Evan
553ecc6947
* fix: pin npm package versions in MCP integration templates Prevent supply chain attacks by pinning exact versions instead of using unpinned `npx -y @package` which pulls latest on every run. 23 of 25 integrations pinned. sqlite-mcp and aws skipped (packages not found on npm registry). * fix: use stable azure/mcp version instead of beta * feat: add pricing sync script and update model prices from OpenRouter API - scripts/sync-pricing.py fetches real-time pricing from OpenRouter - Updated 64 price fields across 13 provider files - Run periodically or in CI to keep prices current
119 lines
2.7 KiB
TOML
119 lines
2.7 KiB
TOML
# nvidia — auto-generated from OpenRouter API
|
|
|
|
[provider]
|
|
id = "nvidia"
|
|
display_name = "Nvidia"
|
|
api_key_env = "NVIDIA_API_KEY"
|
|
base_url = ""
|
|
key_required = true
|
|
|
|
[[models]]
|
|
id = "llama-3.1-nemotron-70b-instruct"
|
|
display_name = "NVIDIA: Llama 3.1 Nemotron 70B Instruct"
|
|
tier = "smart"
|
|
context_window = 131072
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 1.2
|
|
output_cost_per_m = 1.2
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "llama-3.1-nemotron-ultra-253b-v1"
|
|
display_name = "NVIDIA: Llama 3.1 Nemotron Ultra 253B v1"
|
|
tier = "smart"
|
|
context_window = 131072
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.6
|
|
output_cost_per_m = 1.8
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "llama-3.3-nemotron-super-49b-v1.5"
|
|
display_name = "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5"
|
|
tier = "fast"
|
|
context_window = 131072
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.1
|
|
output_cost_per_m = 0.4
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "nemotron-3-nano-30b-a3b"
|
|
display_name = "NVIDIA: Nemotron 3 Nano 30B A3B"
|
|
tier = "fast"
|
|
context_window = 262144
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.05
|
|
output_cost_per_m = 0.2
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "nemotron-3-nano-30b-a3b:free"
|
|
display_name = "NVIDIA: Nemotron 3 Nano 30B A3B (free)"
|
|
tier = "free"
|
|
context_window = 256000
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.0
|
|
output_cost_per_m = 0.0
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "nemotron-3-super-120b-a12b"
|
|
display_name = "NVIDIA: Nemotron 3 Super"
|
|
tier = "fast"
|
|
context_window = 262144
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.1
|
|
output_cost_per_m = 0.5
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "nemotron-3-super-120b-a12b:free"
|
|
display_name = "NVIDIA: Nemotron 3 Super (free)"
|
|
tier = "free"
|
|
context_window = 262144
|
|
max_output_tokens = 262144
|
|
input_cost_per_m = 0.0
|
|
output_cost_per_m = 0.0
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "nemotron-nano-12b-v2-vl"
|
|
display_name = "NVIDIA: Nemotron Nano 12B 2 VL"
|
|
tier = "fast"
|
|
context_window = 131072
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.2
|
|
output_cost_per_m = 0.6
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "nemotron-nano-12b-v2-vl:free"
|
|
display_name = "NVIDIA: Nemotron Nano 12B 2 VL (free)"
|
|
tier = "free"
|
|
context_window = 128000
|
|
max_output_tokens = 128000
|
|
input_cost_per_m = 0.0
|
|
output_cost_per_m = 0.0
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "nemotron-nano-9b-v2"
|
|
display_name = "NVIDIA: Nemotron Nano 9B V2"
|
|
tier = "fast"
|
|
context_window = 131072
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.04
|
|
output_cost_per_m = 0.16
|
|
supports_streaming = true
|
|
|
|
[[models]]
|
|
id = "nemotron-nano-9b-v2:free"
|
|
display_name = "NVIDIA: Nemotron Nano 9B V2 (free)"
|
|
tier = "free"
|
|
context_window = 128000
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.0
|
|
output_cost_per_m = 0.0
|
|
supports_streaming = true
|