Evan
12d19943c5
OpenAI-compatible LLM gateway. Pairs with the librefang-llm-drivers registration (librefang PR #3076) so Novita models surface in the dashboard model picker without each user having to add them via /api/models/custom. Pricing and limits sourced from GET /openai/v1/models on 2026-04-25 (input_token_price_per_m / output_token_price_per_m, divided by 10000 to get USD per million tokens). Curated to a small popular subset: - deepseek/deepseek-v3.2 (frontier) - moonshotai/kimi-k2-thinking (frontier, supports_thinking) - minimax/minimax-m2 (smart) - meta-llama/llama-3.3-70b-instruct (smart) - qwen/qwen3-coder-30b-a3b-instruct (balanced) - zai-org/glm-4.7-flash (balanced)
92 lines
2.1 KiB
TOML
92 lines
2.1 KiB
TOML
# Novita AI — https://novita.ai
|
|
# OpenAI-compatible LLM gateway. Endpoint: https://api.novita.ai/openai/v1
|
|
# Pricing reflects values returned by GET /openai/v1/models on 2026-04-25
|
|
# (input_token_price_per_m / output_token_price_per_m, scaled /10000 to USD).
|
|
# Models: 6
|
|
|
|
[provider]
|
|
id = "novita"
|
|
display_name = "Novita AI"
|
|
api_key_env = "NOVITA_API_KEY"
|
|
base_url = "https://api.novita.ai/openai/v1"
|
|
key_required = true
|
|
|
|
[[models]]
|
|
id = "deepseek/deepseek-v3.2"
|
|
display_name = "DeepSeek V3.2 (Novita)"
|
|
tier = "frontier"
|
|
context_window = 163840
|
|
max_output_tokens = 65536
|
|
input_cost_per_m = 0.269
|
|
output_cost_per_m = 0.40
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "moonshotai/kimi-k2-thinking"
|
|
display_name = "Kimi K2 Thinking (Novita)"
|
|
tier = "frontier"
|
|
context_window = 262144
|
|
max_output_tokens = 262144
|
|
input_cost_per_m = 0.60
|
|
output_cost_per_m = 2.50
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
supports_thinking = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "minimax/minimax-m2"
|
|
display_name = "MiniMax M2 (Novita)"
|
|
tier = "smart"
|
|
context_window = 204800
|
|
max_output_tokens = 131072
|
|
input_cost_per_m = 0.30
|
|
output_cost_per_m = 1.20
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "meta-llama/llama-3.3-70b-instruct"
|
|
display_name = "Llama 3.3 70B (Novita)"
|
|
tier = "smart"
|
|
context_window = 131072
|
|
max_output_tokens = 120000
|
|
input_cost_per_m = 0.135
|
|
output_cost_per_m = 0.40
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "qwen/qwen3-coder-30b-a3b-instruct"
|
|
display_name = "Qwen3 Coder 30B (Novita)"
|
|
tier = "balanced"
|
|
context_window = 160000
|
|
max_output_tokens = 32768
|
|
input_cost_per_m = 0.07
|
|
output_cost_per_m = 0.27
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "zai-org/glm-4.7-flash"
|
|
display_name = "GLM 4.7 Flash (Novita)"
|
|
tier = "balanced"
|
|
context_window = 200000
|
|
max_output_tokens = 128000
|
|
input_cost_per_m = 0.07
|
|
output_cost_per_m = 0.40
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|