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- anthropic: remove claude-3.5-sonnet (superseded by 4.x)
- openai: remove gpt-4o/4-turbo/3.5/o1/o3-mini (superseded by gpt-5/4.1/o3/o4-mini)
- gemini: remove 1.5-*/2.0-flash (superseded by 2.5/3.x)
- deepseek: remove coder/chat-v3-0324 (superseded by r1/v3)
- qwen: remove turbo/2.5-coder (superseded by qwen3)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- xai: remove grok-2 (superseded by grok-3/4)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

.githooks/pre-commit

@@ -0,0 +1,22 @@
+#!/usr/bin/env bash
+# Pre-commit hook: format staged TOML files with taplo
+
+STAGED=$(git diff --cached --name-only --diff-filter=ACM | grep '\.toml$')
+if [ -z "$STAGED" ]; then
+    exit 0
+fi
+
+if ! command -v taplo &>/dev/null; then
+    echo "taplo not found — install with: cargo install taplo-cli"
+    exit 1
+fi
+
+for f in $STAGED; do
+    if [ -f "$f" ]; then
+        taplo fmt "$f" 2>/dev/null
+        if ! git diff --quiet "$f"; then
+            echo "Formatted $f"
+            git add "$f"
+        fi
+    fi
+done

.gitignore

@@ -3,3 +3,5 @@
 __pycache__/
 *.pyc
 .env
+.make-setup-done
+.sync_marker

Makefile

@@ -12,6 +12,19 @@ SKILLS_DIR    := skills
 PLUGINS_DIR   := plugins
 PROVIDERS_DIR := providers
 
+# ── Setup ────────────────────────────────────────────────────────────────────
+
+.PHONY: setup
+setup: ## Configure git hooks for auto-formatting
+	git config core.hooksPath .githooks
+	@echo "Git hooks installed (.githooks/pre-commit)"
+
+# Auto-configure hooks on first make invocation
+-include .make-setup-done
+.make-setup-done:
+	@git config core.hooksPath .githooks 2>/dev/null || true
+	@touch .make-setup-done
+
 # ── Validation ────────────────────────────────────────────────────────────────
 
 .PHONY: validate

agents/hello-world/agent.toml

@@ -26,7 +26,9 @@ Answer questions directly. If you can look something up to give a better answer,
 
 When the user asks a factual question, use web_search to find current information rather than relying on potentially outdated knowledge. Present findings clearly without dumping raw search results.
 
-Keep responses brief (2-4 paragraphs max) unless the user asks for detail."""
+Keep responses brief (2-4 paragraphs max) unless the user asks for detail.
+
+Always reply in the same language the user uses. Never literally translate proper nouns, product names, or technical terms (e.g. "Hello World", "LibreFang", "Agent OS" stay as-is)."""
 
 [resources]
 max_llm_tokens_per_hour = 100000

providers/aion-labs.toml

@@ -1,48 +0,0 @@
-# aion-labs — auto-generated from OpenRouter API
-
-[provider]
-id = "aion-labs"
-display_name = "Aion Labs"
-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"
-tier = "smart"
-context_window = 131072
-max_output_tokens = 32768
-input_cost_per_m = 0.8
-output_cost_per_m = 1.6
-supports_streaming = true
-
-[[models]]
-id = "aion-rp-llama-3.1-8b"
-display_name = "AionLabs: Aion-RP 1.0 (8B)"
-tier = "smart"
-context_window = 32768
-max_output_tokens = 32768
-input_cost_per_m = 0.8
-output_cost_per_m = 1.6
-supports_streaming = true

providers/anthropic.toml

@@ -1,5 +1,5 @@
 # Anthropic — https://anthropic.com
-# Models: 7
+# Models: 6
 
 [provider]
 id = "anthropic"
@@ -91,17 +91,3 @@ supports_vision = true
 supports_streaming = true
 supports_thinking = true
 aliases = []
-
-[[models]]
-id = "claude-3-5-sonnet-20241022"
-display_name = "Claude 3.5 Sonnet"
-tier = "smart"
-context_window = 200000
-max_output_tokens = 8192
-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 = []

providers/arcee-ai.toml

@@ -1,79 +0,0 @@
-# arcee-ai — auto-generated from OpenRouter API
-
-[provider]
-id = "arcee-ai"
-display_name = "Arcee Ai"
-api_key_env = "ARCEE_API_KEY"
-base_url = "https://api.arcee.ai/v1"
-key_required = true
-
-[[models]]
-id = "coder-large"
-display_name = "Arcee AI: Coder Large"
-tier = "smart"
-context_window = 32768
-max_output_tokens = 8192
-input_cost_per_m = 0.5
-output_cost_per_m = 0.8
-supports_streaming = true
-
-[[models]]
-id = "maestro-reasoning"
-display_name = "Arcee AI: Maestro Reasoning"
-tier = "smart"
-context_window = 131072
-max_output_tokens = 32000
-input_cost_per_m = 0.9
-output_cost_per_m = 3.3
-supports_streaming = true
-supports_thinking = true
-
-[[models]]
-id = "spotlight"
-display_name = "Arcee AI: Spotlight"
-tier = "fast"
-context_window = 131072
-max_output_tokens = 65537
-input_cost_per_m = 0.18
-output_cost_per_m = 0.18
-supports_streaming = true
-
-[[models]]
-id = "trinity-large-preview:free"
-display_name = "Arcee AI: Trinity Large Preview (free)"
-tier = "fast"
-context_window = 131000
-max_output_tokens = 16384
-input_cost_per_m = 0.0
-output_cost_per_m = 0.0
-supports_streaming = true
-
-[[models]]
-id = "trinity-mini"
-display_name = "Arcee AI: Trinity Mini"
-tier = "fast"
-context_window = 131072
-max_output_tokens = 131072
-input_cost_per_m = 0.045
-output_cost_per_m = 0.15
-supports_streaming = true
-
-[[models]]
-id = "trinity-mini:free"
-display_name = "Arcee AI: Trinity Mini (free)"
-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 = "virtuoso-large"
-display_name = "Arcee AI: Virtuoso Large"
-tier = "smart"
-context_window = 131072
-max_output_tokens = 64000
-input_cost_per_m = 0.75
-output_cost_per_m = 1.2
-supports_streaming = true

providers/deepcogito.toml

@@ -1,18 +0,0 @@
-# deepcogito — auto-generated from OpenRouter API
-
-[provider]
-id = "deepcogito"
-display_name = "Deepcogito"
-api_key_env = "OPENROUTER_API_KEY"
-base_url = "https://openrouter.ai/api/v1"
-key_required = true
-
-[[models]]
-id = "cogito-v2.1-671b"
-display_name = "Deep Cogito: Cogito v2.1 671B"
-tier = "smart"
-context_window = 128000
-max_output_tokens = 16384
-input_cost_per_m = 1.25
-output_cost_per_m = 1.25
-supports_streaming = true

providers/deepseek.toml

@@ -1,5 +1,5 @@
 # DeepSeek — https://deepseek.com
-# Models: 4
+# Models: 2
 
 [provider]
 id = "deepseek"
@@ -34,29 +34,3 @@ supports_vision = false
 supports_streaming = true
 supports_thinking = true
 aliases = ["deepseek-r1"]
-
-[[models]]
-id = "deepseek-coder"
-display_name = "DeepSeek Coder V2"
-tier = "balanced"
-context_window = 128000
-max_output_tokens = 8192
-input_cost_per_m = 0.14
-output_cost_per_m = 0.28
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "deepseek-chat-v3-0324"
-display_name = "DeepSeek V3 0324"
-tier = "smart"
-context_window = 64000
-max_output_tokens = 8192
-input_cost_per_m = 0.19999999999999998
-output_cost_per_m = 0.77
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []

providers/eleutherai.toml

@@ -1,18 +0,0 @@
-# eleutherai — auto-generated from OpenRouter API
-
-[provider]
-id = "eleutherai"
-display_name = "Eleutherai"
-api_key_env = "KRATER_API_KEY"
-base_url = "https://api.krater.ai/v1"
-key_required = true
-
-[[models]]
-id = "llemma_7b"
-display_name = "EleutherAI: Llemma 7b"
-tier = "smart"
-context_window = 4096
-max_output_tokens = 4096
-input_cost_per_m = 0.8
-output_cost_per_m = 1.2
-supports_streaming = true

providers/essentialai.toml

@@ -1,18 +0,0 @@
-# essentialai — auto-generated from OpenRouter API
-
-[provider]
-id = "essentialai"
-display_name = "Essentialai"
-api_key_env = "OPENROUTER_API_KEY"
-base_url = "https://openrouter.ai/api/v1"
-key_required = true
-
-[[models]]
-id = "rnj-1-instruct"
-display_name = "EssentialAI: Rnj 1 Instruct"
-tier = "fast"
-context_window = 32768
-max_output_tokens = 8192
-input_cost_per_m = 0.15
-output_cost_per_m = 0.15
-supports_streaming = true

providers/gemini.toml

@@ -1,5 +1,5 @@
 # Google Gemini — https://ai.google.dev
-# Models: 10
+# Models: 6
 
 [provider]
 id = "gemini"
@@ -57,8 +57,8 @@ display_name = "Gemini 2.5 Flash Lite"
 tier = "fast"
 context_window = 1048576
 max_output_tokens = 8192
-input_cost_per_m = 0.09999999999999999
+input_cost_per_m = 0.1
-output_cost_per_m = 0.39999999999999997
+output_cost_per_m = 0.4
 supports_tools = true
 supports_vision = true
 supports_streaming = true
@@ -92,55 +92,3 @@ supports_vision = true
 supports_streaming = true
 supports_thinking = true
 aliases = ["flash"]
-
-[[models]]
-id = "gemini-2.0-flash"
-display_name = "Gemini 2.0 Flash"
-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 = []
-
-[[models]]
-id = "gemini-2.0-flash-lite"
-display_name = "Gemini 2.0 Flash Lite"
-tier = "fast"
-context_window = 1048576
-max_output_tokens = 8192
-input_cost_per_m = 0.075
-output_cost_per_m = 0.30
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "gemini-1.5-pro"
-display_name = "Gemini 1.5 Pro"
-tier = "smart"
-context_window = 2097152
-max_output_tokens = 8192
-input_cost_per_m = 1.25
-output_cost_per_m = 5.00
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "gemini-1.5-flash"
-display_name = "Gemini 1.5 Flash"
-tier = "fast"
-context_window = 1048576
-max_output_tokens = 8192
-input_cost_per_m = 0.075
-output_cost_per_m = 0.30
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = []

providers/groq.toml

@@ -1,5 +1,5 @@
 # Groq — https://groq.com
-# Models: 10
+# Models: 3
 
 [provider]
 id = "groq"
@@ -22,96 +22,18 @@ supports_streaming = true
 aliases = ["llama", "llama-70b"]
 
 [[models]]
-id = "llama-3.1-8b-instant"
+id = "meta-llama/llama-4-scout-17b-16e-instruct"
-display_name = "Llama 3.1 8B"
+display_name = "Llama 4 Scout 17B"
-tier = "fast"
-context_window = 128000
-max_output_tokens = 8192
-input_cost_per_m = 0.05
-output_cost_per_m = 0.08
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "llama-3.2-90b-vision-preview"
-display_name = "Llama 3.2 90B Vision"
-tier = "smart"
-context_window = 128000
-max_output_tokens = 8192
-input_cost_per_m = 0.90
-output_cost_per_m = 0.90
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "llama-3.2-11b-vision-preview"
-display_name = "Llama 3.2 11B Vision"
 tier = "balanced"
 context_window = 128000
 max_output_tokens = 8192
-input_cost_per_m = 0.18
+input_cost_per_m = 0.11
-output_cost_per_m = 0.18
+output_cost_per_m = 0.34
 supports_tools = true
 supports_vision = true
 supports_streaming = true
 aliases = []
 
-[[models]]
-id = "llama-3.2-3b-preview"
-display_name = "Llama 3.2 3B"
-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
-aliases = []
-
-[[models]]
-id = "llama-3.2-1b-preview"
-display_name = "Llama 3.2 1B"
-tier = "fast"
-context_window = 128000
-max_output_tokens = 8192
-input_cost_per_m = 0.04
-output_cost_per_m = 0.04
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "mixtral-8x7b-32768"
-display_name = "Mixtral 8x7B"
-tier = "balanced"
-context_window = 32768
-max_output_tokens = 4096
-input_cost_per_m = 0.024
-output_cost_per_m = 0.024
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = ["mixtral"]
-
-[[models]]
-id = "gemma2-9b-it"
-display_name = "Gemma 2 9B"
-tier = "fast"
-context_window = 8192
-max_output_tokens = 4096
-input_cost_per_m = 0.02
-output_cost_per_m = 0.02
-supports_tools = false
-supports_vision = false
-supports_streaming = true
-aliases = []
-
 [[models]]
 id = "qwen-qwq-32b"
 display_name = "Qwen QWQ 32B"
@@ -125,16 +47,3 @@ supports_vision = false
 supports_streaming = true
 supports_thinking = true
 aliases = []
-
-[[models]]
-id = "meta-llama/llama-4-scout-17b-16e-instruct"
-display_name = "Llama 4 Scout 17B"
-tier = "balanced"
-context_window = 128000
-max_output_tokens = 8192
-input_cost_per_m = 0.11
-output_cost_per_m = 0.34
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = []

providers/ibm-granite.toml

@@ -1,18 +0,0 @@
-# ibm-granite — auto-generated from OpenRouter API
-
-[provider]
-id = "ibm-granite"
-display_name = "Ibm Granite"
-api_key_env = "WATSONX_API_KEY"
-base_url = "https://us-south.ml.cloud.ibm.com/ml/v1"
-key_required = true
-
-[[models]]
-id = "granite-4.0-h-micro"
-display_name = "IBM: Granite 4.0 Micro"
-tier = "fast"
-context_window = 131000
-max_output_tokens = 16384
-input_cost_per_m = 0.017
-output_cost_per_m = 0.11
-supports_streaming = true

providers/inception.toml

@@ -1,38 +0,0 @@
-# inception — auto-generated from OpenRouter API
-
-[provider]
-id = "inception"
-display_name = "Inception"
-api_key_env = "INCEPTION_API_KEY"
-base_url = "https://api.inceptionlabs.ai/v1"
-key_required = true
-
-[[models]]
-id = "mercury"
-display_name = "Inception: Mercury"
-tier = "fast"
-context_window = 128000
-max_output_tokens = 32000
-input_cost_per_m = 0.25
-output_cost_per_m = 0.75
-supports_streaming = true
-
-[[models]]
-id = "mercury-2"
-display_name = "Inception: Mercury 2"
-tier = "fast"
-context_window = 128000
-max_output_tokens = 50000
-input_cost_per_m = 0.25
-output_cost_per_m = 0.75
-supports_streaming = true
-
-[[models]]
-id = "mercury-coder"
-display_name = "Inception: Mercury Coder"
-tier = "fast"
-context_window = 128000
-max_output_tokens = 32000
-input_cost_per_m = 0.25
-output_cost_per_m = 0.75
-supports_streaming = true

providers/inflection.toml

@@ -1,28 +0,0 @@
-# inflection — auto-generated from OpenRouter API
-
-[provider]
-id = "inflection"
-display_name = "Inflection"
-api_key_env = "OPENROUTER_API_KEY"
-base_url = "https://openrouter.ai/api/v1"
-key_required = true
-
-[[models]]
-id = "inflection-3-pi"
-display_name = "Inflection: Inflection 3 Pi"
-tier = "smart"
-context_window = 8000
-max_output_tokens = 1024
-input_cost_per_m = 2.5
-output_cost_per_m = 10.0
-supports_streaming = true
-
-[[models]]
-id = "inflection-3-productivity"
-display_name = "Inflection: Inflection 3 Productivity"
-tier = "smart"
-context_window = 8000
-max_output_tokens = 1024
-input_cost_per_m = 2.5
-output_cost_per_m = 10.0
-supports_streaming = true

providers/kwaipilot.toml

@@ -1,18 +0,0 @@
-# kwaipilot — auto-generated from OpenRouter API
-
-[provider]
-id = "kwaipilot"
-display_name = "Kwaipilot"
-api_key_env = "OPENROUTER_API_KEY"
-base_url = "https://openrouter.ai/api/v1"
-key_required = true
-
-[[models]]
-id = "kat-coder-pro"
-display_name = "Kwaipilot: KAT-Coder-Pro V1"
-tier = "fast"
-context_window = 256000
-max_output_tokens = 128000
-input_cost_per_m = 0.3
-output_cost_per_m = 1.2
-supports_streaming = true

providers/lemonade.toml

@@ -1,9 +0,0 @@
-# Lemonade — local NPU accelerated inference
-# Models: 0 (all models discovered dynamically at runtime)
-
-[provider]
-id = "lemonade"
-display_name = "Lemonade"
-api_key_env = "LEMONADE_API_KEY"
-base_url = "http://localhost:8888/api/v1"
-key_required = false

providers/liquid.toml

@@ -1,59 +0,0 @@
-# liquid — auto-generated from OpenRouter API
-
-[provider]
-id = "liquid"
-display_name = "Liquid"
-api_key_env = "OPENROUTER_API_KEY"
-base_url = "https://openrouter.ai/api/v1"
-key_required = true
-
-[[models]]
-id = "lfm-2-24b-a2b"
-display_name = "LiquidAI: LFM2-24B-A2B"
-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 = "lfm-2.2-6b"
-display_name = "LiquidAI: LFM2-2.6B"
-tier = "fast"
-context_window = 32768
-max_output_tokens = 8192
-input_cost_per_m = 0.01
-output_cost_per_m = 0.02
-supports_streaming = true
-
-[[models]]
-id = "lfm-2.5-1.2b-instruct:free"
-display_name = "LiquidAI: LFM2.5-1.2B-Instruct (free)"
-tier = "fast"
-context_window = 32768
-max_output_tokens = 8192
-input_cost_per_m = 0.0
-output_cost_per_m = 0.0
-supports_streaming = true
-
-[[models]]
-id = "lfm-2.5-1.2b-thinking:free"
-display_name = "LiquidAI: LFM2.5-1.2B-Thinking (free)"
-tier = "fast"
-context_window = 32768
-max_output_tokens = 8192
-input_cost_per_m = 0.0
-output_cost_per_m = 0.0
-supports_streaming = true
-supports_thinking = true
-
-[[models]]
-id = "lfm2-8b-a1b"
-display_name = "LiquidAI: LFM2-8B-A1B"
-tier = "fast"
-context_window = 32768
-max_output_tokens = 8192
-input_cost_per_m = 0.01
-output_cost_per_m = 0.02
-supports_streaming = true

providers/meta-llama.toml

@@ -1,4 +1,5 @@
-# meta-llama — auto-generated from OpenRouter API
+# meta-llama — https://llama.com
+# Models: 5
 
 [provider]
 id = "meta-llama"
@@ -7,106 +8,6 @@ api_key_env = "LLAMA_API_KEY"
 base_url = "https://api.llama.com/v1"
 key_required = true
 
-[[models]]
-id = "llama-3-70b-instruct"
-display_name = "Meta: Llama 3 70B Instruct"
-tier = "smart"
-context_window = 8192
-max_output_tokens = 8000
-input_cost_per_m = 0.51
-output_cost_per_m = 0.74
-supports_streaming = true
-
-[[models]]
-id = "llama-3-8b-instruct"
-display_name = "Meta: Llama 3 8B Instruct"
-tier = "fast"
-context_window = 8192
-max_output_tokens = 16384
-input_cost_per_m = 0.03
-output_cost_per_m = 0.04
-supports_streaming = true
-
-[[models]]
-id = "llama-3.1-70b-instruct"
-display_name = "Meta: Llama 3.1 70B Instruct"
-tier = "fast"
-context_window = 131072
-max_output_tokens = 16384
-input_cost_per_m = 0.4
-output_cost_per_m = 0.4
-supports_streaming = true
-
-[[models]]
-id = "llama-3.1-8b-instruct"
-display_name = "Meta: Llama 3.1 8B Instruct"
-tier = "fast"
-context_window = 16384
-max_output_tokens = 16384
-input_cost_per_m = 0.02
-output_cost_per_m = 0.05
-supports_streaming = true
-
-[[models]]
-id = "llama-3.2-11b-vision-instruct"
-display_name = "Meta: Llama 3.2 11B Vision Instruct"
-tier = "fast"
-context_window = 131072
-max_output_tokens = 16384
-input_cost_per_m = 0.245
-output_cost_per_m = 0.245
-supports_streaming = true
-
-[[models]]
-id = "llama-3.2-1b-instruct"
-display_name = "Meta: Llama 3.2 1B Instruct"
-tier = "fast"
-context_window = 60000
-max_output_tokens = 15000
-input_cost_per_m = 0.027
-output_cost_per_m = 0.2
-supports_streaming = true
-
-[[models]]
-id = "llama-3.2-3b-instruct"
-display_name = "Meta: Llama 3.2 3B Instruct"
-tier = "fast"
-context_window = 80000
-max_output_tokens = 16384
-input_cost_per_m = 0.051
-output_cost_per_m = 0.34
-supports_streaming = true
-
-[[models]]
-id = "llama-3.2-3b-instruct:free"
-display_name = "Meta: Llama 3.2 3B Instruct (free)"
-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 = "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-3.3-70b-instruct:free"
-display_name = "Meta: Llama 3.3 70B Instruct (free)"
-tier = "fast"
-context_window = 65536
-max_output_tokens = 16384
-input_cost_per_m = 0.0
-output_cost_per_m = 0.0
-supports_streaming = true
-
 [[models]]
 id = "llama-4-maverick"
 display_name = "Meta: Llama 4 Maverick"
@@ -128,8 +29,8 @@ output_cost_per_m = 0.3
 supports_streaming = true
 
 [[models]]
-id = "llama-guard-3-8b"
+id = "llama-3.3-70b-instruct"
-display_name = "Llama Guard 3 8B"
+display_name = "Meta: Llama 3.3 70B Instruct"
 tier = "fast"
 context_window = 131072
 max_output_tokens = 16384

providers/mistral.toml

@@ -1,5 +1,5 @@
 # Mistral AI — https://mistral.ai
-# Models: 6
+# Models: 3
 
 [provider]
 id = "mistral"
@@ -21,19 +21,6 @@ supports_vision = false
 supports_streaming = true
 aliases = ["mistral"]
 
-[[models]]
-id = "mistral-medium-latest"
-display_name = "Mistral Medium"
-tier = "balanced"
-context_window = 128000
-max_output_tokens = 8192
-input_cost_per_m = 2.70
-output_cost_per_m = 8.10
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
 [[models]]
 id = "mistral-small-latest"
 display_name = "Mistral Small"
@@ -59,29 +46,3 @@ supports_tools = true
 supports_vision = false
 supports_streaming = true
 aliases = ["codestral"]
-
-[[models]]
-id = "open-mistral-nemo"
-display_name = "Mistral Nemo"
-tier = "fast"
-context_window = 128000
-max_output_tokens = 8192
-input_cost_per_m = 0.15
-output_cost_per_m = 0.15
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = ["mistral-nemo"]
-
-[[models]]
-id = "pixtral-large-latest"
-display_name = "Pixtral Large"
-tier = "smart"
-context_window = 128000
-max_output_tokens = 8192
-input_cost_per_m = 2.00
-output_cost_per_m = 6.00
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = ["pixtral"]

providers/morph.toml

@@ -1,28 +0,0 @@
-# morph — auto-generated from OpenRouter API
-
-[provider]
-id = "morph"
-display_name = "Morph"
-api_key_env = "MORPH_API_KEY"
-base_url = "https://api.morphllm.com/v1"
-key_required = true
-
-[[models]]
-id = "morph-v3-fast"
-display_name = "Morph: Morph V3 Fast"
-tier = "smart"
-context_window = 81920
-max_output_tokens = 38000
-input_cost_per_m = 0.8
-output_cost_per_m = 1.2
-supports_streaming = true
-
-[[models]]
-id = "morph-v3-large"
-display_name = "Morph: Morph V3 Large"
-tier = "smart"
-context_window = 262144
-max_output_tokens = 131072
-input_cost_per_m = 0.9
-output_cost_per_m = 1.9
-supports_streaming = true

providers/nex-agi.toml

@@ -1,18 +0,0 @@
-# nex-agi — auto-generated from OpenRouter API
-
-[provider]
-id = "nex-agi"
-display_name = "Nex Agi"
-api_key_env = "OPENROUTER_API_KEY"
-base_url = "https://openrouter.ai/api/v1"
-key_required = true
-
-[[models]]
-id = "deepseek-v3.1-nex-n1"
-display_name = "Nex AGI: DeepSeek V3.1 Nex N1"
-tier = "fast"
-context_window = 131072
-max_output_tokens = 163840
-input_cost_per_m = 0.135
-output_cost_per_m = 0.5
-supports_streaming = true

providers/nousresearch.toml

@@ -1,68 +0,0 @@
-# nousresearch — auto-generated from OpenRouter API
-
-[provider]
-id = "nousresearch"
-display_name = "Nousresearch"
-api_key_env = "OPENROUTER_API_KEY"
-base_url = "https://openrouter.ai/api/v1"
-key_required = true
-
-[[models]]
-id = "hermes-2-pro-llama-3-8b"
-display_name = "NousResearch: Hermes 2 Pro - Llama-3 8B"
-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 = "hermes-3-llama-3.1-405b"
-display_name = "Nous: Hermes 3 405B Instruct"
-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 = "hermes-3-llama-3.1-405b:free"
-display_name = "Nous: Hermes 3 405B Instruct (free)"
-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 = "hermes-3-llama-3.1-70b"
-display_name = "Nous: Hermes 3 70B Instruct"
-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 = "hermes-4-405b"
-display_name = "Nous: Hermes 4 405B"
-tier = "smart"
-context_window = 131072
-max_output_tokens = 16384
-input_cost_per_m = 1.0
-output_cost_per_m = 3.0
-supports_streaming = true
-
-[[models]]
-id = "hermes-4-70b"
-display_name = "Nous: Hermes 4 70B"
-tier = "fast"
-context_window = 131072
-max_output_tokens = 16384
-input_cost_per_m = 0.13
-output_cost_per_m = 0.4
-supports_streaming = true

providers/ollama.toml

@@ -1,5 +1,5 @@
 # Ollama — https://ollama.com
-# Models: 6 (static entries; additional models discovered dynamically at runtime)
+# Current-generation models only. Additional models are discovered dynamically at runtime.
 
 [provider]
 id = "ollama"
@@ -9,80 +9,96 @@ base_url = "http://localhost:11434/v1"
 key_required = false
 
 [[models]]
-id = "llama3.2"
+id = "gemma4"
-display_name = "Llama 3.2 (Ollama)"
+display_name = "Gemma 4"
 tier = "local"
 context_window = 128000
-max_output_tokens = 4096
+max_output_tokens = 8192
 input_cost_per_m = 0.0
 output_cost_per_m = 0.0
 supports_tools = true
-supports_vision = false
+supports_vision = true
 supports_streaming = true
-aliases = []
+supports_thinking = true
-
+aliases = ["gemma4:latest"]
-[[models]]
-id = "llama3.1"
-display_name = "Llama 3.1 (Ollama)"
-tier = "local"
-context_window = 128000
-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 = []
-
-[[models]]
-id = "mistral:latest"
-display_name = "Mistral (Ollama)"
-tier = "local"
-context_window = 32768
-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 = []
-
-[[models]]
-id = "qwen2.5"
-display_name = "Qwen 2.5 (Ollama)"
-tier = "local"
-context_window = 32768
-max_output_tokens = 4096
-input_cost_per_m = 0.2
-output_cost_per_m = 0.6
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "phi3"
-display_name = "Phi-3 (Ollama)"
-tier = "local"
-context_window = 128000
-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 = "deepseek-r1:latest"
-display_name = "DeepSeek R1 (Ollama)"
+display_name = "DeepSeek R1"
 tier = "local"
 context_window = 64000
-max_output_tokens = 4096
+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 = ["deepseek-r1"]
+
+[[models]]
+id = "qwen3"
+display_name = "Qwen 3"
+tier = "local"
+context_window = 40960
+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
+supports_thinking = true
+aliases = ["qwen3:latest"]
+
+[[models]]
+id = "qwq"
+display_name = "QwQ"
+tier = "local"
+context_window = 40960
+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
+supports_thinking = true
+aliases = ["qwq:latest"]
+
+[[models]]
+id = "llama4"
+display_name = "Llama 4"
+tier = "local"
+context_window = 128000
+max_output_tokens = 8192
+input_cost_per_m = 0.0
+output_cost_per_m = 0.0
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = ["llama4:latest"]
+
+[[models]]
+id = "mistral:latest"
+display_name = "Mistral"
+tier = "local"
+context_window = 32768
+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 = []
+
+[[models]]
+id = "phi4"
+display_name = "Phi-4"
+tier = "local"
+context_window = 16384
+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 = ["phi4:latest"]

providers/openai.toml

@@ -1,5 +1,5 @@
 # OpenAI — https://openai.com
-# Models: 18 (including 2 Codex variants)
+# Models: 13 (including 2 Codex variants)
 
 [provider]
 id = "openai"
@@ -9,32 +9,6 @@ base_url = "https://api.openai.com/v1"
 key_required = true
 media_capabilities = ["image_generation", "text_to_speech"]
 
-[[models]]
-id = "gpt-4o"
-display_name = "GPT-4o"
-tier = "smart"
-context_window = 128000
-max_output_tokens = 16384
-input_cost_per_m = 2.50
-output_cost_per_m = 10.0
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = ["gpt4", "gpt4o"]
-
-[[models]]
-id = "gpt-4o-mini"
-display_name = "GPT-4o Mini"
-tier = "fast"
-context_window = 128000
-max_output_tokens = 16384
-input_cost_per_m = 0.15
-output_cost_per_m = 0.60
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = ["gpt4-mini"]
-
 [[models]]
 id = "gpt-4.1"
 display_name = "GPT-4.1"
@@ -88,20 +62,6 @@ supports_streaming = true
 supports_thinking = true
 aliases = []
 
-[[models]]
-id = "o3-mini"
-display_name = "o3-mini"
-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 = false
-supports_streaming = true
-supports_thinking = true
-aliases = []
-
 [[models]]
 id = "o4-mini"
 display_name = "o4-mini"
@@ -116,32 +76,6 @@ supports_streaming = true
 supports_thinking = true
 aliases = []
 
-[[models]]
-id = "gpt-4-turbo"
-display_name = "GPT-4 Turbo"
-tier = "smart"
-context_window = 128000
-max_output_tokens = 4096
-input_cost_per_m = 10.00
-output_cost_per_m = 30.00
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "gpt-3.5-turbo"
-display_name = "GPT-3.5 Turbo"
-tier = "fast"
-context_window = 16385
-max_output_tokens = 4096
-input_cost_per_m = 0.5
-output_cost_per_m = 1.5
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
 [[models]]
 id = "gpt-5"
 display_name = "GPT-5"

providers/prime-intellect.toml

@@ -1,18 +0,0 @@
-# prime-intellect — auto-generated from OpenRouter API
-
-[provider]
-id = "prime-intellect"
-display_name = "Prime Intellect"
-api_key_env = "OPENROUTER_API_KEY"
-base_url = "https://openrouter.ai/api/v1"
-key_required = true
-
-[[models]]
-id = "intellect-3"
-display_name = "Prime Intellect: INTELLECT-3"
-tier = "fast"
-context_window = 131072
-max_output_tokens = 131072
-input_cost_per_m = 0.2
-output_cost_per_m = 1.1
-supports_streaming = true

providers/qwen.toml

@@ -1,5 +1,5 @@
 # Qwen / Alibaba — https://dashscope.aliyuncs.com
-# Models: 11
+# Models: 9
 # Regions: china (default), intl (Singapore), us (Virginia)
 
 [provider]
@@ -41,19 +41,6 @@ supports_vision = false
 supports_streaming = true
 aliases = ["qwen"]
 
-[[models]]
-id = "qwen-turbo"
-display_name = "Qwen Turbo"
-tier = "fast"
-context_window = 131072
-max_output_tokens = 8192
-input_cost_per_m = 0.0325
-output_cost_per_m = 0.13
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
 [[models]]
 id = "qwen-vl-plus"
 display_name = "Qwen VL Plus"
@@ -61,15 +48,28 @@ tier = "smart"
 context_window = 32768
 max_output_tokens = 8192
 input_cost_per_m = 0.1365
-output_cost_per_m = 0.40950000000000003
+output_cost_per_m = 0.4095
 supports_tools = false
 supports_vision = true
 supports_streaming = true
 aliases = []
 
 [[models]]
-id = "qwen-coder-plus"
+id = "qwen-vl-max"
-display_name = "Qwen Coder Plus"
+display_name = "Qwen VL Max"
+tier = "frontier"
+context_window = 32768
+max_output_tokens = 8192
+input_cost_per_m = 0.52
+output_cost_per_m = 2.08
+supports_tools = false
+supports_vision = true
+supports_streaming = true
+aliases = []
+
+[[models]]
+id = "qwen-coder-plus-latest"
+display_name = "Qwen Coder Plus (Latest)"
 tier = "smart"
 context_window = 131072
 max_output_tokens = 8192
@@ -78,7 +78,7 @@ output_cost_per_m = 2.00
 supports_tools = true
 supports_vision = false
 supports_streaming = true
-aliases = []
+aliases = ["qwen-coder"]
 
 [[models]]
 id = "qwen-long"
@@ -121,45 +121,6 @@ supports_streaming = true
 supports_thinking = true
 aliases = []
 
-[[models]]
-id = "qwen-coder-plus-latest"
-display_name = "Qwen Coder Plus (Latest)"
-tier = "smart"
-context_window = 131072
-max_output_tokens = 8192
-input_cost_per_m = 0.80
-output_cost_per_m = 2.00
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = ["qwen-coder"]
-
-[[models]]
-id = "qwen2.5-coder-32b-instruct"
-display_name = "Qwen 2.5 Coder 32B"
-tier = "balanced"
-context_window = 131072
-max_output_tokens = 8192
-input_cost_per_m = 0.80
-output_cost_per_m = 2.00
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "qwen-vl-max"
-display_name = "Qwen VL Max"
-tier = "frontier"
-context_window = 32768
-max_output_tokens = 8192
-input_cost_per_m = 0.52
-output_cost_per_m = 2.08
-supports_tools = false
-supports_vision = true
-supports_streaming = true
-aliases = []
-
 [[models]]
 id = "tongyi-deepresearch-30b-a3b"
 display_name = "Tongyi DeepResearch 30B A3B"

providers/reka.toml

@@ -1,28 +0,0 @@
-# reka — auto-generated from OpenRouter API
-
-[provider]
-id = "reka"
-display_name = "Reka"
-api_key_env = "REKA_API_KEY"
-base_url = "https://api.reka.ai/v1"
-key_required = true
-
-[[models]]
-id = "reka-edge"
-display_name = "Reka Edge"
-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 = "reka-flash-3"
-display_name = "Reka: Flash 3"
-tier = "fast"
-context_window = 131072
-max_output_tokens = 32768
-input_cost_per_m = 0.1
-output_cost_per_m = 0.2
-supports_streaming = true

providers/relace.toml

@@ -1,28 +0,0 @@
-# relace — auto-generated from OpenRouter API
-
-[provider]
-id = "relace"
-display_name = "Relace"
-api_key_env = "OPENROUTER_API_KEY"
-base_url = "https://openrouter.ai/api/v1"
-key_required = true
-
-[[models]]
-id = "relace-apply-3"
-display_name = "Relace: Relace Apply 3"
-tier = "smart"
-context_window = 256000
-max_output_tokens = 128000
-input_cost_per_m = 0.85
-output_cost_per_m = 1.25
-supports_streaming = true
-
-[[models]]
-id = "relace-search"
-display_name = "Relace: Relace Search"
-tier = "smart"
-context_window = 256000
-max_output_tokens = 128000
-input_cost_per_m = 1.0
-output_cost_per_m = 3.0
-supports_streaming = true

providers/switchpoint.toml

@@ -1,18 +0,0 @@
-# switchpoint — auto-generated from OpenRouter API
-
-[provider]
-id = "switchpoint"
-display_name = "Switchpoint"
-api_key_env = "OPENROUTER_API_KEY"
-base_url = "https://openrouter.ai/api/v1"
-key_required = true
-
-[[models]]
-id = "router"
-display_name = "Switchpoint Router"
-tier = "smart"
-context_window = 131072
-max_output_tokens = 16384
-input_cost_per_m = 0.85
-output_cost_per_m = 3.4
-supports_streaming = true

providers/tngtech.toml

@@ -1,19 +0,0 @@
-# tngtech — auto-generated from OpenRouter API
-
-[provider]
-id = "tngtech"
-display_name = "Tngtech"
-api_key_env = "OPENROUTER_API_KEY"
-base_url = "https://openrouter.ai/api/v1"
-key_required = true
-
-[[models]]
-id = "deepseek-r1t2-chimera"
-display_name = "TNG: DeepSeek R1T2 Chimera"
-tier = "fast"
-context_window = 163840
-max_output_tokens = 163840
-input_cost_per_m = 0.3
-output_cost_per_m = 1.1
-supports_streaming = true
-supports_thinking = true

providers/upstage.toml

@@ -1,18 +0,0 @@
-# upstage — auto-generated from OpenRouter API
-
-[provider]
-id = "upstage"
-display_name = "Upstage"
-api_key_env = "UPSTAGE_API_KEY"
-base_url = "https://api.upstage.ai/v1"
-key_required = true
-
-[[models]]
-id = "solar-pro-3"
-display_name = "Upstage: Solar Pro 3"
-tier = "fast"
-context_window = 128000
-max_output_tokens = 16384
-input_cost_per_m = 0.15
-output_cost_per_m = 0.6
-supports_streaming = true

providers/writer.toml

@@ -1,61 +0,0 @@
-# Writer — https://writer.com
-# Models: 4
-
-[provider]
-id = "writer"
-display_name = "Writer"
-api_key_env = "WRITER_API_KEY"
-base_url = "https://api.writer.com/v1"
-key_required = true
-
-[[models]]
-id = "palmyra-x5"
-display_name = "Palmyra X5"
-tier = "frontier"
-context_window = 1048576
-max_output_tokens = 8192
-input_cost_per_m = 0.60
-output_cost_per_m = 6.00
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = ["palmyra-x5", "writer-x5"]
-
-[[models]]
-id = "palmyra-x4"
-display_name = "Palmyra X4"
-tier = "smart"
-context_window = 131072
-max_output_tokens = 4096
-input_cost_per_m = 2.50
-output_cost_per_m = 10.00
-supports_tools = true
-supports_vision = false
-supports_streaming = true
-aliases = ["palmyra-x4", "writer-x4"]
-
-[[models]]
-id = "palmyra-med"
-display_name = "Palmyra Med"
-tier = "smart"
-context_window = 32768
-max_output_tokens = 4096
-input_cost_per_m = 5.00
-output_cost_per_m = 12.00
-supports_tools = false
-supports_vision = false
-supports_streaming = true
-aliases = ["palmyra-med", "writer-med"]
-
-[[models]]
-id = "palmyra-fin"
-display_name = "Palmyra Fin"
-tier = "smart"
-context_window = 131072
-max_output_tokens = 4096
-input_cost_per_m = 5.00
-output_cost_per_m = 12.00
-supports_tools = false
-supports_vision = false
-supports_streaming = true
-aliases = ["palmyra-fin", "writer-fin"]

providers/xai.toml

@@ -1,5 +1,5 @@
 # xAI — https://x.ai
-# Models: 9
+# Models: 7
 
 [provider]
 id = "xai"
@@ -100,29 +100,3 @@ supports_tools = true
 supports_vision = false
 supports_streaming = true
 aliases = []
-
-[[models]]
-id = "grok-2"
-display_name = "Grok 2"
-tier = "smart"
-context_window = 131072
-max_output_tokens = 32768
-input_cost_per_m = 2.0
-output_cost_per_m = 10.0
-supports_tools = true
-supports_vision = true
-supports_streaming = true
-aliases = []
-
-[[models]]
-id = "grok-2-mini"
-display_name = "Grok 2 Mini"
-tier = "fast"
-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 = ["grok-mini"]