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writer Clean up 10 major providers — keep only latest generation models: - anthropic: remove claude-3.5-sonnet (superseded by 4.x) - openai: remove gpt-4o/4-turbo/3.5/o1/o3-mini (superseded by gpt-5/4.1/o3/o4-mini) - gemini: remove 1.5-*/2.0-flash (superseded by 2.5/3.x) - deepseek: remove coder/chat-v3-0324 (superseded by r1/v3) - qwen: remove turbo/2.5-coder (superseded by qwen3) - groq: remove old llama/mixtral/gemma (keep latest only) - mistral: remove medium/nemo/pixtral-large (keep large/small/codestral) - xai: remove grok-2 (superseded by grok-3/4) - meta-llama: remove 3.x/guard (keep llama-4 + 3.3) - ollama: rewrite with current models (gemma4, qwen3, qwq, llama4, etc) Total: 90 → 48 models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
50 lines
1.0 KiB
TOML
50 lines
1.0 KiB
TOML
# meta-llama — https://llama.com
|
|
# Models: 5
|
|
|
|
[provider]
|
|
id = "meta-llama"
|
|
display_name = "Meta Llama"
|
|
api_key_env = "LLAMA_API_KEY"
|
|
base_url = "https://api.llama.com/v1"
|
|
key_required = true
|
|
|
|
[[models]]
|
|
id = "llama-4-maverick"
|
|
display_name = "Meta: Llama 4 Maverick"
|
|
tier = "fast"
|
|
context_window = 1048576
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.15
|
|
output_cost_per_m = 0.6
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "llama-4-scout"
|
|
display_name = "Meta: Llama 4 Scout"
|
|
tier = "fast"
|
|
context_window = 327680
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.08
|
|
output_cost_per_m = 0.3
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "llama-3.3-70b-instruct"
|
|
display_name = "Meta: Llama 3.3 70B Instruct"
|
|
tier = "fast"
|
|
context_window = 131072
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.48
|
|
output_cost_per_m = 0.03
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "llama-guard-4-12b"
|
|
display_name = "Meta: Llama Guard 4 12B"
|
|
tier = "fast"
|
|
context_window = 163840
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.18
|
|
output_cost_per_m = 0.18
|
|
supports_streaming = true
|