chore: prune deprecated models across providers (#75)

* 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Remove old-generation models that are strictly superseded by current versions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Apply the same 'strictly superseded by same-provider/family successor'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.

providers/README.md

@@ -2,7 +2,7 @@
 
 LLM provider and model metadata for LibreFang. Each `.toml` file defines one provider's API configuration and all its available models with pricing, context windows, and capability flags.
 
-**Current state: 46 providers, 232+ models**
+**Current state: 46 providers, 220+ models**
 
 ---
 
@@ -13,13 +13,13 @@ LLM provider and model metadata for LibreFang. Each `.toml` file defines one pro
 | ID | Display Name | Base URL | API Key Env | Models | Description |
 |----|-------------|----------|-------------|--------|-------------|
 | `anthropic` | Anthropic | `https://api.anthropic.com` | `ANTHROPIC_API_KEY` | 7 | Claude family (Haiku / Sonnet / Opus); native Anthropic wire protocol, not OpenAI-compatible |
-| `openai` | OpenAI | `https://api.openai.com/v1` | `OPENAI_API_KEY` | 15 | GPT-4.x, o-series reasoning, image generation, TTS; also the fallback for codex-cli |
+| `openai` | OpenAI | `https://api.openai.com/v1` | `OPENAI_API_KEY` | 10 | GPT-5.x family + image generation; codex-cli fallback |
 | `gemini` | Google Gemini | `https://generativelanguage.googleapis.com` | `GEMINI_API_KEY` | 6 | Gemini 2.x family; native Google GenerativeLanguage protocol |
 | `xai` | xAI | `https://api.x.ai/v1` | `XAI_API_KEY` | 7 | Grok-3 family from Elon Musk's xAI |
 | `mistral` | Mistral AI | `https://api.mistral.ai/v1` | `MISTRAL_API_KEY` | 3 | Mistral Large / Small / Codestral; European frontier models |
 | `cohere` | Cohere | `https://api.cohere.com/v2` | `COHERE_API_KEY` | 4 | Command R+ family; strong RAG and tool-use models |
 | `deepseek` | DeepSeek | `https://api.deepseek.com/v1` | `DEEPSEEK_API_KEY` | 2 | DeepSeek-V3 (chat) + R1 (reasoning); extremely cost-effective |
-| `meta-llama` | Meta Llama | `https://api.llama.com/v1` | `LLAMA_API_KEY` | 4 | Official Meta Llama API — direct access to Llama 3.x |
+| `meta-llama` | Meta Llama | `https://api.llama.com/v1` | `LLAMA_API_KEY` | 3 | Official Meta Llama API — Llama 4 Maverick / Scout + Guard 4 |
 | `perplexity` | Perplexity AI | `https://api.perplexity.ai` | `PERPLEXITY_API_KEY` | 4 | Sonar family with live web search built in |
 
 ### Fast Inference / Compute Clouds
@@ -27,11 +27,11 @@ LLM provider and model metadata for LibreFang. Each `.toml` file defines one pro
 | ID | Display Name | Base URL | API Key Env | Models | Description |
 |----|-------------|----------|-------------|--------|-------------|
 | `groq` | Groq | `https://api.groq.com/openai/v1` | `GROQ_API_KEY` | 3 | GroqChip hardware; ~10× faster than GPU inference for supported models |
-| `cerebras` | Cerebras | `https://api.cerebras.ai/v1` | `CEREBRAS_API_KEY` | 4 | Wafer-scale chip inference; best-in-class throughput for Llama |
+| `cerebras` | Cerebras | `https://api.cerebras.ai/v1` | `CEREBRAS_API_KEY` | 3 | Wafer-scale chip inference; best-in-class throughput for Llama |
 | `sambanova` | SambaNova | `https://api.sambanova.ai/v1` | `SAMBANOVA_API_KEY` | 3 | Reconfigurable Dataflow Unit (RDU) inference; fast Llama variants |
-| `fireworks` | Fireworks AI | `https://api.fireworks.ai/inference/v1` | `FIREWORKS_API_KEY` | 5 | Serverless open-model hosting; fast cold-start |
-| `together` | Together AI | `https://api.together.xyz/v1` | `TOGETHER_API_KEY` | 8 | Open-model hosting (Llama, Qwen, Mistral) + fine-tuning API |
-| `nvidia-nim` | NVIDIA NIM | `https://integrate.api.nvidia.com/v1` | `NVIDIA_API_KEY` | 26 | NVIDIA NIM microservices; largest model selection in registry |
+| `fireworks` | Fireworks AI | `https://api.fireworks.ai/inference/v1` | `FIREWORKS_API_KEY` | 3 | Serverless open-model hosting; fast cold-start |
+| `together` | Together AI | `https://api.together.xyz/v1` | `TOGETHER_API_KEY` | 4 | Open-model hosting (Llama 4, DeepSeek) + fine-tuning API |
+| `nvidia-nim` | NVIDIA NIM | `https://integrate.api.nvidia.com/v1` | `NVIDIA_API_KEY` | 14 | NVIDIA NIM microservices; broad open-model selection |
 | `replicate` | Replicate | `https://api.replicate.com/v1` | `REPLICATE_API_TOKEN` | 3 | Run any model as a serverless API; image + video + LLM |
 | `huggingface` | Hugging Face | `https://api-inference.huggingface.co/v1` | `HF_API_KEY` | 3 | HF Serverless Inference API for hosted open models |
 
@@ -39,15 +39,15 @@ LLM provider and model metadata for LibreFang. Each `.toml` file defines one pro
 
 | ID | Display Name | Base URL | API Key Env | Models | Description |
 |----|-------------|----------|-------------|--------|-------------|
-| `bedrock` | AWS Bedrock | `https://bedrock-runtime.us-east-1.amazonaws.com` | `AWS_ACCESS_KEY_ID` | 11 | AWS-managed models (Claude, Llama, Mistral, Nova); IAM auth |
-| `vertex-ai` | Google Cloud Vertex AI | `https://us-central1-aiplatform.googleapis.com` | `GOOGLE_APPLICATION_CREDENTIALS` | 6 | GCP-hosted Gemini + third-party models; service account JSON auth |
+| `bedrock` | AWS Bedrock | `https://bedrock-runtime.us-east-1.amazonaws.com` | `AWS_ACCESS_KEY_ID` | 8 | AWS-managed models (Claude, Llama, Mistral, Nova); IAM auth |
+| `vertex-ai` | Google Cloud Vertex AI | `https://us-central1-aiplatform.googleapis.com` | `GOOGLE_APPLICATION_CREDENTIALS` | 4 | GCP-hosted Gemini + third-party models; service account JSON auth |
 | `github-copilot` | GitHub Copilot | `https://api.githubcopilot.com` | `GITHUB_TOKEN` | 1 | Uses `ApiFormat::Copilot` — proprietary protocol, not OpenAI-compatible; requires GitHub PAT with Copilot access |
 
 ### Aggregators / Routers
 
 | ID | Display Name | Base URL | API Key Env | Models | Description |
 |----|-------------|----------|-------------|--------|-------------|
-| `openrouter` | OpenRouter | `https://openrouter.ai/api/v1` | `OPENROUTER_API_KEY` | 18+ | Meta-provider routing to 300+ models; also receives models from OpenRouter-only providers via sync script |
+| `openrouter` | OpenRouter | `https://openrouter.ai/api/v1` | `OPENROUTER_API_KEY` | 38+ | Meta-provider routing to 300+ models; also receives models from OpenRouter-only providers via sync script |
 | `siliconflow` | SiliconFlow | `https://api.siliconflow.cn/v1` | `SILICONFLOW_API_KEY` | dynamic | 硅基流动 — Chinese open-model hosting; models discovered at runtime, not hardcoded in TOML |
 
 ### Chinese Providers
@@ -55,15 +55,15 @@ LLM provider and model metadata for LibreFang. Each `.toml` file defines one pro
 | ID | Display Name | Base URL | API Key Env | Models | Description |
 |----|-------------|----------|-------------|--------|-------------|
 | `qwen` | Qwen (Alibaba) | `https://dashscope.aliyuncs.com/compatible-mode/v1` | `DASHSCOPE_API_KEY` | 9 | Qwen3 family by Alibaba; multi-region support (`intl` / `us`) via `[provider.regions]` |
-| `moonshot` | Moonshot (Kimi) | `https://api.moonshot.ai/v1` | `MOONSHOT_API_KEY` | 5 | Kimi general chat models (moonshot-v1-8k/32k/128k) |
-| `minimax` | MiniMax | `https://api.minimax.io/v1` | `MINIMAX_API_KEY` | 8 | MiniMax M-series; strong Chinese + multilingual models |
-| `zhipu` | Zhipu AI (GLM) | `https://open.bigmodel.cn/api/paas/v4` | `ZHIPU_API_KEY` | 6 | GLM-4 family by Zhipu AI (智谱); general chat + vision |
+| `moonshot` | Moonshot (Kimi) | `https://api.moonshot.ai/v1` | `MOONSHOT_API_KEY` | 2 | Kimi K2 / K2.5 |
+| `minimax` | MiniMax | `https://api.minimax.io/v1` | `MINIMAX_API_KEY` | 4 | MiniMax M-series; strong Chinese + multilingual models |
+| `zhipu` | Zhipu AI (GLM) | `https://open.bigmodel.cn/api/paas/v4` | `ZHIPU_API_KEY` | 2 | GLM-4.7 / GLM-5 by Zhipu AI (智谱) |
 | `zai` | Z.AI | `https://api.z.ai/api/paas/v4` | `ZHIPU_API_KEY` | 2 | Z.AI general models; shares API key with zhipu |
-| `baichuan` | Baichuan (百川) | `https://api.baichuan-ai.com/v1` | `BAICHUAN_API_KEY` | 2 | Baichuan4 family; strong Chinese-language performance |
-| `volcengine` | Volcano Engine (Doubao) | `https://ark.cn-beijing.volces.com/api/v3` | `VOLCENGINE_API_KEY` | 8 | ByteDance Doubao models; Ark platform |
-| `stepfun` | Stepfun (阶跃星辰) | `https://api.stepfun.com/v1` | `STEPFUN_API_KEY` | 4 | Step-2 family; strong long-context and reasoning |
+| `baichuan` | Baichuan (百川) | `https://api.baichuan-ai.com/v1` | `BAICHUAN_API_KEY` | 1 | Baichuan4; strong Chinese-language performance |
+| `volcengine` | Volcano Engine (Doubao) | `https://ark.cn-beijing.volces.com/api/v3` | `VOLCENGINE_API_KEY` | 5 | ByteDance Doubao 2.0 + UI-TARS; Ark platform |
+| `stepfun` | Stepfun (阶跃星辰) | `https://api.stepfun.com/v1` | `STEPFUN_API_KEY` | 2 | Step-3 / Step-3.5 Flash; long-context reasoning |
 | `tencent` | Tencent | `https://api.hunyuan.cloud.tencent.com/v1` | `HUNYUAN_API_KEY` | 1 | Hunyuan models by Tencent |
-| `qianfan` | Baidu Qianfan | `https://qianfan.baidubce.com/v2` | `QIANFAN_API_KEY` | 3 | ERNIE family by Baidu; Qianfan platform |
+| `qianfan` | Baidu Qianfan | `https://qianfan.baidubce.com/v2` | `QIANFAN_API_KEY` | 1 | ERNIE 4.5 by Baidu; Qianfan platform |
 
 ### Coding-Specific Endpoints
 
@@ -72,7 +72,7 @@ Separate `base_url` for coding workloads — not just model aliases. Same API ke
 | ID | Display Name | Base URL | API Key Env | Models | vs. General |
 |----|-------------|----------|-------------|--------|-------------|
 | `kimi_coding` | Kimi for Code | `https://api.kimi.com/coding` | `KIMI_API_KEY` | 1 | vs `moonshot`: `api.moonshot.ai/v1` |
-| `alibaba-coding-plan` | Alibaba Coding Plan (Intl) | `https://coding-intl.dashscope.aliyuncs.com/v1` | `ALIBABA_CODING_PLAN_API_KEY` | 9 | vs `qwen`: `dashscope.aliyuncs.com`; aggregates models from multiple vendors (MiniMax, GLM, Kimi) |
+| `alibaba-coding-plan` | Alibaba Coding Plan (Intl) | `https://coding-intl.dashscope.aliyuncs.com/v1` | `ALIBABA_CODING_PLAN_API_KEY` | 5 | vs `qwen`: `dashscope.aliyuncs.com`; aggregates Qwen + GLM under one plan |
 | `volcengine_coding` | Volcano Engine Coding Plan | `https://ark.cn-beijing.volces.com/api/coding/v3` | `VOLCENGINE_API_KEY` | dynamic | vs `volcengine`: `/api/v3`; models discovered at runtime |
 | `zhipu_coding` | Zhipu Coding (CodeGeeX) | `https://open.bigmodel.cn/api/coding/paas/v4` | `ZHIPU_API_KEY` | 1 | vs `zhipu`: `/api/paas/v4`; CodeGeeX-4 coding model |
 | `zai_coding` | Z.AI Coding | `https://api.z.ai/api/coding/paas/v4` | `ZHIPU_API_KEY` | 2 | vs `zai`: `/api/paas/v4`; GLM coding variants |
@@ -86,7 +86,7 @@ Route through a locally-installed CLI tool. `key_required = false`, `base_url` i
 | `claude-code` | Claude Code | `claude` | 3 | `ClaudeCode` | Anthropic's official CLI; routes through Claude API with OAuth |
 | `codex-cli` | Codex CLI | `codex` | 6 | `CodexCli` | OpenAI Codex CLI; also serves as fallback for `openai` provider |
 | `gemini-cli` | Gemini CLI | `gemini` | 2 | `GeminiCli` | Google Gemini CLI; also serves as fallback for `gemini` provider |
-| `qwen-code` | Qwen Code | `qwen-code` | 3 | `QwenCode` | Alibaba Qwen coding CLI |
+| `qwen-code` | Qwen Code | `qwen-code` | 2 | `QwenCode` | Alibaba Qwen coding CLI |
 
 ### Local / Self-Hosted
 

providers/aion-labs.toml

@@ -7,26 +7,6 @@ api_key_env = "AION_LABS_API_KEY"
 base_url = "https://api.aionlabs.ai/v1"
 key_required = true
 
-[[models]]
-id = "aion-1.0"
-display_name = "AionLabs: Aion-1.0"
-tier = "frontier"
-context_window = 131072
-max_output_tokens = 32768
-input_cost_per_m = 4.0
-output_cost_per_m = 8.0
-supports_streaming = true
-
-[[models]]
-id = "aion-1.0-mini"
-display_name = "AionLabs: Aion-1.0-Mini"
-tier = "smart"
-context_window = 131072
-max_output_tokens = 32768
-input_cost_per_m = 0.7
-output_cost_per_m = 1.4
-supports_streaming = true
-
 [[models]]
 id = "aion-2.0"
 display_name = "AionLabs: Aion-2.0"

providers/alibaba-coding-plan.toml

@@ -1,5 +1,5 @@
 # Alibaba Coding Plan — https://www.alibabacloud.com/help/en/model-studio/coding-plan
-# Models: 8 (Pro plan: $50/month with quota-based access)
+# Models: 5 (Pro plan: $50/month with quota-based access)
 # Note: Monthly subscription for AI coding tools. Uses plan-specific API key (sk-sp-xxxxx)
 # and dedicated base URL (https://coding-intl.dashscope.aliyuncs.com/v1)
 
@@ -24,34 +24,6 @@ supports_streaming = true
 supports_thinking = true
 aliases = []
 
-[[models]]
-id = "alibaba-coding-plan/qwen3.5-plus"
-display_name = "Qwen 3.5 Plus"
-tier = "smart"
-context_window = 1000000
-max_output_tokens = 65536
-input_cost_per_m = 0.0
-output_cost_per_m = 0.0
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-supports_thinking = true
-aliases = []
-
-[[models]]
-id = "alibaba-coding-plan/qwen3-max-2026-01-23"
-display_name = "Qwen 3 Max (2026-01-23)"
-tier = "frontier"
-context_window = 262144
-max_output_tokens = 65536
-input_cost_per_m = 0.0
-output_cost_per_m = 0.0
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-supports_thinking = true
-aliases = []
-
 [[models]]
 id = "alibaba-coding-plan/qwen3-coder-next"
 display_name = "Qwen 3 Coder Next"
@@ -80,19 +52,6 @@ supports_streaming = true
 supports_thinking = true
 aliases = []
 
-[[models]]
-id = "alibaba-coding-plan/MiniMax-M2.5"
-display_name = "MiniMax M2.5"
-tier = "balanced"
-context_window = 196608
-max_output_tokens = 32768
-input_cost_per_m = 0.0
-output_cost_per_m = 0.0
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
 [[models]]
 id = "alibaba-coding-plan/glm-5"
 display_name = "GLM 5"
@@ -118,17 +77,3 @@ supports_tools = true
 supports_vision = false
 supports_streaming = true
 aliases = []
-
-[[models]]
-id = "alibaba-coding-plan/kimi-k2.5"
-display_name = "Kimi K2.5"
-tier = "smart"
-context_window = 262144
-max_output_tokens = 32768
-input_cost_per_m = 0.0
-output_cost_per_m = 0.0
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-supports_thinking = true
-aliases = []

providers/anthropic.toml

@@ -1,5 +1,5 @@
 # Anthropic — https://anthropic.com
-# Models: 7
+# Models: 5
 
 [provider]
 id = "anthropic"
@@ -56,34 +56,6 @@ supports_streaming = true
 supports_thinking = true
 aliases = ["sonnet", "claude-sonnet"]
 
-[[models]]
-id = "claude-opus-4-20250514"
-display_name = "Claude Opus 4"
-tier = "frontier"
-context_window = 200000
-max_output_tokens = 32000
-input_cost_per_m = 15.0
-output_cost_per_m = 75.0
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-supports_thinking = true
-aliases = []
-
-[[models]]
-id = "claude-sonnet-4-20250514"
-display_name = "Claude Sonnet 4"
-tier = "smart"
-context_window = 200000
-max_output_tokens = 64000
-input_cost_per_m = 3.0
-output_cost_per_m = 15.0
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-supports_thinking = true
-aliases = []
-
 [[models]]
 id = "claude-haiku-4-5-20251001"
 display_name = "Claude Haiku 4.5"

providers/baichuan.toml

@@ -1,5 +1,5 @@
 # Baichuan (百川智能) — https://platform.baichuan-ai.com
-# Models: 2
+# Models: 1
 
 [provider]
 id = "baichuan"
@@ -20,16 +20,3 @@ supports_tools = true
 supports_vision = false
 supports_streaming = true
 aliases = ["baichuan-4", "baichuan4"]
-
-[[models]]
-id = "Baichuan3-Turbo-128k"
-display_name = "Baichuan-3 Turbo 128K"
-tier = "smart"
-context_window = 131072
-max_output_tokens = 8192
-input_cost_per_m = 7.15
-output_cost_per_m = 7.15
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = ["baichuan-3-turbo", "baichuan3-turbo"]

providers/bedrock.toml

@@ -36,34 +36,6 @@ supports_streaming = true
 supports_thinking = true
 aliases = []
 
-[[models]]
-id = "bedrock/anthropic.claude-opus-4-20250514"
-display_name = "Claude Opus 4 (Bedrock)"
-tier = "frontier"
-context_window = 200000
-max_output_tokens = 32000
-input_cost_per_m = 15.00
-output_cost_per_m = 75.00
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-supports_thinking = true
-aliases = []
-
-[[models]]
-id = "bedrock/anthropic.claude-sonnet-4-20250514"
-display_name = "Claude Sonnet 4 (Bedrock)"
-tier = "smart"
-context_window = 200000
-max_output_tokens = 64000
-input_cost_per_m = 3.00
-output_cost_per_m = 15.00
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-supports_thinking = true
-aliases = []
-
 [[models]]
 id = "bedrock/anthropic.claude-haiku-4-5-20251001"
 display_name = "Claude Haiku 4.5 (Bedrock)"
@@ -91,19 +63,6 @@ supports_vision = true
 supports_streaming = true
 aliases = []
 
-[[models]]
-id = "bedrock/amazon.nova-lite-v1:0"
-display_name = "Amazon Nova Lite (Bedrock)"
-tier = "fast"
-context_window = 300000
-max_output_tokens = 5120
-input_cost_per_m = 0.06
-output_cost_per_m = 0.24
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = []
-
 [[models]]
 id = "bedrock/meta.llama3-3-70b-instruct-v1:0"
 display_name = "Llama 3.3 70B (Bedrock)"

providers/cerebras.toml

@@ -1,5 +1,5 @@
 # Cerebras — https://cerebras.ai
-# Models: 4
+# Models: 3
 
 [provider]
 id = "cerebras"
@@ -21,19 +21,6 @@ supports_vision = false
 supports_streaming = true
 aliases = []
 
-[[models]]
-id = "cerebras/llama3.1-8b"
-display_name = "Llama 3.1 8B (Cerebras)"
-tier = "fast"
-context_window = 128000
-max_output_tokens = 8192
-input_cost_per_m = 0.01
-output_cost_per_m = 0.01
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
 [[models]]
 id = "cerebras/llama-4-scout-17b"
 display_name = "Llama 4 Scout (Cerebras)"

providers/cohere.toml

@@ -1,5 +1,5 @@
 # Cohere — https://cohere.com
-# Models: 4
+# Models: 2
 
 [provider]
 id = "cohere"
@@ -21,19 +21,6 @@ supports_vision = false
 supports_streaming = true
 aliases = ["command-r"]
 
-[[models]]
-id = "command-r-08-2024"
-display_name = "Command R (Aug 2024)"
-tier = "balanced"
-context_window = 128000
-max_output_tokens = 4096
-input_cost_per_m = 0.15
-output_cost_per_m = 0.60
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
 [[models]]
 id = "command-a"
 display_name = "Command A"
@@ -46,16 +33,3 @@ supports_tools = true
 supports_vision = false
 supports_streaming = true
 aliases = ["command"]
-
-[[models]]
-id = "command-light"
-display_name = "Command Light"
-tier = "fast"
-context_window = 4096
-max_output_tokens = 4096
-input_cost_per_m = 0.30
-output_cost_per_m = 0.60
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []

providers/deepinfra.toml

@@ -8,54 +8,6 @@ api_key_env = "DEEPINFRA_API_KEY"
 base_url = "https://api.deepinfra.com/v1/openai"
 key_required = true
 
-[[models]]
-id = "meta-llama/Meta-Llama-3.1-8B-Instruct"
-display_name = "Llama 3.1 8B Instruct"
-tier = "fast"
-context_window = 128000
-max_output_tokens = 8192
-input_cost_per_m = 0.06
-output_cost_per_m = 0.06
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-
-[[models]]
-id = "meta-llama/Meta-Llama-3.1-70B-Instruct"
-display_name = "Llama 3.1 70B Instruct"
-tier = "balanced"
-context_window = 128000
-max_output_tokens = 8192
-input_cost_per_m = 0.35
-output_cost_per_m = 0.4
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-
-[[models]]
-id = "meta-llama/Meta-Llama-3.1-405B-Instruct"
-display_name = "Llama 3.1 405B Instruct"
-tier = "smart"
-context_window = 128000
-max_output_tokens = 8192
-input_cost_per_m = 0.8
-output_cost_per_m = 0.8
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-
-[[models]]
-id = "mistralai/Mistral-7B-Instruct-v0.3"
-display_name = "Mistral 7B Instruct v0.3"
-tier = "fast"
-context_window = 32768
-max_output_tokens = 8192
-input_cost_per_m = 0.07
-output_cost_per_m = 0.07
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-
 [[models]]
 id = "Qwen/Qwen2.5-72B-Instruct"
 display_name = "Qwen 2.5 72B Instruct"

providers/fireworks.toml

@@ -1,5 +1,5 @@
 # Fireworks AI — https://fireworks.ai
-# Models: 5
+# Models: 3
 
 [provider]
 id = "fireworks"
@@ -8,19 +8,6 @@ api_key_env = "FIREWORKS_API_KEY"
 base_url = "https://api.fireworks.ai/inference/v1"
 key_required = true
 
-[[models]]
-id = "accounts/fireworks/models/llama-v3p1-405b-instruct"
-display_name = "Llama 3.1 405B (Fireworks)"
-tier = "frontier"
-context_window = 131072
-max_output_tokens = 16384
-input_cost_per_m = 3.00
-output_cost_per_m = 3.00
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
 [[models]]
 id = "accounts/fireworks/models/llama-v3p3-70b-instruct"
 display_name = "Llama 3.3 70B (Fireworks)"
@@ -60,16 +47,3 @@ supports_tools = true
 supports_vision = false
 supports_streaming = true
 aliases = []
-
-[[models]]
-id = "accounts/fireworks/models/mixtral-8x22b-instruct"
-display_name = "Mixtral 8x22B (Fireworks)"
-tier = "balanced"
-context_window = 65536
-max_output_tokens = 4096
-input_cost_per_m = 0.90
-output_cost_per_m = 0.90
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []

providers/meta-llama.toml

@@ -1,5 +1,5 @@
 # meta-llama — https://llama.com
-# Models: 5
+# Models: 3
 
 [provider]
 id = "meta-llama"
@@ -28,16 +28,6 @@ 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 = 0.1
-output_cost_per_m = 0.32
-supports_streaming = true
-
 [[models]]
 id = "llama-guard-4-12b"
 display_name = "Meta: Llama Guard 4 12B"

providers/minimax.toml

@@ -1,5 +1,5 @@
 # MiniMax — https://minimax.io
-# Models: 8
+# Models: 4
 # Regions: international (default), china (minimaxi.com)
 
 [provider]
@@ -45,19 +45,6 @@ supports_vision = false
 supports_streaming = true
 aliases = ["minimax-m2.7-highspeed", "m2.7-highspeed"]
 
-[[models]]
-id = "minimax-text-01"
-display_name = "MiniMax Text 01"
-tier = "smart"
-context_window = 1048576
-max_output_tokens = 16384
-input_cost_per_m = 1.00
-output_cost_per_m = 3.00
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = ["minimax"]
-
 [[models]]
 id = "MiniMax-M2.5"
 display_name = "MiniMax M2.5"
@@ -83,42 +70,3 @@ supports_tools = true
 supports_vision = true
 supports_streaming = true
 aliases = ["minimax-m2.5-highspeed", "m2.5-highspeed"]
-
-[[models]]
-id = "MiniMax-M2.1"
-display_name = "MiniMax M2.1"
-tier = "smart"
-context_window = 1048576
-max_output_tokens = 16384
-input_cost_per_m = 1.00
-output_cost_per_m = 3.00
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = ["minimax-m2.1"]
-
-[[models]]
-id = "abab6.5-chat"
-display_name = "ABAB 6.5 Chat"
-tier = "balanced"
-context_window = 245760
-max_output_tokens = 8192
-input_cost_per_m = 0.50
-output_cost_per_m = 1.50
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "abab7-chat"
-display_name = "ABAB 7 Chat"
-tier = "smart"
-context_window = 524288
-max_output_tokens = 16384
-input_cost_per_m = 0.80
-output_cost_per_m = 2.40
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = ["abab7"]

providers/moonshot.toml

@@ -1,5 +1,5 @@
 # Moonshot / Kimi — https://moonshot.ai
-# Models: 5
+# Models: 2
 
 [provider]
 id = "moonshot"
@@ -8,45 +8,6 @@ api_key_env = "MOONSHOT_API_KEY"
 base_url = "https://api.moonshot.ai/v1"
 key_required = true
 
-[[models]]
-id = "moonshot-v1-128k"
-display_name = "Moonshot V1 128K"
-tier = "smart"
-context_window = 131072
-max_output_tokens = 8192
-input_cost_per_m = 2.00
-output_cost_per_m = 5.00
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = ["moonshot"]
-
-[[models]]
-id = "moonshot-v1-32k"
-display_name = "Moonshot V1 32K"
-tier = "balanced"
-context_window = 32768
-max_output_tokens = 8192
-input_cost_per_m = 1.00
-output_cost_per_m = 3.00
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "moonshot-v1-8k"
-display_name = "Moonshot V1 8K"
-tier = "fast"
-context_window = 8192
-max_output_tokens = 4096
-input_cost_per_m = 0.20
-output_cost_per_m = 2.00
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
 [[models]]
 id = "kimi-k2"
 display_name = "Kimi K2"

providers/nvidia-nim.toml

@@ -1,5 +1,5 @@
 # NVIDIA NIM — https://build.nvidia.com
-# Models: 22
+# Models: 14
 
 [provider]
 id = "nvidia-nim"
@@ -36,32 +36,6 @@ supports_vision = false
 supports_streaming = true
 aliases = ["nemotron-super"]
 
-[[models]]
-id = "nvidia/llama-3.1-nemotron-70b-instruct"
-display_name = "Nemotron 70B"
-tier = "balanced"
-context_window = 128000
-max_output_tokens = 4096
-input_cost_per_m = 1.2
-output_cost_per_m = 1.2
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = ["nemotron-70b"]
-
-[[models]]
-id = "nvidia/nemotron-mini-4b-instruct"
-display_name = "Nemotron Mini 4B"
-tier = "fast"
-context_window = 4096
-max_output_tokens = 4096
-input_cost_per_m = 0.01
-output_cost_per_m = 0.01
-supports_tools = false
-supports_vision = false
-supports_streaming = true
-aliases = ["nemotron-mini"]
-
 # ── Meta Llama models ────────────────────────────────────────────
 
 [[models]]
@@ -103,58 +77,6 @@ supports_vision = false
 supports_streaming = true
 aliases = ["llama-70b"]
 
-[[models]]
-id = "meta/llama-3.1-405b-instruct"
-display_name = "Llama 3.1 405B"
-tier = "frontier"
-context_window = 128000
-max_output_tokens = 4096
-input_cost_per_m = 2.00
-output_cost_per_m = 2.00
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = ["llama-405b"]
-
-[[models]]
-id = "meta/llama-3.1-8b-instruct"
-display_name = "Llama 3.1 8B"
-tier = "fast"
-context_window = 128000
-max_output_tokens = 4096
-input_cost_per_m = 0.03
-output_cost_per_m = 0.03
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "meta/llama-3.2-90b-vision-instruct"
-display_name = "Llama 3.2 90B Vision"
-tier = "smart"
-context_window = 128000
-max_output_tokens = 4096
-input_cost_per_m = 0.35
-output_cost_per_m = 0.40
-supports_tools = false
-supports_vision = true
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "meta/llama-3.2-11b-vision-instruct"
-display_name = "Llama 3.2 11B Vision"
-tier = "balanced"
-context_window = 128000
-max_output_tokens = 4096
-input_cost_per_m = 0.07
-output_cost_per_m = 0.07
-supports_tools = false
-supports_vision = true
-supports_streaming = true
-aliases = []
-
 # ── Mistral models ───────────────────────────────────────────────
 
 [[models]]
@@ -170,32 +92,6 @@ supports_vision = false
 supports_streaming = true
 aliases = ["mistral-large-3"]
 
-[[models]]
-id = "mistralai/mistral-small-3.1-24b-instruct-2503"
-display_name = "Mistral Small 3.1 24B"
-tier = "balanced"
-context_window = 128000
-max_output_tokens = 4096
-input_cost_per_m = 0.10
-output_cost_per_m = 0.30
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = ["mistral-small"]
-
-[[models]]
-id = "mistralai/mixtral-8x22b-instruct-v0.1"
-display_name = "Mixtral 8x22B"
-tier = "balanced"
-context_window = 65536
-max_output_tokens = 4096
-input_cost_per_m = 0.27
-output_cost_per_m = 0.27
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = ["mixtral"]
-
 # ── DeepSeek models ──────────────────────────────────────────────
 
 [[models]]
@@ -211,20 +107,6 @@ supports_vision = false
 supports_streaming = true
 aliases = ["deepseek-v3"]
 
-[[models]]
-id = "deepseek-ai/deepseek-r1-distill-qwen-32b"
-display_name = "DeepSeek R1 Distill 32B"
-tier = "balanced"
-context_window = 128000
-max_output_tokens = 8192
-input_cost_per_m = 0.10
-output_cost_per_m = 0.10
-supports_tools = false
-supports_vision = false
-supports_streaming = true
-supports_thinking = true
-aliases = ["deepseek-r1-32b"]
-
 # ── Qwen models ──────────────────────────────────────────────────
 
 [[models]]
@@ -241,33 +123,6 @@ supports_streaming = true
 supports_thinking = true
 aliases = ["qwen3.5"]
 
-[[models]]
-id = "qwen/qwen2.5-coder-32b-instruct"
-display_name = "Qwen 2.5 Coder 32B"
-tier = "balanced"
-context_window = 128000
-max_output_tokens = 8192
-input_cost_per_m = 0.10
-output_cost_per_m = 0.10
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = ["qwen-coder"]
-
-[[models]]
-id = "qwen/qwq-32b"
-display_name = "QWQ 32B"
-tier = "balanced"
-context_window = 128000
-max_output_tokens = 16384
-input_cost_per_m = 0.15
-output_cost_per_m = 0.58
-supports_tools = false
-supports_vision = false
-supports_streaming = true
-supports_thinking = true
-aliases = []
-
 # ── Google Gemma models ──────────────────────────────────────────
 
 [[models]]
@@ -298,19 +153,6 @@ supports_vision = true
 supports_streaming = true
 aliases = ["phi-4"]
 
-[[models]]
-id = "microsoft/phi-4-mini-instruct"
-display_name = "Phi-4 Mini"
-tier = "fast"
-context_window = 16384
-max_output_tokens = 4096
-input_cost_per_m = 0.03
-output_cost_per_m = 0.03
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = ["phi-4-mini"]
-
 [[models]]
 id = "nvidia/nemotron-3-nano-30b-a3b"
 display_name = "Nvidia: Nemotron 3 Nano 30B"

providers/openai.toml

@@ -9,73 +9,6 @@ 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"

providers/openrouter.toml

@@ -1,5 +1,5 @@
 # OpenRouter — https://openrouter.ai
-# Models: 18 (10 paid + 8 free)
+# Models: 38
 
 [provider]
 id = "openrouter"
@@ -39,33 +39,6 @@ supports_streaming = true
 supports_thinking = true
 aliases = []
 
-[[models]]
-id = "openrouter/anthropic/claude-sonnet-4"
-display_name = "Claude Sonnet 4 (OpenRouter)"
-tier = "smart"
-context_window = 200000
-max_output_tokens = 64000
-input_cost_per_m = 3.0
-output_cost_per_m = 15.0
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-supports_thinking = true
-aliases = []
-
-[[models]]
-id = "openrouter/openai/gpt-4o"
-display_name = "GPT-4o (OpenRouter)"
-tier = "smart"
-context_window = 128000
-max_output_tokens = 16384
-input_cost_per_m = 2.5
-output_cost_per_m = 10.0
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = []
-
 [[models]]
 id = "openrouter/deepseek/deepseek-chat"
 display_name = "DeepSeek V3 (OpenRouter)"
@@ -79,32 +52,6 @@ supports_vision = false
 supports_streaming = true
 aliases = []
 
-[[models]]
-id = "openrouter/meta-llama/llama-3.3-70b-instruct"
-display_name = "Llama 3.3 70B (OpenRouter)"
-tier = "balanced"
-context_window = 128000
-max_output_tokens = 32768
-input_cost_per_m = 0.39
-output_cost_per_m = 0.39
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "openrouter/qwen/qwen-2.5-72b-instruct"
-display_name = "Qwen 2.5 72B (OpenRouter)"
-tier = "balanced"
-context_window = 128000
-max_output_tokens = 32768
-input_cost_per_m = 0.36
-output_cost_per_m = 0.36
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
 [[models]]
 id = "openrouter/google/gemini-2.5-pro"
 display_name = "Gemini 2.5 Pro (OpenRouter)"
@@ -132,19 +79,6 @@ supports_vision = false
 supports_streaming = true
 aliases = []
 
-[[models]]
-id = "openrouter/google/gemma-2-9b-it"
-display_name = "Gemma 2 9B (OpenRouter)"
-tier = "fast"
-context_window = 8192
-max_output_tokens = 4096
-input_cost_per_m = 0.03
-output_cost_per_m = 0.09
-supports_tools = false
-supports_vision = false
-supports_streaming = true
-aliases = []
-
 [[models]]
 id = "openrouter/deepseek/deepseek-r1"
 display_name = "DeepSeek R1 (OpenRouter)"
@@ -244,19 +178,6 @@ supports_vision = false
 supports_streaming = true
 aliases = []
 
-[[models]]
-id = "openrouter/meta-llama/llama-3.2-3b-instruct:free"
-display_name = "Llama 3.2 3B Free (OpenRouter)"
-tier = "fast"
-context_window = 131072
-max_output_tokens = 4096
-input_cost_per_m = 0.0
-output_cost_per_m = 0.0
-supports_tools = false
-supports_vision = false
-supports_streaming = true
-aliases = []
-
 [[models]]
 id = "openrouter/ai21/jamba-large-1.7"
 display_name = "AI21: Jamba Large 1.7 (OpenRouter)"
@@ -277,16 +198,6 @@ input_cost_per_m = 0.09
 output_cost_per_m = 0.45
 supports_streaming = true
 
-[[models]]
-id = "openrouter/allenai/olmo-3-32b-think"
-display_name = "AllenAI: Olmo 3 32B Think (OpenRouter)"
-tier = "fast"
-context_window = 65536
-max_output_tokens = 65536
-input_cost_per_m = 0.15
-output_cost_per_m = 0.5
-supports_streaming = true
-
 [[models]]
 id = "openrouter/allenai/olmo-3.1-32b-instruct"
 display_name = "AllenAI: Olmo 3.1 32B Instruct (OpenRouter)"
@@ -307,16 +218,6 @@ input_cost_per_m = 0.3
 output_cost_per_m = 2.5
 supports_streaming = true
 
-[[models]]
-id = "openrouter/amazon/nova-lite-v1"
-display_name = "Amazon: Nova Lite 1.0 (OpenRouter)"
-tier = "fast"
-context_window = 300000
-max_output_tokens = 5120
-input_cost_per_m = 0.06
-output_cost_per_m = 0.24
-supports_streaming = true
-
 [[models]]
 id = "openrouter/amazon/nova-micro-v1"
 display_name = "Amazon: Nova Micro 1.0 (OpenRouter)"
@@ -417,16 +318,6 @@ input_cost_per_m = 2.5
 output_cost_per_m = 10.0
 supports_streaming = true
 
-[[models]]
-id = "openrouter/liquid/lfm-2-24b-a2b"
-display_name = "LiquidAI: LFM2-24B-A2B (OpenRouter)"
-tier = "fast"
-context_window = 32768
-max_output_tokens = 8192
-input_cost_per_m = 0.03
-output_cost_per_m = 0.12
-supports_streaming = true
-
 [[models]]
 id = "openrouter/liquid/lfm-2.5-1.2b-instruct:free"
 display_name = "LiquidAI: LFM2.5-1.2B-Instruct (free) (OpenRouter)"
@@ -457,46 +348,6 @@ input_cost_per_m = 0.135
 output_cost_per_m = 0.5
 supports_streaming = true
 
-[[models]]
-id = "openrouter/nousresearch/hermes-2-pro-llama-3-8b"
-display_name = "NousResearch: Hermes 2 Pro - Llama-3 8B (OpenRouter)"
-tier = "fast"
-context_window = 8192
-max_output_tokens = 8192
-input_cost_per_m = 0.14
-output_cost_per_m = 0.14
-supports_streaming = true
-
-[[models]]
-id = "openrouter/nousresearch/hermes-3-llama-3.1-405b"
-display_name = "Nous: Hermes 3 405B Instruct (OpenRouter)"
-tier = "smart"
-context_window = 131072
-max_output_tokens = 16384
-input_cost_per_m = 1.0
-output_cost_per_m = 1.0
-supports_streaming = true
-
-[[models]]
-id = "openrouter/nousresearch/hermes-3-llama-3.1-405b:free"
-display_name = "Nous: Hermes 3 405B Instruct (free) (OpenRouter)"
-tier = "fast"
-context_window = 131072
-max_output_tokens = 16384
-input_cost_per_m = 0.0
-output_cost_per_m = 0.0
-supports_streaming = true
-
-[[models]]
-id = "openrouter/nousresearch/hermes-3-llama-3.1-70b"
-display_name = "Nous: Hermes 3 70B Instruct (OpenRouter)"
-tier = "fast"
-context_window = 131072
-max_output_tokens = 16384
-input_cost_per_m = 0.3
-output_cost_per_m = 0.3
-supports_streaming = true
-
 [[models]]
 id = "openrouter/nousresearch/hermes-4-405b"
 display_name = "Nous: Hermes 4 405B (OpenRouter)"
@@ -527,16 +378,6 @@ input_cost_per_m = 0.2
 output_cost_per_m = 1.1
 supports_streaming = true
 
-[[models]]
-id = "openrouter/rekaai/reka-edge"
-display_name = "Reka Edge (OpenRouter)"
-tier = "fast"
-context_window = 16384
-max_output_tokens = 16384
-input_cost_per_m = 0.1
-output_cost_per_m = 0.1
-supports_streaming = true
-
 [[models]]
 id = "openrouter/rekaai/reka-flash-3"
 display_name = "Reka Flash 3 (OpenRouter)"

providers/qianfan.toml

@@ -1,5 +1,5 @@
 # Baidu Qianfan / ERNIE — https://qianfan.baidubce.com
-# Models: 3
+# Models: 1
 
 [provider]
 id = "qianfan"
@@ -20,29 +20,3 @@ supports_tools = true
 supports_vision = false
 supports_streaming = true
 aliases = ["ernie"]
-
-[[models]]
-id = "ernie-4.0-turbo-8k"
-display_name = "ERNIE 4.0 Turbo 8K"
-tier = "balanced"
-context_window = 8192
-max_output_tokens = 4096
-input_cost_per_m = 1.00
-output_cost_per_m = 3.00
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "ernie-speed-128k"
-display_name = "ERNIE Speed 128K"
-tier = "fast"
-context_window = 131072
-max_output_tokens = 4096
-input_cost_per_m = 0.0
-output_cost_per_m = 0.0
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []

providers/qwen-code.toml

@@ -1,5 +1,5 @@
 # Qwen Code CLI
-# Models: 3
+# Models: 2
 
 [provider]
 id = "qwen-code"
@@ -34,17 +34,3 @@ supports_tools = false
 supports_vision = false
 supports_streaming = true
 aliases = ["qwen-code-coder-plus"]
-
-[[models]]
-id = "qwen-code/qwq-32b"
-display_name = "QwQ 32B (CLI)"
-tier = "balanced"
-context_window = 131072
-max_output_tokens = 8192
-input_cost_per_m = 0.0
-output_cost_per_m = 0.0
-supports_tools = false
-supports_vision = false
-supports_streaming = true
-supports_thinking = true
-aliases = ["qwen-code-qwq"]

providers/stepfun.toml

@@ -1,5 +1,5 @@
 # Stepfun (阶跃星辰) — https://platform.stepfun.com
-# Models: 4
+# Models: 2
 
 [provider]
 id = "stepfun"
@@ -33,30 +33,3 @@ supports_tools = true
 supports_vision = true
 supports_streaming = true
 aliases = ["stepfun-3"]
-
-[[models]]
-id = "step-2-mini"
-display_name = "Step 2 Mini"
-tier = "fast"
-context_window = 32768
-max_output_tokens = 8192
-input_cost_per_m = 0.14
-output_cost_per_m = 0.29
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = ["stepfun-mini"]
-
-[[models]]
-id = "step-1o-turbo-vision"
-display_name = "Step 1o Turbo Vision"
-tier = "smart"
-context_window = 32768
-max_output_tokens = 8192
-input_cost_per_m = 0.36
-output_cost_per_m = 1.14
-supports_tools = false
-supports_vision = true
-supports_streaming = true
-supports_thinking = true
-aliases = ["stepfun-vision"]

providers/together.toml

@@ -1,5 +1,5 @@
 # Together AI — https://together.ai
-# Models: 8
+# Models: 4
 
 [provider]
 id = "together"
@@ -8,32 +8,6 @@ api_key_env = "TOGETHER_API_KEY"
 base_url = "https://api.together.xyz/v1"
 key_required = true
 
-[[models]]
-id = "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo"
-display_name = "Llama 3.1 405B (Together)"
-tier = "frontier"
-context_window = 130000
-max_output_tokens = 4096
-input_cost_per_m = 3.50
-output_cost_per_m = 3.50
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "meta-llama/Llama-3.3-70B-Instruct-Turbo"
-display_name = "Llama 3.3 70B (Together)"
-tier = "smart"
-context_window = 128000
-max_output_tokens = 4096
-input_cost_per_m = 0.88
-output_cost_per_m = 0.88
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
 [[models]]
 id = "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"
 display_name = "Llama 4 Maverick (Together)"
@@ -86,29 +60,3 @@ supports_tools = true
 supports_vision = false
 supports_streaming = true
 aliases = []
-
-[[models]]
-id = "Qwen/Qwen2.5-72B-Instruct-Turbo"
-display_name = "Qwen 2.5 72B (Together)"
-tier = "smart"
-context_window = 32768
-max_output_tokens = 4096
-input_cost_per_m = 0.20
-output_cost_per_m = 0.60
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "mistralai/Mixtral-8x22B-Instruct-v0.1"
-display_name = "Mixtral 8x22B (Together)"
-tier = "balanced"
-context_window = 65536
-max_output_tokens = 4096
-input_cost_per_m = 0.60
-output_cost_per_m = 0.60
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []

providers/vertex-ai.toml

@@ -63,31 +63,3 @@ supports_tools = true
 supports_vision = true
 supports_streaming = true
 aliases = []
-
-[[models]]
-id = "vertex-ai/gemini-1.5-pro"
-display_name = "Gemini 1.5 Pro (Vertex AI)"
-provider = "vertex-ai"
-tier = "smart"
-context_window = 2097152
-max_output_tokens = 8192
-input_cost_per_m = 1.25
-output_cost_per_m = 5.0
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "vertex-ai/gemini-1.5-flash"
-display_name = "Gemini 1.5 Flash (Vertex AI)"
-provider = "vertex-ai"
-tier = "fast"
-context_window = 1048576
-max_output_tokens = 8192
-input_cost_per_m = 0.075
-output_cost_per_m = 0.3
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = []

providers/volcengine.toml

@@ -1,5 +1,5 @@
 # Volcano Engine / Doubao — https://volcengine.com
-# Models: 7
+# Models: 5
 
 [provider]
 id = "volcengine"
@@ -60,45 +60,6 @@ supports_vision = false
 supports_streaming = true
 aliases = ["doubao-code", "doubao-seed-code"]
 
-[[models]]
-id = "doubao-seed-1-8"
-display_name = "Doubao Seed 1.8"
-tier = "smart"
-context_window = 262144
-max_output_tokens = 16384
-input_cost_per_m = 0.80
-output_cost_per_m = 2.00
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = ["doubao-1.8", "doubao-seed-1.8"]
-
-[[models]]
-id = "doubao-seed-1-6-251015"
-display_name = "Doubao Seed 1.6 Pro"
-tier = "smart"
-context_window = 262144
-max_output_tokens = 16384
-input_cost_per_m = 0.80
-output_cost_per_m = 2.00
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = ["doubao", "doubao-1.6"]
-
-[[models]]
-id = "doubao-seed-1-6-vision-251015"
-display_name = "Doubao Seed 1.6 Vision"
-tier = "smart"
-context_window = 262144
-max_output_tokens = 16384
-input_cost_per_m = 0.80
-output_cost_per_m = 2.00
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = ["doubao-vision"]
-
 [[models]]
 id = "ui-tars-1.5-7b"
 display_name = "ByteDance: UI-TARS 7B"

providers/xai.toml

@@ -1,5 +1,5 @@
 # xAI — https://x.ai
-# Models: 7
+# Models: 5
 
 [provider]
 id = "xai"
@@ -74,29 +74,3 @@ supports_tools = true
 supports_vision = false
 supports_streaming = true
 aliases = []
-
-[[models]]
-id = "grok-3"
-display_name = "Grok 3"
-tier = "frontier"
-context_window = 131072
-max_output_tokens = 32768
-input_cost_per_m = 3.0
-output_cost_per_m = 15.0
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = ["grok3"]
-
-[[models]]
-id = "grok-3-mini"
-display_name = "Grok 3 Mini"
-tier = "balanced"
-context_window = 131072
-max_output_tokens = 32768
-input_cost_per_m = 0.30
-output_cost_per_m = 0.50
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []

providers/xiaomi.toml

@@ -7,36 +7,6 @@ api_key_env = "XIAOMI_ACCESS_KEY_ID"
 base_url = "https://cnbj3-cloud-ml.api.xiaomi.net"
 key_required = true
 
-[[models]]
-id = "mimo-v2-flash"
-display_name = "Xiaomi: MiMo-V2-Flash"
-tier = "fast"
-context_window = 262144
-max_output_tokens = 65536
-input_cost_per_m = 0.09
-output_cost_per_m = 0.29
-supports_streaming = true
-
-[[models]]
-id = "mimo-v2-omni"
-display_name = "Xiaomi: MiMo-V2-Omni"
-tier = "fast"
-context_window = 262144
-max_output_tokens = 65536
-input_cost_per_m = 0.4
-output_cost_per_m = 2.0
-supports_streaming = true
-
-[[models]]
-id = "mimo-v2-pro"
-display_name = "Xiaomi: MiMo-V2-Pro"
-tier = "smart"
-context_window = 1048576
-max_output_tokens = 131072
-input_cost_per_m = 1.0
-output_cost_per_m = 3.0
-supports_streaming = true
-
 [[models]]
 id = "mimo-v2.5"
 display_name = "Xiaomi: MiMo-V2.5"

providers/zhipu.toml

@@ -1,5 +1,5 @@
 # Zhipu AI (GLM) — https://open.bigmodel.cn
-# Models: 6
+# Models: 2
 
 [provider]
 id = "zhipu"
@@ -8,58 +8,6 @@ api_key_env = "ZHIPU_API_KEY"
 base_url = "https://open.bigmodel.cn/api/paas/v4"
 key_required = true
 
-[[models]]
-id = "glm-4-plus"
-display_name = "GLM-4 Plus"
-tier = "smart"
-context_window = 131072
-max_output_tokens = 8192
-input_cost_per_m = 0.60
-output_cost_per_m = 2.20
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = ["glm"]
-
-[[models]]
-id = "glm-4-flash"
-display_name = "GLM-4 Flash"
-tier = "fast"
-context_window = 131072
-max_output_tokens = 8192
-input_cost_per_m = 0.0
-output_cost_per_m = 0.0
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "glm-4v-plus"
-display_name = "GLM-4V Plus"
-tier = "smart"
-context_window = 8192
-max_output_tokens = 4096
-input_cost_per_m = 0.60
-output_cost_per_m = 2.20
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "glm-4-long"
-display_name = "GLM-4 Long"
-tier = "balanced"
-context_window = 1000000
-max_output_tokens = 8192
-input_cost_per_m = 0.10
-output_cost_per_m = 0.10
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
 [[models]]
 id = "glm-5-20250605"
 display_name = "GLM-5"