arka/librefang-registry
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
6d44be4277a4320cde03db2690c00b0202f832ce
librefang-registry/providers/openai.toml
T
Evan 4f8dd2404d feat(providers): expand ollama catalog with thinking-capable models (#58) 
* 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- anthropic: remove claude-3.5-sonnet (superseded by 4.x)
- openai: remove gpt-4o/4-turbo/3.5/o1/o3-mini (superseded by gpt-5/4.1/o3/o4-mini)
- gemini: remove 1.5-*/2.0-flash (superseded by 2.5/3.x)
- deepseek: remove coder/chat-v3-0324 (superseded by r1/v3)
- qwen: remove turbo/2.5-coder (superseded by qwen3)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- xai: remove grok-2 (superseded by grok-3/4)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
2026-04-15 22:18:01 +09:00

185 lines
3.7 KiB
TOML
Raw Blame History

# OpenAI — https://openai.com
# Models: 13 (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
media_capabilities = ["image_generation", "text_to_speech"]
[[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 = 2.0
output_cost_per_m = 8.0
supports_tools = true
supports_vision = true
supports_streaming = true
supports_thinking = true
aliases = []
[[models]]
id = "o4-mini"
display_name = "o4-mini"
tier = "smart"
context_window = 200000
max_output_tokens = 100000
input_cost_per_m = 1.1
output_cost_per_m = 4.4
supports_tools = true
supports_vision = true
supports_streaming = true
supports_thinking = 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 = 21.0
output_cost_per_m = 168.0
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
supports_thinking = true
aliases = ["codex-o4"]
Reference in new issue View Git Blame Copy Permalink