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
49 lines
1.0 KiB
TOML
49 lines
1.0 KiB
TOML
# allenai — auto-generated from OpenRouter API
|
|
|
|
[provider]
|
|
id = "allenai"
|
|
display_name = "Allenai"
|
|
api_key_env = "ALLENAI_API_KEY"
|
|
base_url = ""
|
|
key_required = false
|
|
|
|
[[models]]
|
|
id = "olmo-2-0325-32b-instruct"
|
|
display_name = "AllenAI: Olmo 2 32B Instruct"
|
|
tier = "fast"
|
|
context_window = 128000
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.05
|
|
output_cost_per_m = 0.2
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "olmo-3-32b-think"
|
|
display_name = "AllenAI: Olmo 3 32B Think"
|
|
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 = "olmo-3.1-32b-instruct"
|
|
display_name = "AllenAI: Olmo 3.1 32B Instruct"
|
|
tier = "fast"
|
|
context_window = 65536
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.2
|
|
output_cost_per_m = 0.6
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "olmo-3.1-32b-think"
|
|
display_name = "AllenAI: Olmo 3.1 32B Think"
|
|
tier = "fast"
|
|
context_window = 65536
|
|
max_output_tokens = 65536
|
|
input_cost_per_m = 0.15
|
|
output_cost_per_m = 0.5
|
|
supports_streaming = true
|