feat: initial model catalog with 196 models across 39 providers

Community-maintained TOML catalog for LibreFang. New models can be added
via PR without requiring a LibreFang binary release.

Includes validation script, bilingual docs, and GitHub templates.

providers/ai21.toml

@@ -0,0 +1,48 @@
+# AI21 Labs — https://ai21.com
+# Models: 3
+
+[provider]
+id = "ai21"
+display_name = "AI21 Labs"
+api_key_env = "AI21_API_KEY"
+base_url = "https://api.ai21.com/studio/v1"
+key_required = true
+
+[[models]]
+id = "jamba-1.5-large"
+display_name = "Jamba 1.5 Large"
+tier = "smart"
+context_window = 256000
+max_output_tokens = 4096
+input_cost_per_m = 2.0
+output_cost_per_m = 8.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["jamba"]
+
+[[models]]
+id = "jamba-1.5-mini"
+display_name = "Jamba 1.5 Mini"
+tier = "fast"
+context_window = 256000
+max_output_tokens = 4096
+input_cost_per_m = 0.20
+output_cost_per_m = 0.40
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "jamba-instruct"
+display_name = "Jamba Instruct"
+tier = "balanced"
+context_window = 256000
+max_output_tokens = 4096
+input_cost_per_m = 0.50
+output_cost_per_m = 0.70
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []

providers/anthropic.toml

@@ -0,0 +1,100 @@
+# Anthropic — https://anthropic.com
+# Models: 7
+
+[provider]
+id = "anthropic"
+display_name = "Anthropic"
+api_key_env = "ANTHROPIC_API_KEY"
+base_url = "https://api.anthropic.com"
+key_required = true
+
+[[models]]
+id = "claude-opus-4-6"
+display_name = "Claude Opus 4.6"
+tier = "frontier"
+context_window = 200000
+max_output_tokens = 128000
+input_cost_per_m = 5.0
+output_cost_per_m = 25.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["opus", "claude-opus"]
+
+[[models]]
+id = "claude-sonnet-4-6"
+display_name = "Claude Sonnet 4.6"
+tier = "smart"
+context_window = 200000
+max_output_tokens = 64000
+input_cost_per_m = 3.0
+output_cost_per_m = 15.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["sonnet", "claude-sonnet"]
+
+[[models]]
+id = "claude-opus-4-20250514"
+display_name = "Claude Opus 4"
+tier = "frontier"
+context_window = 200000
+max_output_tokens = 32000
+input_cost_per_m = 15.0
+output_cost_per_m = 75.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "claude-sonnet-4-20250514"
+display_name = "Claude Sonnet 4"
+tier = "smart"
+context_window = 200000
+max_output_tokens = 64000
+input_cost_per_m = 3.0
+output_cost_per_m = 15.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "claude-haiku-4-5-20251001"
+display_name = "Claude Haiku 4.5"
+tier = "fast"
+context_window = 200000
+max_output_tokens = 8192
+input_cost_per_m = 0.25
+output_cost_per_m = 1.25
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["haiku", "claude-haiku"]
+
+[[models]]
+id = "claude-sonnet-4-5-20250514"
+display_name = "Claude Sonnet 4.5"
+tier = "smart"
+context_window = 200000
+max_output_tokens = 64000
+input_cost_per_m = 3.0
+output_cost_per_m = 15.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "claude-3-5-sonnet-20241022"
+display_name = "Claude 3.5 Sonnet"
+tier = "smart"
+context_window = 200000
+max_output_tokens = 8192
+input_cost_per_m = 3.0
+output_cost_per_m = 15.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []

providers/bedrock.toml

@@ -0,0 +1,113 @@
+# AWS Bedrock — https://aws.amazon.com/bedrock
+# Models: 8
+
+[provider]
+id = "bedrock"
+display_name = "AWS Bedrock"
+api_key_env = "AWS_ACCESS_KEY_ID"
+base_url = "https://bedrock-runtime.us-east-1.amazonaws.com"
+key_required = true
+
+[[models]]
+id = "bedrock/anthropic.claude-opus-4-6"
+display_name = "Claude Opus 4.6 (Bedrock)"
+tier = "frontier"
+context_window = 200000
+max_output_tokens = 128000
+input_cost_per_m = 5.00
+output_cost_per_m = 25.00
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "bedrock/anthropic.claude-sonnet-4-6"
+display_name = "Claude Sonnet 4.6 (Bedrock)"
+tier = "smart"
+context_window = 200000
+max_output_tokens = 64000
+input_cost_per_m = 3.00
+output_cost_per_m = 15.00
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "bedrock/anthropic.claude-opus-4-20250514"
+display_name = "Claude Opus 4 (Bedrock)"
+tier = "frontier"
+context_window = 200000
+max_output_tokens = 32000
+input_cost_per_m = 15.00
+output_cost_per_m = 75.00
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "bedrock/anthropic.claude-sonnet-4-20250514"
+display_name = "Claude Sonnet 4 (Bedrock)"
+tier = "smart"
+context_window = 200000
+max_output_tokens = 64000
+input_cost_per_m = 3.00
+output_cost_per_m = 15.00
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "bedrock/anthropic.claude-haiku-4-5-20251001"
+display_name = "Claude Haiku 4.5 (Bedrock)"
+tier = "fast"
+context_window = 200000
+max_output_tokens = 8192
+input_cost_per_m = 0.25
+output_cost_per_m = 1.25
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "bedrock/amazon.nova-pro-v1:0"
+display_name = "Amazon Nova Pro (Bedrock)"
+tier = "smart"
+context_window = 300000
+max_output_tokens = 5120
+input_cost_per_m = 0.80
+output_cost_per_m = 3.20
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "bedrock/amazon.nova-lite-v1:0"
+display_name = "Amazon Nova Lite (Bedrock)"
+tier = "fast"
+context_window = 300000
+max_output_tokens = 5120
+input_cost_per_m = 0.06
+output_cost_per_m = 0.24
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "bedrock/meta.llama3-3-70b-instruct-v1:0"
+display_name = "Llama 3.3 70B (Bedrock)"
+tier = "balanced"
+context_window = 128000
+max_output_tokens = 4096
+input_cost_per_m = 0.72
+output_cost_per_m = 0.72
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []

providers/cerebras.toml

@@ -0,0 +1,61 @@
+# Cerebras — https://cerebras.ai
+# Models: 4
+
+[provider]
+id = "cerebras"
+display_name = "Cerebras"
+api_key_env = "CEREBRAS_API_KEY"
+base_url = "https://api.cerebras.ai/v1"
+key_required = true
+
+[[models]]
+id = "cerebras/llama3.3-70b"
+display_name = "Llama 3.3 70B (Cerebras)"
+tier = "balanced"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 0.06
+output_cost_per_m = 0.06
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "cerebras/llama3.1-8b"
+display_name = "Llama 3.1 8B (Cerebras)"
+tier = "fast"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 0.01
+output_cost_per_m = 0.01
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "cerebras/llama-4-scout-17b"
+display_name = "Llama 4 Scout (Cerebras)"
+tier = "smart"
+context_window = 512000
+max_output_tokens = 8192
+input_cost_per_m = 0.10
+output_cost_per_m = 0.10
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "cerebras/qwen-2.5-32b"
+display_name = "Qwen 2.5 32B (Cerebras)"
+tier = "balanced"
+context_window = 32768
+max_output_tokens = 8192
+input_cost_per_m = 0.06
+output_cost_per_m = 0.06
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []

providers/chatgpt.toml

@@ -0,0 +1,74 @@
+# ChatGPT (Session Auth / Codex Responses API) — https://chatgpt.com
+# Models: 5 (free with ChatGPT subscription via OAuth session)
+
+[provider]
+id = "chatgpt"
+display_name = "ChatGPT (Session Auth)"
+api_key_env = "CHATGPT_SESSION_TOKEN"
+base_url = "https://chatgpt.com/backend-api"
+key_required = true
+
+[[models]]
+id = "gpt-5.4-codex"
+display_name = "GPT-5.4 Codex"
+tier = "frontier"
+context_window = 200000
+max_output_tokens = 65536
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["chatgpt-5.4"]
+
+[[models]]
+id = "gpt-5.3-codex"
+display_name = "GPT-5.3 Codex"
+tier = "frontier"
+context_window = 200000
+max_output_tokens = 65536
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["chatgpt-5.3"]
+
+[[models]]
+id = "gpt-5.2-codex"
+display_name = "GPT-5.2 Codex"
+tier = "smart"
+context_window = 200000
+max_output_tokens = 65536
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["chatgpt-5.2"]
+
+[[models]]
+id = "gpt-5.1-codex"
+display_name = "GPT-5.1 Codex"
+tier = "smart"
+context_window = 200000
+max_output_tokens = 65536
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["chatgpt-5.1"]
+
+[[models]]
+id = "gpt-5.1-codex-mini"
+display_name = "GPT-5.1 Codex Mini"
+tier = "balanced"
+context_window = 200000
+max_output_tokens = 65536
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["chatgpt-mini", "chatgpt"]

providers/chutes.toml

@@ -0,0 +1,74 @@
+# Chutes.ai — https://chutes.ai
+# Models: 5
+
+[provider]
+id = "chutes"
+display_name = "Chutes.ai"
+api_key_env = "CHUTES_API_KEY"
+base_url = "https://llm.chutes.ai/v1"
+key_required = true
+
+[[models]]
+id = "chutes/deepseek-ai/DeepSeek-V3"
+display_name = "DeepSeek V3 (Chutes)"
+tier = "smart"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 0.25
+output_cost_per_m = 0.35
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["chutes-deepseek-v3"]
+
+[[models]]
+id = "chutes/deepseek-ai/DeepSeek-R1"
+display_name = "DeepSeek R1 (Chutes)"
+tier = "smart"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 0.55
+output_cost_per_m = 2.19
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = ["chutes-deepseek-r1"]
+
+[[models]]
+id = "chutes/meta-llama/Llama-4-Maverick-17B-128E-Instruct"
+display_name = "Llama 4 Maverick (Chutes)"
+tier = "balanced"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 0.20
+output_cost_per_m = 0.30
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["chutes-llama-maverick"]
+
+[[models]]
+id = "chutes/Qwen/Qwen3-235B-A22B"
+display_name = "Qwen3 235B (Chutes)"
+tier = "smart"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 0.25
+output_cost_per_m = 0.35
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["chutes-qwen3"]
+
+[[models]]
+id = "chutes/meta-llama/Llama-3.3-70B-Instruct"
+display_name = "Llama 3.3 70B (Chutes)"
+tier = "balanced"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 0.10
+output_cost_per_m = 0.15
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["chutes-llama-70b"]

providers/claude-code.toml

@@ -0,0 +1,48 @@
+# Claude Code CLI — subprocess-based provider
+# Models: 3 (requires `claude` CLI installed)
+
+[provider]
+id = "claude-code"
+display_name = "Claude Code"
+api_key_env = ""
+base_url = ""
+key_required = false
+
+[[models]]
+id = "claude-code/opus"
+display_name = "Claude Opus (CLI)"
+tier = "frontier"
+context_window = 200000
+max_output_tokens = 128000
+input_cost_per_m = 5.0
+output_cost_per_m = 25.0
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = ["claude-code-opus"]
+
+[[models]]
+id = "claude-code/sonnet"
+display_name = "Claude Sonnet (CLI)"
+tier = "smart"
+context_window = 200000
+max_output_tokens = 64000
+input_cost_per_m = 3.0
+output_cost_per_m = 15.0
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = ["claude-code", "claude-code-sonnet"]
+
+[[models]]
+id = "claude-code/haiku"
+display_name = "Claude Haiku (CLI)"
+tier = "fast"
+context_window = 200000
+max_output_tokens = 8192
+input_cost_per_m = 0.25
+output_cost_per_m = 1.25
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = ["claude-code-haiku"]

providers/cohere.toml

@@ -0,0 +1,61 @@
+# Cohere — https://cohere.com
+# Models: 4
+
+[provider]
+id = "cohere"
+display_name = "Cohere"
+api_key_env = "COHERE_API_KEY"
+base_url = "https://api.cohere.com/v2"
+key_required = true
+
+[[models]]
+id = "command-r-plus"
+display_name = "Command R+"
+tier = "smart"
+context_window = 128000
+max_output_tokens = 4096
+input_cost_per_m = 2.50
+output_cost_per_m = 10.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["command-r"]
+
+[[models]]
+id = "command-r-08-2024"
+display_name = "Command R (Aug 2024)"
+tier = "balanced"
+context_window = 128000
+max_output_tokens = 4096
+input_cost_per_m = 0.15
+output_cost_per_m = 0.60
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "command-a"
+display_name = "Command A"
+tier = "smart"
+context_window = 256000
+max_output_tokens = 8192
+input_cost_per_m = 2.50
+output_cost_per_m = 10.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["command"]
+
+[[models]]
+id = "command-light"
+display_name = "Command Light"
+tier = "fast"
+context_window = 4096
+max_output_tokens = 4096
+input_cost_per_m = 0.30
+output_cost_per_m = 0.60
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []

providers/deepseek.toml

@@ -0,0 +1,61 @@
+# DeepSeek — https://deepseek.com
+# Models: 4
+
+[provider]
+id = "deepseek"
+display_name = "DeepSeek"
+api_key_env = "DEEPSEEK_API_KEY"
+base_url = "https://api.deepseek.com/v1"
+key_required = true
+
+[[models]]
+id = "deepseek-chat"
+display_name = "DeepSeek V3"
+tier = "smart"
+context_window = 64000
+max_output_tokens = 8192
+input_cost_per_m = 0.27
+output_cost_per_m = 1.10
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["deepseek", "deepseek-v3"]
+
+[[models]]
+id = "deepseek-reasoner"
+display_name = "DeepSeek R1"
+tier = "frontier"
+context_window = 64000
+max_output_tokens = 8192
+input_cost_per_m = 0.55
+output_cost_per_m = 2.19
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = ["deepseek-r1"]
+
+[[models]]
+id = "deepseek-coder"
+display_name = "DeepSeek Coder V2"
+tier = "balanced"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 0.14
+output_cost_per_m = 0.28
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "deepseek-chat-v3-0324"
+display_name = "DeepSeek V3 0324"
+tier = "smart"
+context_window = 64000
+max_output_tokens = 8192
+input_cost_per_m = 0.27
+output_cost_per_m = 1.10
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []

providers/fireworks.toml

@@ -0,0 +1,74 @@
+# Fireworks AI — https://fireworks.ai
+# Models: 5
+
+[provider]
+id = "fireworks"
+display_name = "Fireworks AI"
+api_key_env = "FIREWORKS_API_KEY"
+base_url = "https://api.fireworks.ai/inference/v1"
+key_required = true
+
+[[models]]
+id = "accounts/fireworks/models/llama-v3p1-405b-instruct"
+display_name = "Llama 3.1 405B (Fireworks)"
+tier = "frontier"
+context_window = 131072
+max_output_tokens = 16384
+input_cost_per_m = 3.00
+output_cost_per_m = 3.00
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "accounts/fireworks/models/llama-v3p3-70b-instruct"
+display_name = "Llama 3.3 70B (Fireworks)"
+tier = "smart"
+context_window = 131072
+max_output_tokens = 16384
+input_cost_per_m = 0.90
+output_cost_per_m = 0.90
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "accounts/fireworks/models/deepseek-r1"
+display_name = "DeepSeek R1 (Fireworks)"
+tier = "frontier"
+context_window = 64000
+max_output_tokens = 8192
+input_cost_per_m = 3.00
+output_cost_per_m = 8.00
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "accounts/fireworks/models/deepseek-v3"
+display_name = "DeepSeek V3 (Fireworks)"
+tier = "smart"
+context_window = 64000
+max_output_tokens = 8192
+input_cost_per_m = 0.90
+output_cost_per_m = 0.90
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "accounts/fireworks/models/mixtral-8x22b-instruct"
+display_name = "Mixtral 8x22B (Fireworks)"
+tier = "balanced"
+context_window = 65536
+max_output_tokens = 4096
+input_cost_per_m = 0.90
+output_cost_per_m = 0.90
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []

providers/gemini.toml

@@ -0,0 +1,139 @@
+# Google Gemini — https://ai.google.dev
+# Models: 10
+
+[provider]
+id = "gemini"
+display_name = "Google Gemini"
+api_key_env = "GEMINI_API_KEY"
+base_url = "https://generativelanguage.googleapis.com"
+key_required = true
+
+[[models]]
+id = "gemini-3.1-pro-preview"
+display_name = "Gemini 3.1 Pro Preview"
+tier = "frontier"
+context_window = 1048576
+max_output_tokens = 65536
+input_cost_per_m = 2.50
+output_cost_per_m = 15.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["gemini-pro"]
+
+[[models]]
+id = "gemini-3-flash-preview"
+display_name = "Gemini 3 Flash Preview"
+tier = "smart"
+context_window = 1048576
+max_output_tokens = 65536
+input_cost_per_m = 0.15
+output_cost_per_m = 0.60
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["gemini-flash"]
+
+[[models]]
+id = "gemini-3.1-flash-lite-preview"
+display_name = "Gemini 3.1 Flash Lite Preview"
+tier = "fast"
+context_window = 1048576
+max_output_tokens = 8192
+input_cost_per_m = 0.04
+output_cost_per_m = 0.15
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "gemini-2.5-flash-lite"
+display_name = "Gemini 2.5 Flash Lite"
+tier = "fast"
+context_window = 1048576
+max_output_tokens = 8192
+input_cost_per_m = 0.04
+output_cost_per_m = 0.15
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "gemini-2.5-pro"
+display_name = "Gemini 2.5 Pro"
+tier = "frontier"
+context_window = 1048576
+max_output_tokens = 65536
+input_cost_per_m = 1.25
+output_cost_per_m = 10.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "gemini-2.5-flash"
+display_name = "Gemini 2.5 Flash"
+tier = "smart"
+context_window = 1048576
+max_output_tokens = 65536
+input_cost_per_m = 0.15
+output_cost_per_m = 0.60
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["flash"]
+
+[[models]]
+id = "gemini-2.0-flash"
+display_name = "Gemini 2.0 Flash"
+tier = "fast"
+context_window = 1048576
+max_output_tokens = 8192
+input_cost_per_m = 0.10
+output_cost_per_m = 0.40
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "gemini-2.0-flash-lite"
+display_name = "Gemini 2.0 Flash Lite"
+tier = "fast"
+context_window = 1048576
+max_output_tokens = 8192
+input_cost_per_m = 0.075
+output_cost_per_m = 0.30
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "gemini-1.5-pro"
+display_name = "Gemini 1.5 Pro"
+tier = "smart"
+context_window = 2097152
+max_output_tokens = 8192
+input_cost_per_m = 1.25
+output_cost_per_m = 5.00
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "gemini-1.5-flash"
+display_name = "Gemini 1.5 Flash"
+tier = "fast"
+context_window = 1048576
+max_output_tokens = 8192
+input_cost_per_m = 0.075
+output_cost_per_m = 0.30
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []

providers/github-copilot.toml

@@ -0,0 +1,35 @@
+# GitHub Copilot — https://github.com/features/copilot
+# Models: 2 (free for GitHub Copilot subscribers)
+
+[provider]
+id = "github-copilot"
+display_name = "GitHub Copilot"
+api_key_env = "GITHUB_TOKEN"
+base_url = "https://api.githubcopilot.com"
+key_required = true
+
+[[models]]
+id = "copilot/gpt-4o"
+display_name = "GPT-4o (Copilot)"
+tier = "smart"
+context_window = 128000
+max_output_tokens = 4096
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["copilot-gpt4o"]
+
+[[models]]
+id = "copilot/gpt-4"
+display_name = "GPT-4 (Copilot)"
+tier = "frontier"
+context_window = 128000
+max_output_tokens = 4096
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["copilot-gpt4"]

providers/groq.toml

@@ -0,0 +1,140 @@
+# Groq — https://groq.com
+# Models: 10
+
+[provider]
+id = "groq"
+display_name = "Groq"
+api_key_env = "GROQ_API_KEY"
+base_url = "https://api.groq.com/openai/v1"
+key_required = true
+
+[[models]]
+id = "llama-3.3-70b-versatile"
+display_name = "Llama 3.3 70B"
+tier = "balanced"
+context_window = 128000
+max_output_tokens = 32768
+input_cost_per_m = 0.059
+output_cost_per_m = 0.079
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["llama", "llama-70b"]
+
+[[models]]
+id = "llama-3.1-8b-instant"
+display_name = "Llama 3.1 8B"
+tier = "fast"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 0.05
+output_cost_per_m = 0.08
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "llama-3.2-90b-vision-preview"
+display_name = "Llama 3.2 90B Vision"
+tier = "smart"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 0.90
+output_cost_per_m = 0.90
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "llama-3.2-11b-vision-preview"
+display_name = "Llama 3.2 11B Vision"
+tier = "balanced"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 0.18
+output_cost_per_m = 0.18
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "llama-3.2-3b-preview"
+display_name = "Llama 3.2 3B"
+tier = "fast"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 0.06
+output_cost_per_m = 0.06
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "llama-3.2-1b-preview"
+display_name = "Llama 3.2 1B"
+tier = "fast"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 0.04
+output_cost_per_m = 0.04
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "mixtral-8x7b-32768"
+display_name = "Mixtral 8x7B"
+tier = "balanced"
+context_window = 32768
+max_output_tokens = 4096
+input_cost_per_m = 0.024
+output_cost_per_m = 0.024
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["mixtral"]
+
+[[models]]
+id = "gemma2-9b-it"
+display_name = "Gemma 2 9B"
+tier = "fast"
+context_window = 8192
+max_output_tokens = 4096
+input_cost_per_m = 0.02
+output_cost_per_m = 0.02
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "qwen-qwq-32b"
+display_name = "Qwen QWQ 32B"
+tier = "balanced"
+context_window = 128000
+max_output_tokens = 16384
+input_cost_per_m = 0.20
+output_cost_per_m = 0.20
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "meta-llama/llama-4-scout-17b-16e-instruct"
+display_name = "Llama 4 Scout 17B"
+tier = "balanced"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 0.11
+output_cost_per_m = 0.34
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+

providers/huggingface.toml

@@ -0,0 +1,48 @@
+# Hugging Face — https://huggingface.co
+# Models: 3 (static entries; additional models discovered dynamically at runtime)
+
+[provider]
+id = "huggingface"
+display_name = "Hugging Face"
+api_key_env = "HF_API_KEY"
+base_url = "https://api-inference.huggingface.co/v1"
+key_required = true
+
+[[models]]
+id = "hf/meta-llama/Llama-3.3-70B-Instruct"
+display_name = "Llama 3.3 70B (HF)"
+tier = "balanced"
+context_window = 128000
+max_output_tokens = 4096
+input_cost_per_m = 0.30
+output_cost_per_m = 0.30
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "hf/deepseek-ai/DeepSeek-R1"
+display_name = "DeepSeek R1 (HF)"
+tier = "smart"
+context_window = 64000
+max_output_tokens = 4096
+input_cost_per_m = 0.30
+output_cost_per_m = 0.30
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "hf/Qwen/Qwen2.5-72B-Instruct"
+display_name = "Qwen 2.5 72B (HF)"
+tier = "balanced"
+context_window = 32768
+max_output_tokens = 4096
+input_cost_per_m = 0.30
+output_cost_per_m = 0.30
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = []

providers/kimi-coding.toml

@@ -0,0 +1,22 @@
+# Kimi for Code — https://api.kimi.com
+# Models: 1
+
+[provider]
+id = "kimi_coding"
+display_name = "Kimi for Code"
+api_key_env = "KIMI_API_KEY"
+base_url = "https://api.kimi.com/coding"
+key_required = true
+
+[[models]]
+id = "kimi-for-coding"
+display_name = "Kimi For Coding"
+tier = "frontier"
+context_window = 262144
+max_output_tokens = 32768
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []

providers/lemonade.toml

@@ -0,0 +1,9 @@
+# Lemonade — local NPU accelerated inference
+# Models: 0 (all models discovered dynamically at runtime)
+
+[provider]
+id = "lemonade"
+display_name = "Lemonade"
+api_key_env = "LEMONADE_API_KEY"
+base_url = "http://localhost:8888/api/v1"
+key_required = false

providers/lmstudio.toml

@@ -0,0 +1,22 @@
+# LM Studio — https://lmstudio.ai
+# Models: 1 (generic entry; additional models discovered dynamically at runtime)
+
+[provider]
+id = "lmstudio"
+display_name = "LM Studio"
+api_key_env = "LMSTUDIO_API_KEY"
+base_url = "http://localhost:1234/v1"
+key_required = false
+
+[[models]]
+id = "lmstudio-local"
+display_name = "LM Studio Local Model"
+tier = "local"
+context_window = 32768
+max_output_tokens = 4096
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []

providers/minimax-cn.toml

@@ -0,0 +1,87 @@
+# MiniMax (China) — https://minimaxi.com
+# Models: 6 (same models as international, different endpoint)
+
+[provider]
+id = "minimax-cn"
+display_name = "MiniMax (China)"
+api_key_env = "MINIMAX_CN_API_KEY"
+base_url = "https://api.minimaxi.com/v1"
+key_required = true
+
+[[models]]
+id = "minimax-text-01"
+display_name = "MiniMax Text 01"
+tier = "smart"
+context_window = 1048576
+max_output_tokens = 16384
+input_cost_per_m = 1.00
+output_cost_per_m = 3.00
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "MiniMax-M2.5"
+display_name = "MiniMax M2.5"
+tier = "frontier"
+context_window = 1048576
+max_output_tokens = 16384
+input_cost_per_m = 1.10
+output_cost_per_m = 4.40
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "MiniMax-M2.5-highspeed"
+display_name = "MiniMax M2.5 Highspeed"
+tier = "smart"
+context_window = 1048576
+max_output_tokens = 16384
+input_cost_per_m = 0.80
+output_cost_per_m = 3.20
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "MiniMax-M2.1"
+display_name = "MiniMax M2.1"
+tier = "smart"
+context_window = 1048576
+max_output_tokens = 16384
+input_cost_per_m = 1.00
+output_cost_per_m = 3.00
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "abab6.5-chat"
+display_name = "ABAB 6.5 Chat"
+tier = "balanced"
+context_window = 245760
+max_output_tokens = 8192
+input_cost_per_m = 0.50
+output_cost_per_m = 1.50
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "abab7-chat"
+display_name = "ABAB 7 Chat"
+tier = "smart"
+context_window = 524288
+max_output_tokens = 16384
+input_cost_per_m = 0.80
+output_cost_per_m = 2.40
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []

providers/minimax.toml

@@ -0,0 +1,87 @@
+# MiniMax (International) — https://minimax.io
+# Models: 6
+
+[provider]
+id = "minimax"
+display_name = "MiniMax (International)"
+api_key_env = "MINIMAX_API_KEY"
+base_url = "https://api.minimax.io/v1"
+key_required = true
+
+[[models]]
+id = "minimax-text-01"
+display_name = "MiniMax Text 01"
+tier = "smart"
+context_window = 1048576
+max_output_tokens = 16384
+input_cost_per_m = 1.00
+output_cost_per_m = 3.00
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["minimax"]
+
+[[models]]
+id = "MiniMax-M2.5"
+display_name = "MiniMax M2.5"
+tier = "frontier"
+context_window = 1048576
+max_output_tokens = 16384
+input_cost_per_m = 1.10
+output_cost_per_m = 4.40
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["minimax-m2.5"]
+
+[[models]]
+id = "MiniMax-M2.5-highspeed"
+display_name = "MiniMax M2.5 Highspeed"
+tier = "smart"
+context_window = 1048576
+max_output_tokens = 16384
+input_cost_per_m = 0.80
+output_cost_per_m = 3.20
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["minimax-m2.5-highspeed", "m2.5-highspeed"]
+
+[[models]]
+id = "MiniMax-M2.1"
+display_name = "MiniMax M2.1"
+tier = "smart"
+context_window = 1048576
+max_output_tokens = 16384
+input_cost_per_m = 1.00
+output_cost_per_m = 3.00
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["minimax-m2.1"]
+
+[[models]]
+id = "abab6.5-chat"
+display_name = "ABAB 6.5 Chat"
+tier = "balanced"
+context_window = 245760
+max_output_tokens = 8192
+input_cost_per_m = 0.50
+output_cost_per_m = 1.50
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "abab7-chat"
+display_name = "ABAB 7 Chat"
+tier = "smart"
+context_window = 524288
+max_output_tokens = 16384
+input_cost_per_m = 0.80
+output_cost_per_m = 2.40
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["abab7"]

providers/mistral.toml

@@ -0,0 +1,87 @@
+# Mistral AI — https://mistral.ai
+# Models: 6
+
+[provider]
+id = "mistral"
+display_name = "Mistral AI"
+api_key_env = "MISTRAL_API_KEY"
+base_url = "https://api.mistral.ai/v1"
+key_required = true
+
+[[models]]
+id = "mistral-large-latest"
+display_name = "Mistral Large"
+tier = "smart"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 2.00
+output_cost_per_m = 6.00
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["mistral"]
+
+[[models]]
+id = "mistral-medium-latest"
+display_name = "Mistral Medium"
+tier = "balanced"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 2.70
+output_cost_per_m = 8.10
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "mistral-small-latest"
+display_name = "Mistral Small"
+tier = "fast"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 0.10
+output_cost_per_m = 0.30
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "codestral-latest"
+display_name = "Codestral"
+tier = "smart"
+context_window = 32000
+max_output_tokens = 8192
+input_cost_per_m = 0.30
+output_cost_per_m = 0.90
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["codestral"]
+
+[[models]]
+id = "open-mistral-nemo"
+display_name = "Mistral Nemo"
+tier = "fast"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 0.15
+output_cost_per_m = 0.15
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["mistral-nemo"]
+
+[[models]]
+id = "pixtral-large-latest"
+display_name = "Pixtral Large"
+tier = "smart"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 2.00
+output_cost_per_m = 6.00
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["pixtral"]

providers/moonshot.toml

@@ -0,0 +1,74 @@
+# Moonshot / Kimi — https://moonshot.ai
+# Models: 5
+
+[provider]
+id = "moonshot"
+display_name = "Moonshot (Kimi)"
+api_key_env = "MOONSHOT_API_KEY"
+base_url = "https://api.moonshot.ai/v1"
+key_required = true
+
+[[models]]
+id = "moonshot-v1-128k"
+display_name = "Moonshot V1 128K"
+tier = "smart"
+context_window = 131072
+max_output_tokens = 8192
+input_cost_per_m = 0.80
+output_cost_per_m = 0.80
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["moonshot"]
+
+[[models]]
+id = "moonshot-v1-32k"
+display_name = "Moonshot V1 32K"
+tier = "balanced"
+context_window = 32768
+max_output_tokens = 8192
+input_cost_per_m = 0.30
+output_cost_per_m = 0.30
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "moonshot-v1-8k"
+display_name = "Moonshot V1 8K"
+tier = "fast"
+context_window = 8192
+max_output_tokens = 4096
+input_cost_per_m = 0.10
+output_cost_per_m = 0.10
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "kimi-k2"
+display_name = "Kimi K2"
+tier = "frontier"
+context_window = 131072
+max_output_tokens = 16384
+input_cost_per_m = 2.00
+output_cost_per_m = 8.00
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["kimi"]
+
+[[models]]
+id = "kimi-k2.5"
+display_name = "Kimi K2.5"
+tier = "frontier"
+context_window = 131072
+max_output_tokens = 16384
+input_cost_per_m = 2.00
+output_cost_per_m = 8.00
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["kimi-k2.5-0711"]

providers/ollama.toml

@@ -0,0 +1,87 @@
+# Ollama — https://ollama.com
+# Models: 6 (static entries; additional models discovered dynamically at runtime)
+
+[provider]
+id = "ollama"
+display_name = "Ollama"
+api_key_env = "OLLAMA_API_KEY"
+base_url = "http://localhost:11434/v1"
+key_required = false
+
+[[models]]
+id = "llama3.2"
+display_name = "Llama 3.2 (Ollama)"
+tier = "local"
+context_window = 128000
+max_output_tokens = 4096
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "llama3.1"
+display_name = "Llama 3.1 (Ollama)"
+tier = "local"
+context_window = 128000
+max_output_tokens = 4096
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "mistral:latest"
+display_name = "Mistral (Ollama)"
+tier = "local"
+context_window = 32768
+max_output_tokens = 4096
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "qwen2.5"
+display_name = "Qwen 2.5 (Ollama)"
+tier = "local"
+context_window = 32768
+max_output_tokens = 4096
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "phi3"
+display_name = "Phi-3 (Ollama)"
+tier = "local"
+context_window = 128000
+max_output_tokens = 4096
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "deepseek-r1:latest"
+display_name = "DeepSeek R1 (Ollama)"
+tier = "local"
+context_window = 64000
+max_output_tokens = 4096
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = []

providers/openai.toml

@@ -0,0 +1,245 @@
+# OpenAI — https://openai.com
+# Models: 18 (including 2 Codex variants)
+
+[provider]
+id = "openai"
+display_name = "OpenAI"
+api_key_env = "OPENAI_API_KEY"
+base_url = "https://api.openai.com/v1"
+key_required = true
+
+[[models]]
+id = "gpt-4o"
+display_name = "GPT-4o"
+tier = "smart"
+context_window = 128000
+max_output_tokens = 16384
+input_cost_per_m = 2.50
+output_cost_per_m = 10.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["gpt4", "gpt4o"]
+
+[[models]]
+id = "gpt-4o-mini"
+display_name = "GPT-4o Mini"
+tier = "fast"
+context_window = 128000
+max_output_tokens = 16384
+input_cost_per_m = 0.15
+output_cost_per_m = 0.60
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["gpt4-mini"]
+
+[[models]]
+id = "gpt-4.1"
+display_name = "GPT-4.1"
+tier = "frontier"
+context_window = 1047576
+max_output_tokens = 32768
+input_cost_per_m = 2.00
+output_cost_per_m = 8.00
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "gpt-4.1-mini"
+display_name = "GPT-4.1 Mini"
+tier = "balanced"
+context_window = 1047576
+max_output_tokens = 32768
+input_cost_per_m = 0.40
+output_cost_per_m = 1.60
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "gpt-4.1-nano"
+display_name = "GPT-4.1 Nano"
+tier = "fast"
+context_window = 1047576
+max_output_tokens = 32768
+input_cost_per_m = 0.10
+output_cost_per_m = 0.40
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "o3"
+display_name = "o3"
+tier = "frontier"
+context_window = 200000
+max_output_tokens = 100000
+input_cost_per_m = 2.00
+output_cost_per_m = 8.00
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "o3-mini"
+display_name = "o3-mini"
+tier = "smart"
+context_window = 200000
+max_output_tokens = 100000
+input_cost_per_m = 1.10
+output_cost_per_m = 4.40
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "o4-mini"
+display_name = "o4-mini"
+tier = "smart"
+context_window = 200000
+max_output_tokens = 100000
+input_cost_per_m = 1.10
+output_cost_per_m = 4.40
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "gpt-4-turbo"
+display_name = "GPT-4 Turbo"
+tier = "smart"
+context_window = 128000
+max_output_tokens = 4096
+input_cost_per_m = 10.00
+output_cost_per_m = 30.00
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "gpt-3.5-turbo"
+display_name = "GPT-3.5 Turbo"
+tier = "fast"
+context_window = 16385
+max_output_tokens = 4096
+input_cost_per_m = 0.50
+output_cost_per_m = 1.50
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "gpt-5"
+display_name = "GPT-5"
+tier = "frontier"
+context_window = 400000
+max_output_tokens = 128000
+input_cost_per_m = 1.25
+output_cost_per_m = 10.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "gpt-5-mini"
+display_name = "GPT-5 Mini"
+tier = "balanced"
+context_window = 400000
+max_output_tokens = 128000
+input_cost_per_m = 0.25
+output_cost_per_m = 2.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["gpt5-mini"]
+
+[[models]]
+id = "gpt-5-nano"
+display_name = "GPT-5 Nano"
+tier = "fast"
+context_window = 400000
+max_output_tokens = 128000
+input_cost_per_m = 0.05
+output_cost_per_m = 0.40
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "gpt-5.1"
+display_name = "GPT-5.1"
+tier = "frontier"
+context_window = 400000
+max_output_tokens = 128000
+input_cost_per_m = 1.25
+output_cost_per_m = 10.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "gpt-5.2"
+display_name = "GPT-5.2"
+tier = "frontier"
+context_window = 400000
+max_output_tokens = 128000
+input_cost_per_m = 1.75
+output_cost_per_m = 14.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["gpt5"]
+
+[[models]]
+id = "gpt-5.2-pro"
+display_name = "GPT-5.2 Pro"
+tier = "frontier"
+context_window = 400000
+max_output_tokens = 128000
+input_cost_per_m = 1.75
+output_cost_per_m = 14.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+# Codex variants (same OpenAI driver & API key)
+
+[[models]]
+id = "codex/gpt-4.1"
+display_name = "GPT-4.1 (Codex)"
+tier = "frontier"
+context_window = 1047576
+max_output_tokens = 32768
+input_cost_per_m = 2.00
+output_cost_per_m = 8.00
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["codex", "codex-4.1"]
+
+[[models]]
+id = "codex/o4-mini"
+display_name = "o4-mini (Codex)"
+tier = "smart"
+context_window = 200000
+max_output_tokens = 100000
+input_cost_per_m = 1.10
+output_cost_per_m = 4.40
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["codex-o4"]

providers/openrouter.toml

@@ -0,0 +1,219 @@
+# OpenRouter — https://openrouter.ai
+# Models: 16 (10 paid + 6 free)
+
+[provider]
+id = "openrouter"
+display_name = "OpenRouter"
+api_key_env = "OPENROUTER_API_KEY"
+base_url = "https://openrouter.ai/api/v1"
+key_required = true
+
+[[models]]
+id = "openrouter/google/gemini-2.5-flash"
+display_name = "Gemini 2.5 Flash (OpenRouter)"
+tier = "smart"
+context_window = 1048576
+max_output_tokens = 65536
+input_cost_per_m = 0.15
+output_cost_per_m = 0.60
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "openrouter/anthropic/claude-sonnet-4"
+display_name = "Claude Sonnet 4 (OpenRouter)"
+tier = "smart"
+context_window = 200000
+max_output_tokens = 64000
+input_cost_per_m = 3.0
+output_cost_per_m = 15.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "openrouter/openai/gpt-4o"
+display_name = "GPT-4o (OpenRouter)"
+tier = "smart"
+context_window = 128000
+max_output_tokens = 16384
+input_cost_per_m = 2.5
+output_cost_per_m = 10.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "openrouter/deepseek/deepseek-chat"
+display_name = "DeepSeek V3 (OpenRouter)"
+tier = "smart"
+context_window = 128000
+max_output_tokens = 32768
+input_cost_per_m = 0.14
+output_cost_per_m = 0.28
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "openrouter/meta-llama/llama-3.3-70b-instruct"
+display_name = "Llama 3.3 70B (OpenRouter)"
+tier = "balanced"
+context_window = 128000
+max_output_tokens = 32768
+input_cost_per_m = 0.39
+output_cost_per_m = 0.39
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "openrouter/qwen/qwen-2.5-72b-instruct"
+display_name = "Qwen 2.5 72B (OpenRouter)"
+tier = "balanced"
+context_window = 128000
+max_output_tokens = 32768
+input_cost_per_m = 0.36
+output_cost_per_m = 0.36
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "openrouter/google/gemini-2.5-pro"
+display_name = "Gemini 2.5 Pro (OpenRouter)"
+tier = "frontier"
+context_window = 1048576
+max_output_tokens = 65536
+input_cost_per_m = 1.25
+output_cost_per_m = 10.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "openrouter/mistralai/mistral-large-latest"
+display_name = "Mistral Large (OpenRouter)"
+tier = "smart"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 2.0
+output_cost_per_m = 6.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "openrouter/google/gemma-2-9b-it"
+display_name = "Gemma 2 9B (OpenRouter)"
+tier = "fast"
+context_window = 8192
+max_output_tokens = 4096
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "openrouter/deepseek/deepseek-r1"
+display_name = "DeepSeek R1 (OpenRouter)"
+tier = "frontier"
+context_window = 128000
+max_output_tokens = 32768
+input_cost_per_m = 0.55
+output_cost_per_m = 2.19
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+# Free models
+
+[[models]]
+id = "openrouter/google/gemma-2-9b-it:free"
+display_name = "Gemma 2 9B Free (OpenRouter)"
+tier = "fast"
+context_window = 8192
+max_output_tokens = 4096
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "openrouter/meta-llama/llama-3.1-8b-instruct:free"
+display_name = "Llama 3.1 8B Free (OpenRouter)"
+tier = "fast"
+context_window = 131072
+max_output_tokens = 4096
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "openrouter/qwen/qwen-2.5-7b-instruct:free"
+display_name = "Qwen 2.5 7B Free (OpenRouter)"
+tier = "fast"
+context_window = 32768
+max_output_tokens = 4096
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "openrouter/mistralai/mistral-7b-instruct:free"
+display_name = "Mistral 7B Free (OpenRouter)"
+tier = "fast"
+context_window = 32768
+max_output_tokens = 4096
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "openrouter/huggingfaceh4/zephyr-7b-beta:free"
+display_name = "Zephyr 7B Free (OpenRouter)"
+tier = "fast"
+context_window = 4096
+max_output_tokens = 2048
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "openrouter/deepseek/deepseek-r1:free"
+display_name = "DeepSeek R1 Free (OpenRouter)"
+tier = "smart"
+context_window = 128000
+max_output_tokens = 32768
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = []

providers/perplexity.toml

@@ -0,0 +1,61 @@
+# Perplexity AI — https://perplexity.ai
+# Models: 4
+
+[provider]
+id = "perplexity"
+display_name = "Perplexity AI"
+api_key_env = "PERPLEXITY_API_KEY"
+base_url = "https://api.perplexity.ai"
+key_required = true
+
+[[models]]
+id = "sonar-pro"
+display_name = "Sonar Pro"
+tier = "smart"
+context_window = 200000
+max_output_tokens = 8192
+input_cost_per_m = 3.0
+output_cost_per_m = 15.0
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = ["sonar"]
+
+[[models]]
+id = "sonar-reasoning-pro"
+display_name = "Sonar Reasoning Pro"
+tier = "frontier"
+context_window = 200000
+max_output_tokens = 8192
+input_cost_per_m = 2.0
+output_cost_per_m = 8.0
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "sonar-reasoning"
+display_name = "Sonar Reasoning"
+tier = "balanced"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 1.0
+output_cost_per_m = 5.0
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "sonar-basic"
+display_name = "Sonar"
+tier = "fast"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 1.0
+output_cost_per_m = 5.0
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = []

providers/qianfan.toml

@@ -0,0 +1,48 @@
+# Baidu Qianfan / ERNIE — https://qianfan.baidubce.com
+# Models: 3
+
+[provider]
+id = "qianfan"
+display_name = "Baidu Qianfan"
+api_key_env = "QIANFAN_API_KEY"
+base_url = "https://qianfan.baidubce.com/v2"
+key_required = true
+
+[[models]]
+id = "ernie-4.5-8k"
+display_name = "ERNIE 4.5 8K"
+tier = "smart"
+context_window = 8192
+max_output_tokens = 4096
+input_cost_per_m = 2.00
+output_cost_per_m = 6.00
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["ernie"]
+
+[[models]]
+id = "ernie-4.0-turbo-8k"
+display_name = "ERNIE 4.0 Turbo 8K"
+tier = "balanced"
+context_window = 8192
+max_output_tokens = 4096
+input_cost_per_m = 1.00
+output_cost_per_m = 3.00
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "ernie-speed-128k"
+display_name = "ERNIE Speed 128K"
+tier = "fast"
+context_window = 131072
+max_output_tokens = 4096
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []

providers/qwen.toml

@@ -0,0 +1,152 @@
+# Qwen / Alibaba — https://dashscope.aliyuncs.com
+# Models: 11
+
+[provider]
+id = "qwen"
+display_name = "Qwen (Alibaba)"
+api_key_env = "DASHSCOPE_API_KEY"
+base_url = "https://dashscope.aliyuncs.com/compatible-mode/v1"
+key_required = true
+
+[[models]]
+id = "qwen-max"
+display_name = "Qwen Max"
+tier = "frontier"
+context_window = 32768
+max_output_tokens = 8192
+input_cost_per_m = 4.00
+output_cost_per_m = 12.00
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "qwen-plus"
+display_name = "Qwen Plus"
+tier = "smart"
+context_window = 131072
+max_output_tokens = 8192
+input_cost_per_m = 0.80
+output_cost_per_m = 2.00
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["qwen"]
+
+[[models]]
+id = "qwen-turbo"
+display_name = "Qwen Turbo"
+tier = "fast"
+context_window = 131072
+max_output_tokens = 8192
+input_cost_per_m = 0.30
+output_cost_per_m = 0.60
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "qwen-vl-plus"
+display_name = "Qwen VL Plus"
+tier = "smart"
+context_window = 32768
+max_output_tokens = 8192
+input_cost_per_m = 1.50
+output_cost_per_m = 4.50
+supports_tools = false
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "qwen-coder-plus"
+display_name = "Qwen Coder Plus"
+tier = "smart"
+context_window = 131072
+max_output_tokens = 8192
+input_cost_per_m = 0.80
+output_cost_per_m = 2.00
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "qwen-long"
+display_name = "Qwen Long"
+tier = "balanced"
+context_window = 1000000
+max_output_tokens = 8192
+input_cost_per_m = 0.50
+output_cost_per_m = 2.00
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "qwen3-235b-a22b"
+display_name = "Qwen3 235B"
+tier = "frontier"
+context_window = 131072
+max_output_tokens = 8192
+input_cost_per_m = 4.00
+output_cost_per_m = 12.00
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["qwen3"]
+
+[[models]]
+id = "qwen3-30b-a3b"
+display_name = "Qwen3 30B"
+tier = "fast"
+context_window = 131072
+max_output_tokens = 8192
+input_cost_per_m = 0.30
+output_cost_per_m = 0.60
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "qwen-coder-plus-latest"
+display_name = "Qwen Coder Plus (Latest)"
+tier = "smart"
+context_window = 131072
+max_output_tokens = 8192
+input_cost_per_m = 0.80
+output_cost_per_m = 2.00
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["qwen-coder"]
+
+[[models]]
+id = "qwen2.5-coder-32b-instruct"
+display_name = "Qwen 2.5 Coder 32B"
+tier = "balanced"
+context_window = 131072
+max_output_tokens = 8192
+input_cost_per_m = 0.80
+output_cost_per_m = 2.00
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "qwen-vl-max"
+display_name = "Qwen VL Max"
+tier = "frontier"
+context_window = 32768
+max_output_tokens = 8192
+input_cost_per_m = 3.00
+output_cost_per_m = 9.00
+supports_tools = false
+supports_vision = true
+supports_streaming = true
+aliases = []

providers/replicate.toml

@@ -0,0 +1,48 @@
+# Replicate — https://replicate.com
+# Models: 3
+
+[provider]
+id = "replicate"
+display_name = "Replicate"
+api_key_env = "REPLICATE_API_TOKEN"
+base_url = "https://api.replicate.com/v1"
+key_required = true
+
+[[models]]
+id = "replicate/meta-llama-3.3-70b-instruct"
+display_name = "Llama 3.3 70B (Replicate)"
+tier = "balanced"
+context_window = 128000
+max_output_tokens = 4096
+input_cost_per_m = 0.40
+output_cost_per_m = 0.40
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "replicate/deepseek-r1"
+display_name = "DeepSeek R1 (Replicate)"
+tier = "smart"
+context_window = 64000
+max_output_tokens = 4096
+input_cost_per_m = 0.40
+output_cost_per_m = 0.40
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "replicate/mistral-7b-instruct"
+display_name = "Mistral 7B (Replicate)"
+tier = "fast"
+context_window = 32768
+max_output_tokens = 4096
+input_cost_per_m = 0.05
+output_cost_per_m = 0.25
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = []

providers/sambanova.toml

@@ -0,0 +1,48 @@
+# SambaNova — https://sambanova.ai
+# Models: 3
+
+[provider]
+id = "sambanova"
+display_name = "SambaNova"
+api_key_env = "SAMBANOVA_API_KEY"
+base_url = "https://api.sambanova.ai/v1"
+key_required = true
+
+[[models]]
+id = "sambanova/llama-3.3-70b"
+display_name = "Llama 3.3 70B (SambaNova)"
+tier = "balanced"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 0.06
+output_cost_per_m = 0.06
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "sambanova/deepseek-r1"
+display_name = "DeepSeek R1 (SambaNova)"
+tier = "smart"
+context_window = 64000
+max_output_tokens = 8192
+input_cost_per_m = 0.06
+output_cost_per_m = 0.06
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "sambanova/qwen-2.5-72b"
+display_name = "Qwen 2.5 72B (SambaNova)"
+tier = "smart"
+context_window = 32768
+max_output_tokens = 8192
+input_cost_per_m = 0.06
+output_cost_per_m = 0.06
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []

providers/together.toml

@@ -0,0 +1,113 @@
+# Together AI — https://together.ai
+# Models: 8
+
+[provider]
+id = "together"
+display_name = "Together AI"
+api_key_env = "TOGETHER_API_KEY"
+base_url = "https://api.together.xyz/v1"
+key_required = true
+
+[[models]]
+id = "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo"
+display_name = "Llama 3.1 405B (Together)"
+tier = "frontier"
+context_window = 130000
+max_output_tokens = 4096
+input_cost_per_m = 3.50
+output_cost_per_m = 3.50
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "meta-llama/Llama-3.3-70B-Instruct-Turbo"
+display_name = "Llama 3.3 70B (Together)"
+tier = "smart"
+context_window = 128000
+max_output_tokens = 4096
+input_cost_per_m = 0.88
+output_cost_per_m = 0.88
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"
+display_name = "Llama 4 Maverick (Together)"
+tier = "smart"
+context_window = 1048576
+max_output_tokens = 8192
+input_cost_per_m = 0.27
+output_cost_per_m = 0.35
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "meta-llama/Llama-4-Scout-17B-16E-Instruct"
+display_name = "Llama 4 Scout (Together)"
+tier = "balanced"
+context_window = 512000
+max_output_tokens = 8192
+input_cost_per_m = 0.18
+output_cost_per_m = 0.30
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "deepseek-ai/DeepSeek-R1"
+display_name = "DeepSeek R1 (Together)"
+tier = "frontier"
+context_window = 64000
+max_output_tokens = 8192
+input_cost_per_m = 3.00
+output_cost_per_m = 7.00
+supports_tools = false
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "deepseek-ai/DeepSeek-V3"
+display_name = "DeepSeek V3 (Together)"
+tier = "smart"
+context_window = 64000
+max_output_tokens = 8192
+input_cost_per_m = 0.90
+output_cost_per_m = 0.90
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "Qwen/Qwen2.5-72B-Instruct-Turbo"
+display_name = "Qwen 2.5 72B (Together)"
+tier = "smart"
+context_window = 32768
+max_output_tokens = 4096
+input_cost_per_m = 0.20
+output_cost_per_m = 0.60
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "mistralai/Mixtral-8x22B-Instruct-v0.1"
+display_name = "Mixtral 8x22B (Together)"
+tier = "balanced"
+context_window = 65536
+max_output_tokens = 4096
+input_cost_per_m = 0.60
+output_cost_per_m = 0.60
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []

providers/venice.toml

@@ -0,0 +1,48 @@
+# Venice.ai — https://venice.ai
+# Models: 3
+
+[provider]
+id = "venice"
+display_name = "Venice.ai"
+api_key_env = "VENICE_API_KEY"
+base_url = "https://api.venice.ai/api/v1"
+key_required = true
+
+[[models]]
+id = "venice-uncensored"
+display_name = "Venice Uncensored"
+tier = "fast"
+context_window = 32000
+max_output_tokens = 8192
+input_cost_per_m = 0.20
+output_cost_per_m = 0.90
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["venice"]
+
+[[models]]
+id = "llama-3.3-70b"
+display_name = "Llama 3.3 70B (Venice)"
+tier = "balanced"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 0.20
+output_cost_per_m = 0.90
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "qwen3-235b-a22b-instruct-2507"
+display_name = "Qwen3 235B A22B (Venice)"
+tier = "smart"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 0.20
+output_cost_per_m = 0.90
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []

providers/vllm.toml

@@ -0,0 +1,22 @@
+# vLLM — https://vllm.ai
+# Models: 1 (generic entry; additional models discovered dynamically at runtime)
+
+[provider]
+id = "vllm"
+display_name = "vLLM"
+api_key_env = "VLLM_API_KEY"
+base_url = "http://localhost:8000/v1"
+key_required = false
+
+[[models]]
+id = "vllm-local"
+display_name = "vLLM Local Model"
+tier = "local"
+context_window = 32768
+max_output_tokens = 4096
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []

providers/volcengine-coding.toml

@@ -0,0 +1,9 @@
+# Volcano Engine Coding Plan — https://volcengine.com
+# Models: 0 (uses same API, coding-specific endpoint)
+
+[provider]
+id = "volcengine_coding"
+display_name = "Volcano Engine Coding Plan"
+api_key_env = "VOLCENGINE_API_KEY"
+base_url = "https://ark.cn-beijing.volces.com/api/coding/v3"
+key_required = true

providers/volcengine.toml

@@ -0,0 +1,61 @@
+# Volcano Engine / Doubao — https://volcengine.com
+# Models: 4
+
+[provider]
+id = "volcengine"
+display_name = "Volcano Engine (Doubao)"
+api_key_env = "VOLCENGINE_API_KEY"
+base_url = "https://ark.cn-beijing.volces.com/api/v3"
+key_required = true
+
+[[models]]
+id = "doubao-seed-1-6-251015"
+display_name = "Doubao Seed 1.6 Pro"
+tier = "smart"
+context_window = 262144
+max_output_tokens = 16384
+input_cost_per_m = 0.80
+output_cost_per_m = 2.00
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["doubao", "doubao-pro"]
+
+[[models]]
+id = "doubao-seed-2-0-lite"
+display_name = "Doubao Seed 2.0 Lite"
+tier = "balanced"
+context_window = 131072
+max_output_tokens = 16384
+input_cost_per_m = 0.30
+output_cost_per_m = 0.60
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["doubao-lite"]
+
+[[models]]
+id = "doubao-seed-2-0-mini"
+display_name = "Doubao Seed 2.0 Mini"
+tier = "fast"
+context_window = 131072
+max_output_tokens = 16384
+input_cost_per_m = 0.10
+output_cost_per_m = 0.10
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["doubao-mini"]
+
+[[models]]
+id = "doubao-seed-code"
+display_name = "Doubao Seed Code"
+tier = "smart"
+context_window = 131072
+max_output_tokens = 16384
+input_cost_per_m = 0.50
+output_cost_per_m = 1.00
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["doubao-code"]

providers/xai.toml

@@ -0,0 +1,126 @@
+# xAI — https://x.ai
+# Models: 9
+
+[provider]
+id = "xai"
+display_name = "xAI"
+api_key_env = "XAI_API_KEY"
+base_url = "https://api.x.ai/v1"
+key_required = true
+
+[[models]]
+id = "grok-4-0709"
+display_name = "Grok 4"
+tier = "frontier"
+context_window = 256000
+max_output_tokens = 32768
+input_cost_per_m = 3.0
+output_cost_per_m = 15.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["grok", "grok-4"]
+
+[[models]]
+id = "grok-4-fast-reasoning"
+display_name = "Grok 4 Fast Reasoning"
+tier = "smart"
+context_window = 256000
+max_output_tokens = 32768
+input_cost_per_m = 1.0
+output_cost_per_m = 5.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "grok-4-fast-non-reasoning"
+display_name = "Grok 4 Fast Non-Reasoning"
+tier = "smart"
+context_window = 256000
+max_output_tokens = 32768
+input_cost_per_m = 1.0
+output_cost_per_m = 5.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "grok-4-1-fast-reasoning"
+display_name = "Grok 4.1 Fast Reasoning"
+tier = "fast"
+context_window = 2000000
+max_output_tokens = 32768
+input_cost_per_m = 0.20
+output_cost_per_m = 0.50
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["grok-fast"]
+
+[[models]]
+id = "grok-4-1-fast-non-reasoning"
+display_name = "Grok 4.1 Fast Non-Reasoning"
+tier = "fast"
+context_window = 2000000
+max_output_tokens = 32768
+input_cost_per_m = 0.20
+output_cost_per_m = 0.50
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "grok-3"
+display_name = "Grok 3"
+tier = "frontier"
+context_window = 131072
+max_output_tokens = 32768
+input_cost_per_m = 3.0
+output_cost_per_m = 15.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["grok3"]
+
+[[models]]
+id = "grok-3-mini"
+display_name = "Grok 3 Mini"
+tier = "balanced"
+context_window = 131072
+max_output_tokens = 32768
+input_cost_per_m = 0.30
+output_cost_per_m = 0.50
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "grok-2"
+display_name = "Grok 2"
+tier = "smart"
+context_window = 131072
+max_output_tokens = 32768
+input_cost_per_m = 2.0
+output_cost_per_m = 10.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "grok-2-mini"
+display_name = "Grok 2 Mini"
+tier = "fast"
+context_window = 131072
+max_output_tokens = 32768
+input_cost_per_m = 0.30
+output_cost_per_m = 0.50
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["grok-mini"]

providers/zai-coding.toml

@@ -0,0 +1,35 @@
+# Z.AI Coding / GLM Coding Models — https://api.z.ai
+# Models: 2
+
+[provider]
+id = "zai_coding"
+display_name = "Z.AI Coding"
+api_key_env = "ZHIPU_API_KEY"
+base_url = "https://api.z.ai/api/coding/paas/v4"
+key_required = true
+
+[[models]]
+id = "glm-5-coding"
+display_name = "GLM-5 Coding"
+tier = "frontier"
+context_window = 131072
+max_output_tokens = 16384
+input_cost_per_m = 2.00
+output_cost_per_m = 8.00
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["glm-5-code", "glm-coding"]
+
+[[models]]
+id = "glm-4.7-coding"
+display_name = "GLM-4.7 Coding"
+tier = "smart"
+context_window = 131072
+max_output_tokens = 16384
+input_cost_per_m = 1.50
+output_cost_per_m = 5.00
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["glm-4.7-code"]

providers/zai.toml

@@ -0,0 +1,9 @@
+# Z.AI — https://api.z.ai (Zhipu domain alias)
+# Models: 0 (uses same models as zhipu, different domain)
+
+[provider]
+id = "zai"
+display_name = "Z.AI"
+api_key_env = "ZHIPU_API_KEY"
+base_url = "https://api.z.ai/api/paas/v4"
+key_required = true

providers/zhipu-coding.toml

@@ -0,0 +1,22 @@
+# Zhipu Coding / CodeGeeX — https://open.bigmodel.cn
+# Models: 1
+
+[provider]
+id = "zhipu_coding"
+display_name = "Zhipu Coding (CodeGeeX)"
+api_key_env = "ZHIPU_API_KEY"
+base_url = "https://open.bigmodel.cn/api/coding/paas/v4"
+key_required = true
+
+[[models]]
+id = "codegeex-4"
+display_name = "CodeGeeX 4"
+tier = "smart"
+context_window = 131072
+max_output_tokens = 8192
+input_cost_per_m = 0.10
+output_cost_per_m = 0.10
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["codegeex"]

providers/zhipu.toml

@@ -0,0 +1,87 @@
+# Zhipu AI (GLM) — https://open.bigmodel.cn
+# Models: 6
+
+[provider]
+id = "zhipu"
+display_name = "Zhipu AI (GLM)"
+api_key_env = "ZHIPU_API_KEY"
+base_url = "https://open.bigmodel.cn/api/paas/v4"
+key_required = true
+
+[[models]]
+id = "glm-4-plus"
+display_name = "GLM-4 Plus"
+tier = "smart"
+context_window = 131072
+max_output_tokens = 8192
+input_cost_per_m = 0.60
+output_cost_per_m = 2.20
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = ["glm"]
+
+[[models]]
+id = "glm-4-flash"
+display_name = "GLM-4 Flash"
+tier = "fast"
+context_window = 131072
+max_output_tokens = 8192
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "glm-4v-plus"
+display_name = "GLM-4V Plus"
+tier = "smart"
+context_window = 8192
+max_output_tokens = 4096
+input_cost_per_m = 0.60
+output_cost_per_m = 2.20
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "glm-4-long"
+display_name = "GLM-4 Long"
+tier = "balanced"
+context_window = 1000000
+max_output_tokens = 8192
+input_cost_per_m = 0.10
+output_cost_per_m = 0.10
+supports_tools = true
+supports_vision = false
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "glm-5-20250605"
+display_name = "GLM-5"
+tier = "frontier"
+context_window = 131072
+max_output_tokens = 16384
+input_cost_per_m = 1.00
+output_cost_per_m = 3.20
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["glm-5"]
+
+[[models]]
+id = "glm-4.7"
+display_name = "GLM-4.7"
+tier = "smart"
+context_window = 131072
+max_output_tokens = 16384
+input_cost_per_m = 0.60
+output_cost_per_m = 2.20
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []