Evan
4f8dd2404d
* feat(providers): expand ollama model catalog with thinking-capable models Add commonly used local models with accurate capability flags: - gemma4, gemma3: supports_thinking, supports_vision - deepseek-r1: supports_thinking (fix missing flag) - deepseek-v3: supports_tools - qwen3, qwq: supports_thinking - llama4: supports_vision - llama3.3: supports_tools - phi4: supports_tools Previously only 6 models were listed and none had supports_thinking (except deepseek-r1), causing the dashboard to hide thinking toggles for models that actually support it. * chore(providers): major cleanup — remove defunct providers and old models Delete 21 defunct/obscure providers: aion-labs, arcee-ai, deepcogito, eleutherai, essentialai, ibm-granite, inception, inflection, kwaipilot, lemonade, liquid, morph, nex-agi, nousresearch, prime-intellect, reka, relace, switchpoint, tngtech, upstage, writer Clean up 10 major providers — keep only latest generation models: - anthropic: remove claude-3.5-sonnet (superseded by 4.x) - openai: remove gpt-4o/4-turbo/3.5/o1/o3-mini (superseded by gpt-5/4.1/o3/o4-mini) - gemini: remove 1.5-*/2.0-flash (superseded by 2.5/3.x) - deepseek: remove coder/chat-v3-0324 (superseded by r1/v3) - qwen: remove turbo/2.5-coder (superseded by qwen3) - groq: remove old llama/mixtral/gemma (keep latest only) - mistral: remove medium/nemo/pixtral-large (keep large/small/codestral) - xai: remove grok-2 (superseded by grok-3/4) - meta-llama: remove 3.x/guard (keep llama-4 + 3.3) - ollama: rewrite with current models (gemma4, qwen3, qwq, llama4, etc) Total: 90 → 48 models across major providers. All thinking-capable models now have supports_thinking = true. * chore: add pre-commit hook for automatic TOML formatting - .githooks/pre-commit: runs taplo fmt on staged .toml files - Makefile: add setup target + auto-configure hooks on first make - .gitignore: add .make-setup-done and .sync_marker
95 lines
2.1 KiB
TOML
95 lines
2.1 KiB
TOML
# Google Gemini — https://ai.google.dev
|
|
# Models: 6
|
|
|
|
[provider]
|
|
id = "gemini"
|
|
display_name = "Google Gemini"
|
|
api_key_env = "GEMINI_API_KEY"
|
|
base_url = "https://generativelanguage.googleapis.com"
|
|
key_required = true
|
|
media_capabilities = ["image_generation"]
|
|
|
|
[[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 = 2.0
|
|
output_cost_per_m = 12.0
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
supports_thinking = 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 = 0.5
|
|
output_cost_per_m = 3.0
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
supports_thinking = 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 = 0.25
|
|
output_cost_per_m = 1.5
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
supports_thinking = 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 = 0.1
|
|
output_cost_per_m = 0.4
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
supports_thinking = 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
|
|
supports_thinking = 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 = 0.3
|
|
output_cost_per_m = 2.5
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
supports_thinking = true
|
|
aliases = ["flash"]
|