Evan
80c6ee79cd
Add `claude-opus-4-7`, Anthropic's current flagship model (per https://platform.claude.com/docs/en/docs/about-claude/models/overview). - Context window: 1,000,000 tokens (Opus 4.7 ships with a new tokenizer) - Max output: 128,000 tokens - Pricing: $5 / input MTok, $25 / output MTok (unchanged from 4.6) - Tier: frontier - Supports tools, vision, streaming, and adaptive thinking Move the `opus` / `claude-opus` aliases from 4.6 to 4.7 so a user asking for "opus" gets the current flagship. Opus 4.6 is now in Anthropic's "Legacy" section of the models overview; keeping it in the registry entry (for existing callers that pin the exact ID) but without the generic aliases. Also **correct Opus 4.6's `context_window`**: it was listed as 200,000 tokens but the official model page has shown 1M tokens since release. That was a pre-existing bug this PR fixes in passing since it directly affects anyone who'd have routed queries to 4.6 expecting 1M. Add a header comment pinning the source URL and explaining the "latest-first" ordering convention so future additions don't silently rebind aliases to a previous-generation snapshot.
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.