Evan
4f8dd2404d
* 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writer Clean up 10 major providers — keep only latest generation models: - anthropic: remove claude-3.5-sonnet (superseded by 4.x) - openai: remove gpt-4o/4-turbo/3.5/o1/o3-mini (superseded by gpt-5/4.1/o3/o4-mini) - gemini: remove 1.5-*/2.0-flash (superseded by 2.5/3.x) - deepseek: remove coder/chat-v3-0324 (superseded by r1/v3) - qwen: remove turbo/2.5-coder (superseded by qwen3) - groq: remove old llama/mixtral/gemma (keep latest only) - mistral: remove medium/nemo/pixtral-large (keep large/small/codestral) - xai: remove grok-2 (superseded by grok-3/4) - meta-llama: remove 3.x/guard (keep llama-4 + 3.3) - ollama: rewrite with current models (gemma4, qwen3, qwq, llama4, etc) Total: 90 → 48 models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
133 lines
2.8 KiB
TOML
133 lines
2.8 KiB
TOML
# Qwen / Alibaba — https://dashscope.aliyuncs.com
|
|
# Models: 9
|
|
# Regions: china (default), intl (Singapore), us (Virginia)
|
|
|
|
[provider]
|
|
id = "qwen"
|
|
display_name = "Qwen (Alibaba)"
|
|
api_key_env = "DASHSCOPE_API_KEY"
|
|
base_url = "https://dashscope.aliyuncs.com/compatible-mode/v1"
|
|
key_required = true
|
|
|
|
[provider.regions.intl]
|
|
base_url = "https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
|
|
|
|
[provider.regions.us]
|
|
base_url = "https://dashscope-us.aliyuncs.com/compatible-mode/v1"
|
|
|
|
[[models]]
|
|
id = "qwen-max"
|
|
display_name = "Qwen Max"
|
|
tier = "frontier"
|
|
context_window = 32768
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 1.04
|
|
output_cost_per_m = 4.16
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "qwen-plus"
|
|
display_name = "Qwen Plus"
|
|
tier = "smart"
|
|
context_window = 131072
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.26
|
|
output_cost_per_m = 0.78
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = ["qwen"]
|
|
|
|
[[models]]
|
|
id = "qwen-vl-plus"
|
|
display_name = "Qwen VL Plus"
|
|
tier = "smart"
|
|
context_window = 32768
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.1365
|
|
output_cost_per_m = 0.4095
|
|
supports_tools = false
|
|
supports_vision = true
|
|
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 = "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 = "qwen-long"
|
|
display_name = "Qwen Long"
|
|
tier = "balanced"
|
|
context_window = 1000000
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.50
|
|
output_cost_per_m = 2.00
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "qwen3-235b-a22b"
|
|
display_name = "Qwen3 235B"
|
|
tier = "frontier"
|
|
context_window = 131072
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.455
|
|
output_cost_per_m = 1.82
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
supports_thinking = true
|
|
aliases = ["qwen3"]
|
|
|
|
[[models]]
|
|
id = "qwen3-30b-a3b"
|
|
display_name = "Qwen3 30B"
|
|
tier = "fast"
|
|
context_window = 131072
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.08
|
|
output_cost_per_m = 0.28
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
supports_thinking = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "tongyi-deepresearch-30b-a3b"
|
|
display_name = "Tongyi DeepResearch 30B A3B"
|
|
tier = "fast"
|
|
context_window = 131072
|
|
max_output_tokens = 131072
|
|
input_cost_per_m = 0.09
|
|
output_cost_per_m = 0.45
|
|
supports_streaming = true
|