a3b', name='Qwen: Qwen3 30B A3B', provider='openrouter', cost=Cost(input=0.09, output=0.44999999999999996, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=20000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-8b', name='Qwen: Qwen3 8B', provider='openrouter', cost=Cost(input=0.049999999999999996, output=0.39999999999999997, cache_read=0.049999999999999996, cache_write=0.0), thinking=True, context_window=131072, max_tokens=8192, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-14b', name='Qwen: Qwen3 14B', provider='openrouter', cost=Cost(input=0.09999999999999999, output=0.24, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131702, max_tokens=40960, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-32b', name='Qwen: Qwen3 32B', provider='openrouter', cost=Cost(input=0.08, output=0.28, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen3-235b-a22b', name='Qwen: Qwen3 235B A22B', provider='openrouter', cost=Cost(input=0.45499999999999996, output=1.8199999999999998, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=8192, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/o4-mini-high', name='OpenAI: o4 Mini High', provider='openrouter', cost=Cost(input=1.1, output=4.4, cache_read=0.275, cache_write=0.0), thinking=True, context_window=200000, max_tokens=100000, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/o3', name='OpenAI: o3', provider='openrouter', cost=Cost(input=2.0, output=8.0, cache_read=0.5, cache_write=0.0), thinking=True, context_window=200000, max_tokens=100000, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/o4-mini', name='OpenAI: o4 Mini', provider='openrouter', cost=Cost(input=1.1, output=4.4, cache_read=0.275, cache_write=0.0), thinking=True, context_window=200000, max_tokens=100000, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-4.1', name='OpenAI: GPT-4.1', provider='openrouter', cost=Cost(input=2.0, output=8.0, cache_read=0.5, cache_write=0.0), thinking=False, context_window=1047576, max_tokens=16384, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-4.1-mini', name='OpenAI: GPT-4.1 Mini', provider='openrouter', cost=Cost(input=0.39999999999999997, output=1.5999999999999999, cache_read=0.09999999999999999, cache_write=0.0), thinking=False, context_window=1047576, max_tokens=32768, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-4.1-nano', name='OpenAI: GPT-4.1 Nano', provider='openrouter', cost=Cost(input=0.09999999999999999, output=0.39999999999999997, cache_read=0.024999999999999998, cache_write=0.0), thinking=False, context_window=1047576, max_tokens=32768, input=[Modality.Image, Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='alfredpros/codellama-7b-instruct-solidity', name='AlfredPros: CodeLLaMa 7B Instruct Solidity', provider='openrouter', cost=Cost(input=0.7999999999999999, output=1.2, cache_read=0.0, cache_write=0.0), thinking=False, context_window=4096, max_tokens=4096, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='meta-llama/llama-4-maverick', name='Meta: Llama 4 Maverick', provider='openrouter', cost=Cost(input=0.15, output=0.6, cache_read=0.0, cache_write=0.0), thinking=False, context_window=1048576, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='meta-llama/llama-4-scout', name='Meta: Llama 4 Scout', provider='openrouter', cost=Cost(input=0.08, output=0.3, cache_read=0.0, cache_write=0.0), thinking=False, context_window=10000000, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='deepseek/deepseek-chat-v3-0324', name='DeepSeek: DeepSeek V3 0324', provider='openrouter', cost=Cost(input=0.19999999999999998, output=0.77, cache_read=0.135, cache_write=0.0), thinking=False, context_window=163840, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/o1-pro', name='OpenAI: o1-pro', provider='openrouter', cost=Cost(input=150.0, output=600.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=200000, max_tokens=100000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/mistral-small-3.1-24b-instruct', name='Mistral: Mistral Small 3.1 24B', provider='openrouter', cost=Cost(input=0.351, output=0.5549999999999999, cache_read=0.0, cache_write=0.0), thinking=False, context_window=128000, max_tokens=128000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemma-3-4b-it', name='Google: Gemma 3 4B', provider='openrouter', cost=Cost(input=0.04, output=0.08, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemma-3-12b-it', name='Google: Gemma 3 12B', provider='openrouter', cost=Cost(input=0.04, output=0.13, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='cohere/command-a', name='Cohere: Command A', provider='openrouter', cost=Cost(input=2.5, output=10.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=256000, max_tokens=8192, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-4o-mini-search-preview', name='OpenAI: GPT-4o-mini Search Preview', provider='openrouter', cost=Cost(input=0.15, output=0.6, cache_read=0.0, cache_write=0.0), thinking=False, context_window=128000, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-4o-search-preview', name='OpenAI: GPT-4o Search Preview', provider='openrouter', cost=Cost(input=2.5, output=10.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=128000, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='rekaai/reka-flash-3', name='Reka Flash 3', provider='openrouter', cost=Cost(input=0.09999999999999999, output=0.19999999999999998, cache_read=0.0, cache_write=0.0), thinking=True, context_window=65536, max_tokens=65536, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemma-3-27b-it', name='Google: Gemma 3 27B', provider='openrouter', cost=Cost(input=0.08, output=0.16, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='thedrummer/skyfall-36b-v2', name='TheDrummer: Skyfall 36B V2', provider='openrouter', cost=Cost(input=0.55, output=0.7999999999999999, cache_read=0.25, cache_write=0.0), thinking=False, context_window=32768, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='perplexity/sonar-reasoning-pro', name='Perplexity: Sonar Reasoning Pro', provider='openrouter', cost=Cost(input=2.0, output=8.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=128000, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='perplexity/sonar-pro', name='Perplexity: Sonar Pro', provider='openrouter', cost=Cost(input=3.0, output=15.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=200000, max_tokens=8000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='perplexity/sonar-deep-research', name='Perplexity: Sonar Deep Research', provider='openrouter', cost=Cost(input=2.0, output=8.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=128000, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemini-2.0-flash-lite-001', name='Google: Gemini 2.0 Flash Lite', provider='openrouter', cost=Cost(input=0.075, output=0.3, cache_read=0.0, cache_write=0.0), thinking=False, context_window=1048576, max_tokens=8192, input=[Modality.Text, Modality.Image, Modality.Audio, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/mistral-saba', name='Mistral: Saba', provider='openrouter', cost=Cost(input=0.19999999999999998, output=0.6, cache_read=0.02, cache_write=0.0), thinking=False, context_window=32768, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='meta-llama/llama-guard-3-8b', name='Llama Guard 3 8B', provider='openrouter', cost=Cost(input=0.48400000000000004, output=0.03, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=131072, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/o3-mini-high', name='OpenAI: o3 Mini High', provider='openrouter', cost=Cost(input=1.1, output=4.4, cache_read=0.55, cache_write=0.0), thinking=True, context_window=200000, max_tokens=100000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemini-2.0-flash-001', name='Google: Gemini 2.0 Flash', provider='openrouter', cost=Cost(input=0.09999999999999999, output=0.39999999999999997, cache_read=0.024999999999999998, cache_write=0.08333333333333334), thinking=False, context_window=1000000, max_tokens=8192, input=[Modality.Text, Modality.Image, Modality.Audio, Modality.Video], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='aion-labs/aion-1.0', name='AionLabs: Aion-1.0', provider='openrouter', cost=Cost(input=4.0, output=8.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='aion-labs/aion-1.0-mini', name='AionLabs: Aion-1.0-Mini', provider='openrouter', cost=Cost(input=0.7, output=1.4, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='aion-labs/aion-rp-llama-3.1-8b', name='AionLabs: Aion-RP 1.0 (8B)', provider='openrouter', cost=Cost(input=0.7999999999999999, output=1.5999999999999999, cache_read=0.0, cache_write=0.0), thinking=False, context_window=32768, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen2.5-vl-72b-instruct', name='Qwen: Qwen2.5 VL 72B Instruct', provider='openrouter', cost=Cost(input=0.25, output=0.75, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen-plus', name='Qwen: Qwen-Plus', provider='openrouter', cost=Cost(input=0.26, output=0.78, cache_read=0.052000000000000005, cache_write=0.325), thinking=False, context_window=1000000, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/o3-mini', name='OpenAI: o3 Mini', provider='openrouter', cost=Cost(input=1.1, output=4.4, cache_read=0.55, cache_write=0.0), thinking=True, context_window=200000, max_tokens=100000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/mistral-small-24b-instruct-2501', name='Mistral: Mistral Small 3', provider='openrouter', cost=Cost(input=0.049999999999999996, output=0.08, cache_read=0.0, cache_write=0.0), thinking=False, context_window=32768, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='deepseek/deepseek-r1-distill-qwen-32b', name='DeepSeek: R1 Distill Qwen 32B', provider='openrouter', cost=Cost(input=0.29, output=0.29, cache_read=0.0, cache_write=0.0), thinking=True, context_window=128000, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='perplexity/sonar', name='Perplexity: Sonar', provider='openrouter', cost=Cost(input=1.0, output=1.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=127072, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='deepseek/deepseek-r1-distill-llama-70b', name='DeepSeek: R1 Distill Llama 70B', provider='openrouter', cost=Cost(input=0.7, output=0.7999999999999999, cache_read=0.0, cache_write=0.0), thinking=True, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='deepseek/deepseek-r1', name='DeepSeek: R1', provider='openrouter', cost=Cost(input=0.7, output=2.5, cache_read=0.0, cache_write=0.0), thinking=True, context_window=163840, max_tokens=16000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='minimax/minimax-01', name='MiniMax: MiniMax-01', provider='openrouter', cost=Cost(input=0.19999999999999998, output=1.1, cache_read=0.0, cache_write=0.0), thinking=False, context_window=1000192, max_tokens=1000192, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='microsoft/phi-4', name='Microsoft: Phi 4', provider='openrouter', cost=Cost(input=0.065, output=0.14, cache_read=0.0, cache_write=0.0), thinking=False, context_window=16384, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='sao10k/l3.1-70b-hanami-x1', name='Sao10K: Llama 3.1 70B Hanami x1', provider='openrouter', cost=Cost(input=3.0, output=3.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=16000, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='deepseek/deepseek-chat', name='DeepSeek: DeepSeek V3', provider='openrouter', cost=Cost(input=0.32, output=0.8899999999999999, cache_read=0.0, cache_write=0.0), thinking=False, context_window=163840, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='sao10k/l3.3-euryale-70b', name='Sao10K: Llama 3.3 Euryale 70B', provider='openrouter', cost=Cost(input=0.65, output=0.75, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/o1', name='OpenAI: o1', provider='openrouter', cost=Cost(input=15.0, output=60.0, cache_read=7.5, cache_write=0.0), thinking=True, context_window=200000, max_tokens=100000, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='cohere/command-r7b-12-2024', name='Cohere: Command R7B (12-2024)', provider='openrouter', cost=Cost(input=0.0375, output=0.15, cache_read=0.0, cache_write=0.0), thinking=False, context_window=128000, max_tokens=4000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='meta-llama/llama-3.3-70b-instruct:free', name='Meta: Llama 3.3 70B Instruct (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='meta-llama/llama-3.3-70b-instruct', name='Meta: Llama 3.3 70B Instruct', provider='openrouter', cost=Cost(input=0.09999999999999999, output=0.32, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='amazon/nova-lite-v1', name='Amazon: Nova Lite 1.0', provider='openrouter', cost=Cost(input=0.06, output=0.24, cache_read=0.0, cache_write=0.0), thinking=False, context_window=300000, max_tokens=5120, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='amazon/nova-micro-v1', name='Amazon: Nova Micro 1.0', provider='openrouter', cost=Cost(input=0.035, output=0.14, cache_read=0.0, cache_write=0.0), thinking=False, context_window=128000, max_tokens=5120, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='amazon/nova-pro-v1', name='Amazon: Nova Pro 1.0', provider='openrouter', cost=Cost(input=0.7999999999999999, output=3.1999999999999997, cache_read=0.0, cache_write=0.0), thinking=False, context_window=300000, max_tokens=5120, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-4o-2024-11-20', name='OpenAI: GPT-4o (2024-11-20)', provider='openrouter', cost=Cost(input=2.5, output=10.0, cache_read=1.25, cache_write=0.0), thinking=False, context_window=128000, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/mistral-large-2411', name='Mistral Large 2411', provider='openrouter', cost=Cost(input=2.0, output=6.0, cache_read=0.19999999999999998, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/mistral-large-2407', name='Mistral Large 2407', provider='openrouter', cost=Cost(input=2.0, output=6.0, cache_read=0.19999999999999998, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/pixtral-large-2411', name='Mistral: Pixtral Large 2411', provider='openrouter', cost=Cost(input=2.0, output=6.0, cache_read=0.19999999999999998, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen-2.5-coder-32b-instruct', name='Qwen2.5 Coder 32B Instruct', provider='openrouter', cost=Cost(input=0.66, output=1.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=128000, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='thedrummer/unslopnemo-12b', name='TheDrummer: UnslopNemo 12B', provider='openrouter', cost=Cost(input=0.39999999999999997, output=0.39999999999999997, cache_read=0.0, cache_write=0.0), thinking=False, context_window=32768, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='anthropic/claude-3.5-haiku', name='Anthropic: Claude 3.5 Haiku', provider='openrouter', cost=Cost(input=0.7999999999999999, output=4.0, cache_read=0.08, cache_write=1.0), thinking=False, context_window=200000, max_tokens=8192, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='anthracite-org/magnum-v4-72b', name='Magnum v4 72B', provider='openrouter', cost=Cost(input=3.0, output=5.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=32768, max_tokens=2048, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen-2.5-7b-instruct', name='Qwen: Qwen2.5 7B Instruct', provider='openrouter', cost=Cost(input=0.04, output=0.09999999999999999, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='inflection/inflection-3-productivity', name='Inflection: Inflection 3 Productivity', provider='openrouter', cost=Cost(input=2.5, output=10.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=8000, max_tokens=1024, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='inflection/inflection-3-pi', name='Inflection: Inflection 3 Pi', provider='openrouter', cost=Cost(input=2.5, output=10.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=8000, max_tokens=1024, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='thedrummer/rocinante-12b', name='TheDrummer: Rocinante 12B', provider='openrouter', cost=Cost(input=0.16999999999999998, output=0.43, cache_read=0.0, cache_write=0.0), thinking=False, context_window=32768, max_tokens=32768, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='meta-llama/llama-3.2-11b-vision-instruct', name='Meta: Llama 3.2 11B Vision Instruct', provider='openrouter', cost=Cost(input=0.245, output=0.245, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='meta-llama/llama-3.2-1b-instruct', name='Meta: Llama 3.2 1B Instruct', provider='openrouter', cost=Cost(input=0.027, output=0.201, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=60000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='meta-llama/llama-3.2-3b-instruct:free', name='Meta: Llama 3.2 3B Instruct (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='meta-llama/llama-3.2-3b-instruct', name='Meta: Llama 3.2 3B Instruct', provider='openrouter', cost=Cost(input=0.0509, output=0.335, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=80000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='qwen/qwen-2.5-72b-instruct', name='Qwen2.5 72B Instruct', provider='openrouter', cost=Cost(input=0.36, output=0.39999999999999997, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='cohere/command-r-08-2024', name='Cohere: Command R (08-2024)', provider='openrouter', cost=Cost(input=0.15, output=0.6, cache_read=0.0, cache_write=0.0), thinking=False, context_window=128000, max_tokens=4000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='cohere/command-r-plus-08-2024', name='Cohere: Command R+ (08-2024)', provider='openrouter', cost=Cost(input=2.5, output=10.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=128000, max_tokens=4000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='sao10k/l3.1-euryale-70b', name='Sao10K: Llama 3.1 Euryale 70B v2.2', provider='openrouter', cost=Cost(input=0.85, output=0.85, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='nousresearch/hermes-3-llama-3.1-70b', name='Nous: Hermes 3 70B Instruct', provider='openrouter', cost=Cost(input=0.3, output=0.3, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='nousresearch/hermes-3-llama-3.1-405b:free', name='Nous: Hermes 3 405B Instruct (free)', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='nousresearch/hermes-3-llama-3.1-405b', name='Nous: Hermes 3 405B Instruct', provider='openrouter', cost=Cost(input=1.0, output=1.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='sao10k/l3-lunaris-8b', name='Sao10K: Llama 3 8B Lunaris', provider='openrouter', cost=Cost(input=0.04, output=0.049999999999999996, cache_read=0.0, cache_write=0.0), thinking=False, context_window=8192, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-4o-2024-08-06', name='OpenAI: GPT-4o (2024-08-06)', provider='openrouter', cost=Cost(input=2.5, output=10.0, cache_read=1.25, cache_write=0.0), thinking=False, context_window=128000, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='meta-llama/llama-3.1-70b-instruct', name='Meta: Llama 3.1 70B Instruct', provider='openrouter', cost=Cost(input=0.39999999999999997, output=0.39999999999999997, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='meta-llama/llama-3.1-8b-instruct', name='Meta: Llama 3.1 8B Instruct', provider='openrouter', cost=Cost(input=0.02, output=0.049999999999999996, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/mistral-nemo', name='Mistral: Mistral Nemo', provider='openrouter', cost=Cost(input=0.02, output=0.03, cache_read=0.0, cache_write=0.0), thinking=False, context_window=131072, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-4o-mini-2024-07-18', name='OpenAI: GPT-4o-mini (2024-07-18)', provider='openrouter', cost=Cost(input=0.15, output=0.6, cache_read=0.075, cache_write=0.0), thinking=False, context_window=128000, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-4o-mini', name='OpenAI: GPT-4o-mini', provider='openrouter', cost=Cost(input=0.15, output=0.6, cache_read=0.075, cache_write=0.0), thinking=False, context_window=128000, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='google/gemma-2-27b-it', name='Google: Gemma 2 27B', provider='openrouter', cost=Cost(input=0.65, output=0.65, cache_read=0.0, cache_write=0.0), thinking=False, context_window=8192, max_tokens=2048, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='sao10k/l3-euryale-70b', name='Sao10k: Llama 3 Euryale 70B v2.1', provider='openrouter', cost=Cost(input=1.48, output=1.48, cache_read=0.0, cache_write=0.0), thinking=False, context_window=8192, max_tokens=8192, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='nousresearch/hermes-2-pro-llama-3-8b', name='NousResearch: Hermes 2 Pro - Llama-3 8B', provider='openrouter', cost=Cost(input=0.14, output=0.14, cache_read=0.0, cache_write=0.0), thinking=False, context_window=8192, max_tokens=8192, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-4o', name='OpenAI: GPT-4o', provider='openrouter', cost=Cost(input=2.5, output=10.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=128000, max_tokens=16384, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-4o-2024-05-13', name='OpenAI: GPT-4o (2024-05-13)', provider='openrouter', cost=Cost(input=5.0, output=15.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=128000, max_tokens=4096, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='meta-llama/llama-3-70b-instruct', name='Meta: Llama 3 70B Instruct', provider='openrouter', cost=Cost(input=0.51, output=0.74, cache_read=0.0, cache_write=0.0), thinking=False, context_window=8192, max_tokens=8000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='meta-llama/llama-3-8b-instruct', name='Meta: Llama 3 8B Instruct', provider='openrouter', cost=Cost(input=0.04, output=0.04, cache_read=0.0, cache_write=0.0), thinking=False, context_window=8192, max_tokens=8192, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/mixtral-8x22b-instruct', name='Mistral: Mixtral 8x22B Instruct', provider='openrouter', cost=Cost(input=2.0, output=6.0, cache_read=0.19999999999999998, cache_write=0.0), thinking=False, context_window=65536, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='microsoft/wizardlm-2-8x22b', name='WizardLM-2 8x22B', provider='openrouter', cost=Cost(input=0.62, output=0.62, cache_read=0.0, cache_write=0.0), thinking=False, context_window=65536, max_tokens=8000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-4-turbo', name='OpenAI: GPT-4 Turbo', provider='openrouter', cost=Cost(input=10.0, output=30.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=128000, max_tokens=4096, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='anthropic/claude-3-haiku', name='Anthropic: Claude 3 Haiku', provider='openrouter', cost=Cost(input=0.25, output=1.25, cache_read=0.03, cache_write=0.3), thinking=False, context_window=200000, max_tokens=4096, input=[Modality.Text, Modality.Image], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/mistral-large', name='Mistral Large', provider='openrouter', cost=Cost(input=2.0, output=6.0, cache_read=0.19999999999999998, cache_write=0.0), thinking=False, context_window=128000, max_tokens=16384, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-3.5-turbo-0613', name='OpenAI: GPT-3.5 Turbo (older v0613)', provider='openrouter', cost=Cost(input=1.0, output=2.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=4095, max_tokens=4096, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-4-turbo-preview', name='OpenAI: GPT-4 Turbo Preview', provider='openrouter', cost=Cost(input=10.0, output=30.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=128000, max_tokens=4096, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openrouter/auto', name='Auto Router', provider='openrouter', cost=Cost(input=0.0, output=0.0, cache_read=0.0, cache_write=0.0), thinking=True, context_window=2000000, max_tokens=16384, input=[Modality.Text, Modality.Image, Modality.Audio, Modality.Video], output=[Modality.Text, Modality.Image], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-4-1106-preview', name='OpenAI: GPT-4 Turbo (older v1106)', provider='openrouter', cost=Cost(input=10.0, output=30.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=128000, max_tokens=4096, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mistralai/mistral-7b-instruct-v0.1', name='Mistral: Mistral 7B Instruct v0.1', provider='openrouter', cost=Cost(input=0.11, output=0.19, cache_read=0.0, cache_write=0.0), thinking=False, context_window=4096, max_tokens=2824, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-3.5-turbo-instruct', name='OpenAI: GPT-3.5 Turbo Instruct', provider='openrouter', cost=Cost(input=1.5, output=2.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=4095, max_tokens=4096, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-3.5-turbo-16k', name='OpenAI: GPT-3.5 Turbo 16k', provider='openrouter', cost=Cost(input=3.0, output=4.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=16385, max_tokens=4096, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='mancer/weaver', name='Mancer: Weaver (alpha)', provider='openrouter', cost=Cost(input=0.75, output=1.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=8000, max_tokens=2000, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='undi95/remm-slerp-l2-13b', name='ReMM SLERP 13B', provider='openrouter', cost=Cost(input=0.44999999999999996, output=0.65, cache_read=0.0, cache_write=0.0), thinking=False, context_window=6144, max_tokens=4096, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='gryphe/mythomax-l2-13b', name='MythoMax 13B', provider='openrouter', cost=Cost(input=0.06, output=0.06, cache_read=0.0, cache_write=0.0), thinking=False, context_window=4096, max_tokens=4096, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-4-0314', name='OpenAI: GPT-4 (older v0314)', provider='openrouter', cost=Cost(input=30.0, output=60.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=8191, max_tokens=4096, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-3.5-turbo', name='OpenAI: GPT-3.5 Turbo', provider='openrouter', cost=Cost(input=0.5, output=1.5, cache_read=0.0, cache_write=0.0), thinking=False, context_window=16385, max_tokens=4096, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+    Model(id='openai/gpt-4', name='OpenAI: GPT-4', provider='openrouter', cost=Cost(input=30.0, output=60.0, cache_read=0.0, cache_write=0.0), thinking=False, context_window=8191, max_tokens=4096, input=[Modality.Text], output=[Modality.Text], api=None, base_url=None, voices=[]),
+]