Files
letta-code/src/models.json
Charles Packer c32e43cac8 chore: misc UI improvements (#317)
Co-authored-by: Letta <noreply@letta.com>
2025-12-18 22:21:48 -08:00

422 lines
12 KiB
JSON

[
{
"id": "sonnet-4.5",
"handle": "anthropic/claude-sonnet-4-5-20250929",
"label": "Claude Sonnet 4.5 (default)",
"description": "The recommended default model (currently Sonnet 4.5)",
"isDefault": true,
"isFeatured": true,
"updateArgs": {
"context_window": 180000,
"max_output_tokens": 64000,
"max_reasoning_tokens": 31999
}
},
{
"id": "sonnet-4.5-no-reasoning",
"handle": "anthropic/claude-sonnet-4-5-20250929",
"label": "Claude Sonnet 4.5 (no reasoning)",
"description": "Sonnet 4.5 with extended thinking/reasoning explicitly disabled",
"updateArgs": {
"enable_reasoner": false,
"context_window": 180000,
"max_output_tokens": 64000
}
},
{
"id": "opus",
"handle": "anthropic/claude-opus-4-5-20251101",
"label": "Claude Opus 4.5",
"description": "Anthropic's newest flagship Opus 4.5 model",
"isFeatured": true,
"updateArgs": {
"context_window": 180000,
"max_output_tokens": 64000,
"max_reasoning_tokens": 31999
}
},
{
"id": "haiku",
"handle": "anthropic/claude-haiku-4-5-20251001",
"label": "Claude Haiku 4.5",
"description": "Anthropic's fastest model",
"isFeatured": true,
"updateArgs": {
"context_window": 180000,
"max_output_tokens": 64000
}
},
{
"id": "gpt-5-codex",
"handle": "openai/gpt-5-codex",
"label": "GPT-5-Codex",
"description": "A variant of GPT-5 optimized for agentic coding",
"updateArgs": {
"reasoning_effort": "medium",
"verbosity": "medium",
"context_window": 272000,
"max_output_tokens": 128000
}
},
{
"id": "gpt-5.2-none",
"handle": "openai/gpt-5.2",
"label": "GPT-5.2 (none)",
"description": "OpenAI's latest model (no reasoning, fastest GPT-5.2 option)",
"updateArgs": {
"reasoning_effort": "none",
"verbosity": "medium",
"context_window": 272000,
"max_output_tokens": 128000
}
},
{
"id": "gpt-5.2-low",
"handle": "openai/gpt-5.2",
"label": "GPT-5.2 (low)",
"description": "OpenAI's latest model (some reasoning enabled)",
"updateArgs": {
"reasoning_effort": "low",
"verbosity": "medium",
"context_window": 272000,
"max_output_tokens": 128000
}
},
{
"id": "gpt-5.2-medium",
"handle": "openai/gpt-5.2",
"label": "GPT-5.2 (medium)",
"description": "OpenAI's latest model (using their recommended reasoning level)",
"isFeatured": true,
"updateArgs": {
"reasoning_effort": "medium",
"verbosity": "medium",
"context_window": 272000,
"max_output_tokens": 128000
}
},
{
"id": "gpt-5.2-high",
"handle": "openai/gpt-5.2",
"label": "GPT-5.2 (high)",
"description": "OpenAI's latest model (high reasoning effort)",
"updateArgs": {
"reasoning_effort": "high",
"verbosity": "medium",
"context_window": 272000,
"max_output_tokens": 128000
}
},
{
"id": "gpt-5.2-xhigh",
"handle": "openai/gpt-5.2",
"label": "GPT-5.2 (extra-high)",
"description": "OpenAI's latest model (maximum reasoning depth)",
"updateArgs": {
"reasoning_effort": "xhigh",
"verbosity": "medium",
"context_window": 272000,
"max_output_tokens": 128000
}
},
{
"id": "gpt-5.1-none",
"handle": "openai/gpt-5.1",
"label": "GPT-5.1 (none)",
"description": "OpenAI's GPT-5.1 model (no reasoning, fastest GPT-5.1 option)",
"updateArgs": {
"reasoning_effort": "none",
"verbosity": "medium",
"context_window": 272000,
"max_output_tokens": 128000
}
},
{
"id": "gpt-5.1-low",
"handle": "openai/gpt-5.1",
"label": "GPT-5.1 (low)",
"description": "OpenAI's GPT-5.1 model (some reasoning enabled)",
"updateArgs": {
"reasoning_effort": "low",
"verbosity": "medium",
"context_window": 272000,
"max_output_tokens": 128000
}
},
{
"id": "gpt-5.1-medium",
"handle": "openai/gpt-5.1",
"label": "GPT-5.1 (medium)",
"description": "OpenAI's GPT-5.1 model (using their recommended reasoning level)",
"updateArgs": {
"reasoning_effort": "medium",
"verbosity": "medium",
"context_window": 272000,
"max_output_tokens": 128000
}
},
{
"id": "gpt-5.1-high",
"handle": "openai/gpt-5.1",
"label": "GPT-5.1 (high)",
"description": "OpenAI's GPT-5.1 model (maximum reasoning depth)",
"updateArgs": {
"reasoning_effort": "high",
"verbosity": "medium",
"context_window": 272000,
"max_output_tokens": 128000
}
},
{
"id": "gpt-5.1-codex-none",
"handle": "openai/gpt-5.1-codex",
"label": "GPT-5.1-Codex (none)",
"description": "GPT-5.1-Codex with no reasoning (fastest Codex option)",
"updateArgs": {
"reasoning_effort": "none",
"verbosity": "medium",
"context_window": 272000,
"max_output_tokens": 128000
}
},
{
"id": "gpt-5.1-codex-medium",
"handle": "openai/gpt-5.1-codex",
"label": "GPT-5.1-Codex (medium)",
"description": "GPT-5.1-Codex with recommended reasoning level",
"isFeatured": true,
"updateArgs": {
"reasoning_effort": "medium",
"verbosity": "medium",
"context_window": 272000,
"max_output_tokens": 128000
}
},
{
"id": "gpt-5.1-codex-high",
"handle": "openai/gpt-5.1-codex",
"label": "GPT-5.1-Codex (high)",
"description": "GPT-5.1-Codex with maximum reasoning depth",
"updateArgs": {
"reasoning_effort": "high",
"verbosity": "medium",
"context_window": 272000,
"max_output_tokens": 128000
}
},
{
"id": "gpt-5.1-codex-max-medium",
"handle": "openai/gpt-5.1-codex-max",
"label": "GPT-5.1-Codex (max-medium)",
"description": "GPT-5.1-Codex with maximum capabilities enabled",
"updateArgs": {
"reasoning_effort": "medium",
"verbosity": "medium",
"context_window": 272000,
"max_output_tokens": 128000
}
},
{
"id": "gpt-5.1-codex-max-high",
"handle": "openai/gpt-5.1-codex-max",
"label": "GPT-5.1-Codex (max-high)",
"description": "GPT-5.1-Codex with maximum capabilities enabled",
"updateArgs": {
"reasoning_effort": "high",
"verbosity": "medium",
"context_window": 272000,
"max_output_tokens": 128000
}
},
{
"id": "gpt-5.1-codex-max-x-high",
"handle": "openai/gpt-5.1-codex-max",
"label": "GPT-5.1-Codex (max-x-high)",
"description": "GPT-5.1-Codex with maximum capabilities enabled",
"updateArgs": {
"reasoning_effort": "xhigh",
"verbosity": "medium",
"context_window": 272000,
"max_output_tokens": 128000
}
},
{
"id": "gpt-5-minimal",
"handle": "openai/gpt-5",
"label": "GPT-5 (minimal)",
"description": "OpenAI's latest model (limited reasoning, fastest GPT-5 option)",
"updateArgs": {
"reasoning_effort": "minimal",
"verbosity": "medium",
"context_window": 272000
}
},
{
"id": "gpt-5-low",
"handle": "openai/gpt-5",
"label": "GPT-5 (low)",
"description": "OpenAI's latest model (some reasoning enabled)",
"updateArgs": {
"reasoning_effort": "low",
"verbosity": "medium",
"context_window": 272000
}
},
{
"id": "gpt-5-medium",
"handle": "openai/gpt-5",
"label": "GPT-5 (medium)",
"description": "OpenAI's latest model (using their recommended reasoning level)",
"updateArgs": {
"reasoning_effort": "medium",
"verbosity": "medium",
"context_window": 272000
}
},
{
"id": "gpt-5-high",
"handle": "openai/gpt-5",
"label": "GPT-5 (high)",
"description": "OpenAI's latest model (maximum reasoning depth)",
"updateArgs": {
"reasoning_effort": "high",
"verbosity": "medium",
"context_window": 272000
}
},
{
"id": "gpt-5-mini-medium",
"handle": "openai/gpt-5-mini-2025-08-07",
"label": "GPT-5-Mini (medium)",
"description": "OpenAI's latest mini model (using their recommended reasoning level)",
"updateArgs": {
"reasoning_effort": "medium",
"verbosity": "medium",
"context_window": 272000
}
},
{
"id": "gpt-5-nano-medium",
"handle": "openai/gpt-5-nano-2025-08-07",
"label": "GPT-5-Nano (medium)",
"description": "OpenAI's latest nano model (using their recommended reasoning level)",
"updateArgs": {
"reasoning_effort": "medium",
"verbosity": "medium",
"context_window": 272000
}
},
{
"id": "glm-4.6",
"handle": "openrouter/z-ai/glm-4.6:exacto",
"label": "GLM-4.6",
"description": "The best open weights coding model",
"updateArgs": {
"context_window": 200000
}
},
{
"id": "minimax-m2",
"handle": "openrouter/minimax/minimax-m2",
"label": "Minimax M2",
"description": "Minimax's latest model",
"updateArgs": {
"context_window": 196000
}
},
{
"id": "kimi-k2",
"handle": "openrouter/moonshotai/kimi-k2-0905",
"label": "Kimi K2",
"description": "Kimi's latest model",
"updateArgs": {
"context_window": 262144
}
},
{
"id": "kimi-k2-thinking",
"handle": "openrouter/moonshotai/kimi-k2-thinking",
"label": "Kimi K2 Thinking",
"description": "Kimi's K2 model with advanced thinking capabilities",
"updateArgs": {
"context_window": 256000,
"max_output_tokens": 16000,
"temperature": 1.0
}
},
{
"id": "deepseek-chat-v3.1",
"handle": "openrouter/deepseek/deepseek-chat-v3.1",
"label": "DeepSeek Chat V3.1",
"description": "DeepSeek V3.1 model",
"updateArgs": {
"context_window": 128000
}
},
{
"id": "gemini-3",
"handle": "google_ai/gemini-3-pro-preview",
"label": "Gemini 3 Pro",
"description": "Google's smartest model",
"isFeatured": true,
"updateArgs": { "context_window": 180000, "temperature": 1.0 }
},
{
"id": "gemini-3-flash",
"handle": "google_ai/gemini-3-flash-preview",
"label": "Gemini 3 Flash",
"description": "Google's fastest Gemini 3 model",
"isFeatured": true,
"updateArgs": { "context_window": 180000, "temperature": 1.0 }
},
{
"id": "gemini-flash",
"handle": "google_ai/gemini-2.5-flash",
"label": "Gemini 2.5 Flash",
"description": "Google's fastest model",
"updateArgs": { "context_window": 180000 }
},
{
"id": "gemini-pro",
"handle": "google_ai/gemini-2.5-pro",
"label": "Gemini 2.5 Pro",
"description": "Google's last generation flagship model",
"updateArgs": { "context_window": 180000 }
},
{
"id": "gpt-4.1",
"handle": "openai/gpt-4.1",
"label": "GPT-4.1",
"description": "OpenAI's most recent non-reasoner model",
"updateArgs": { "context_window": 1047576 }
},
{
"id": "gpt-4.1-mini",
"handle": "openai/gpt-4.1-mini-2025-04-14",
"label": "GPT-4.1-Mini",
"description": "OpenAI's most recent non-reasoner model (mini version)",
"updateArgs": { "context_window": 1047576 }
},
{
"id": "gpt-4.1-nano",
"handle": "openai/gpt-4.1-nano-2025-04-14",
"label": "GPT-4.1-Nano",
"description": "OpenAI's most recent non-reasoner model (nano version)",
"updateArgs": { "context_window": 1047576 }
},
{
"id": "o4-mini",
"handle": "openai/o4-mini",
"label": "o4-mini",
"description": "OpenAI's latest o-series reasoning model",
"updateArgs": { "context_window": 180000 }
},
{
"id": "gemini-3-vertex",
"handle": "google_vertex/gemini-3-pro-preview",
"label": "Gemini 3 Pro (Vertex AI)",
"description": "Google's smartest Gemini 3 Pro model on Vertex AI",
"updateArgs": { "context_window": 180000, "temperature": 1.0 }
}
]