Evan
85db9c8d78
* feat(providers): add supports_thinking field to thinking-capable models Mark models that support extended thinking / reasoning with supports_thinking = true so the dashboard can conditionally show thinking toggles. Providers updated: anthropic (8), codex-cli (7), gemini (6), openai (3), qwen (2), deepseek (1). Schema updated accordingly. * feat(providers): add supports_thinking to remaining thinking-capable models Cover 19 additional providers: alibaba-coding-plan, allenai, arcee-ai, fireworks, gemini-cli, groq, liquid, nvidia-nim, ollama, openai (codex), openrouter, perplexity, qwen-code, replicate, sambanova, tngtech, venice, vertex-ai, xai. Total: 62 models across 24 providers now have supports_thinking = true. * feat(providers): add supports_thinking to chutes, huggingface, together Missed in prior commits: DeepSeek-R1 on chutes/huggingface/together, Qwen3-235B on chutes. Total now 66 models across 27 providers. * feat(providers): add supports_thinking to bedrock, claude-code, aider, moonshot, stepfun - bedrock: all 5 Claude models - claude-code: all 3 models (opus/sonnet/haiku wrappers) - aider: aider/sonnet (Claude-backed) - moonshot: kimi-k2.5 (reasoning mode) - stepfun: step-1o-turbo-vision (reasoning model) Total: 77 models across 32 providers. * feat(providers): add supports_thinking to alibaba kimi-k2.5, openrouter claude-sonnet-4
Providers
LLM provider and model metadata for LibreFang. Each provider file defines the provider's API configuration and all available models with pricing, context windows, and capability flags.
Structure
providers/
├── anthropic.toml
├── openai.toml
├── groq.toml
└── ... (46 providers, 220+ models)
Provider TOML Format
[provider]
id = "provider-id" # Unique identifier (lowercase, hyphenated)
display_name = "Provider Name"
api_key_env = "PROVIDER_API_KEY" # Env var for API key
base_url = "https://api.example.com"
key_required = true
[[models]]
id = "model-id" # Exact API model ID
display_name = "Model Name"
tier = "smart" # frontier | smart | balanced | fast | local
context_window = 128000
max_output_tokens = 16384
input_cost_per_m = 2.50 # USD per million input tokens
output_cost_per_m = 10.0 # USD per million output tokens
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = ["short-name"]
Tier Definitions
| Tier | Description | Examples |
|---|---|---|
frontier |
Most capable, cutting-edge | Claude Opus, GPT-4.1 |
smart |
Smart, cost-effective | Claude Sonnet, Gemini 2.5 Flash |
balanced |
Balanced speed/cost | GPT-4.1 Mini, Llama 3.3 70B |
fast |
Fastest, cheapest | GPT-4o Mini, Claude Haiku |
local |
Local models, zero cost | Ollama, vLLM, LM Studio |
Validation
python scripts/validate.py
Checks: required fields, valid tiers, non-negative costs, no duplicate model IDs.
Adding or Updating a Model
- Edit or create the provider file in
providers/ - Use exact API model IDs and verify pricing from official sources
- Run
python scripts/validate.py - Submit a PR
See CONTRIBUTING.md for the full guide and pricing source links.