Evan
2fa48bfdcb
- Merge unique models from duplicate providers into their hand-written counterparts and remove the duplicates: - alibaba (tongyi-deepresearch) → qwen - amazon (nova-2-lite, nova-micro, nova-premier) → bedrock - bytedance (ui-tars) → volcengine - nvidia (nemotron-3-nano, nemotron-3-super, etc.) → nvidia-nim - rekaai (reka-flash-3) → reka - Set correct official API base_url for providers with public APIs: arcee-ai, inception, morph, reka, upstage - Set key_required=false for 20 providers only accessible through hosting platforms (no public API) - Update sync-pricing.py with SKIP_DUPLICATES, PROVIDER_API mapping, and default key_required=false for future auto-generated providers
170 lines
3.6 KiB
TOML
170 lines
3.6 KiB
TOML
# Qwen / Alibaba — https://dashscope.aliyuncs.com
|
|
# Models: 11
|
|
# 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-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"
|
|
tier = "smart"
|
|
context_window = 32768
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.1365
|
|
output_cost_per_m = 0.40950000000000003
|
|
supports_tools = false
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "qwen-coder-plus"
|
|
display_name = "Qwen Coder Plus"
|
|
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 = []
|
|
|
|
[[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
|
|
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
|
|
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"
|
|
tier = "fast"
|
|
context_window = 131072
|
|
max_output_tokens = 131072
|
|
input_cost_per_m = 0.09
|
|
output_cost_per_m = 0.45
|
|
supports_streaming = true
|