* chore: prune deprecated models across providers
Remove old-generation models that are strictly superseded by current versions
on the same provider/family. Affected providers: anthropic, bedrock, vertex-ai,
xai, moonshot, zhipu, baichuan, stepfun, volcengine, minimax, cohere, together,
fireworks, deepinfra, openrouter. Also clean up orphan aliases (grok3, grok-mini,
minimax-m2.1) and remap moonshot alias to kimi-k2.5.
Net: -42 model entries across 18 files. Provider model counts and README rows
updated accordingly.
* chore: remove redundant and orphan aliases from aliases.toml
Provider TOML files auto-register their model.aliases at load time, so
re-declaring them globally is duplication. Also drop entries pointing to
models that no longer exist after the prune.
- 45 redundant entries duplicating provider-defined aliases
- 11 orphan targets (gpt-4o, gpt-4o-mini, grok-2-mini, grok-3,
mixtral-8x7b-32768, copilot/gpt-4, open-mistral-nemo,
pixtral-large-latest, jamba-1.5-large, palmyra-x5, venice-uncensored)
Net: 100 lines down to 21. The file is now what the header comment
always claimed it was: 'additional global aliases not tied to a specific
model entry.'
* chore: second pass — prune more deprecated models
Apply the same 'strictly superseded by same-provider/family successor'
rule to providers missed in the first pass:
- openai: gpt-4.1 / -mini / -nano, o3, o4-mini (5)
- meta-llama: llama-3.3-70b-instruct (1)
- zhipu: glm-4v-plus (1)
- together: Llama-3.3-70B-Instruct-Turbo (1)
- xiaomi: mimo-v2-flash / -omni / -pro (3)
- aion-labs: aion-1.0 / -mini (2)
- qianfan: ernie-speed-128k, ernie-4.0-turbo-8k (2)
- cerebras: cerebras/llama3.1-8b (1)
- qwen-code: qwen-code/qwq-32b (1)
- nvidia-nim: 12 models (llama-3.1/3.2 series, mixtral-8x22b,
mistral-small-3.1, phi-4-mini, qwq-32b, r1-distill-32b,
qwen2.5-coder, nemotron-mini-4b, nemotron-70b-instruct)
- openrouter: meta-llama/llama-3.3-70b (paid), rekaai/reka-edge (2)
- alibaba-coding-plan: qwen3.5-plus, qwen3-max-2026-01-23,
MiniMax-M2.5, kimi-k2.5 (4)
Net: -35 model entries. providers/README.md model counts updated.
220 models remain.
Introduces image-generation models as a first-class [[models]] entry via
a new `modality` field on the model schema ("text" default, "image",
"audio"). When modality != "text", context_window / max_output_tokens
are optional since no conventional context gate exists — OpenAI's
gpt-image-2 docs omit them.
Adds `image_input_cost_per_m` / `image_output_cost_per_m` alongside
existing text token cost fields to cover the 4-price structure OpenAI
uses for image generation (text $5/$10, image $8/$30 per 1M tokens).
Validator updated to:
- accept any modality in {text, image, audio}
- require context_window/max_output_tokens only for modality=text
- range-check the two new cost fields
gpt-image-2 entry added to providers/openai.toml with pricing sourced
from https://developers.openai.com/api/docs/pricing. Snapshot
gpt-image-2-2026-04-21 listed as alias.
Add the two GPT-5.4 variants exposed by OpenAI's API (source:
https://developers.openai.com/api/docs/models/gpt-5.4 and
https://developers.openai.com/api/docs/models/gpt-5.4-mini):
- **gpt-5.4** — frontier tier, 1,050,000 context window, 128k max output,
$2.50 / input MTok, $15.00 / output MTok.
- **gpt-5.4-mini** — balanced tier (matching the naming convention used
by `gpt-5-mini`, `gpt-4.1-mini`, etc.), 400,000 context window,
128k max output, $0.75 / input MTok, $4.50 / output MTok.
Ordered right after the GPT-5.2 family and before the Codex variants
section to keep the frontier-GPT chain in release order.
Addresses librefang/librefang-registry#65 — the original request filed
these under the `codex-cli` provider, but Codex CLI's upstream
`models.json` doesn't list `gpt-5.4-mini` (only the full `gpt-5.4`
slug is list-visible there, and it's already tracked in
`providers/codex-cli.toml`). The correct home for OpenAI-API-direct
access is this file; users who want `gpt-5.4-mini` should configure
`provider = "openai"` rather than `provider = "codex-cli"`.
* fix: pin npm package versions in MCP integration templates
Prevent supply chain attacks by pinning exact versions instead of
using unpinned `npx -y @package` which pulls latest on every run.
23 of 25 integrations pinned. sqlite-mcp and aws skipped (packages
not found on npm registry).
* fix: use stable azure/mcp version instead of beta
* feat: add pricing sync script and update model prices from OpenRouter API
- scripts/sync-pricing.py fetches real-time pricing from OpenRouter
- Updated 64 price fields across 13 provider files
- Run periodically or in CI to keep prices current
Community-maintained TOML catalog for LibreFang. New models can be added
via PR without requiring a LibreFang binary release.
Includes validation script, bilingual docs, and GitHub templates.
Evan