Evan
82d5a6ecd5
Extend modality enum to support video and music, then register the non-text MiniMax models that were already declared in media_capabilities but had no concrete entries: - image-01 ($0.0035/image) - speech-2.8/2.6 hd & turbo ($60-$100 per 1M chars) - Hailuo 2.3 Fast / 2.3 / 02 video models ($0.10-$0.56 per video) - music-2.6, lyrics_generation Per-call pricing is documented in inline comments since the schema's token-based cost fields don't naturally fit per-call billing. schema.toml and scripts/validate.py both updated; the change is additive (existing modality values remain valid).
216 lines
4.9 KiB
TOML
216 lines
4.9 KiB
TOML
# MiniMax — https://minimax.io
|
|
# Models: 14 (4 text + 1 image + 4 audio TTS + 3 video + 2 music)
|
|
# Regions: international (default), china (minimaxi.com)
|
|
#
|
|
# Non-text models are billed per call rather than per token, so
|
|
# input_cost_per_m / output_cost_per_m are set to 0.0 and the actual
|
|
# rate is documented in the inline comment above each entry.
|
|
# Source: https://platform.minimax.io/docs/guides/pricing-paygo
|
|
|
|
[provider]
|
|
id = "minimax"
|
|
display_name = "MiniMax"
|
|
api_key_env = "MINIMAX_API_KEY"
|
|
base_url = "https://api.minimax.io/v1"
|
|
key_required = true
|
|
media_capabilities = [
|
|
"image_generation",
|
|
"text_to_speech",
|
|
"video_generation",
|
|
"music_generation",
|
|
]
|
|
|
|
[provider.regions.china]
|
|
base_url = "https://api.minimaxi.com/v1"
|
|
api_key_env = "MINIMAX_CN_API_KEY"
|
|
|
|
[[models]]
|
|
id = "MiniMax-M2.7"
|
|
display_name = "MiniMax M2.7"
|
|
tier = "frontier"
|
|
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 = ["minimax-m2.7"]
|
|
|
|
[[models]]
|
|
id = "MiniMax-M2.7-highspeed"
|
|
display_name = "MiniMax M2.7 Highspeed"
|
|
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 = ["minimax-m2.7-highspeed", "m2.7-highspeed"]
|
|
|
|
[[models]]
|
|
id = "MiniMax-M2.5"
|
|
display_name = "MiniMax M2.5"
|
|
tier = "frontier"
|
|
context_window = 1048576
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 1.10
|
|
output_cost_per_m = 4.40
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = ["minimax-m2.5"]
|
|
|
|
[[models]]
|
|
id = "MiniMax-M2.5-highspeed"
|
|
display_name = "MiniMax M2.5 Highspeed"
|
|
tier = "smart"
|
|
context_window = 1048576
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.80
|
|
output_cost_per_m = 3.20
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = ["minimax-m2.5-highspeed", "m2.5-highspeed"]
|
|
|
|
# --- Image generation ---
|
|
|
|
# $0.0035 per image
|
|
[[models]]
|
|
id = "image-01"
|
|
display_name = "MiniMax Image 01"
|
|
tier = "smart"
|
|
modality = "image"
|
|
input_cost_per_m = 0.0
|
|
output_cost_per_m = 0.0
|
|
supports_tools = false
|
|
supports_vision = false
|
|
supports_streaming = false
|
|
aliases = ["minimax-image"]
|
|
|
|
# --- Text-to-speech ---
|
|
|
|
# $100 per 1M characters
|
|
[[models]]
|
|
id = "speech-2.8-hd"
|
|
display_name = "MiniMax Speech 2.8 HD"
|
|
tier = "frontier"
|
|
modality = "audio"
|
|
input_cost_per_m = 100.0
|
|
output_cost_per_m = 0.0
|
|
supports_tools = false
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = ["minimax-tts-hd", "speech-hd"]
|
|
|
|
# $60 per 1M characters
|
|
[[models]]
|
|
id = "speech-2.8-turbo"
|
|
display_name = "MiniMax Speech 2.8 Turbo"
|
|
tier = "fast"
|
|
modality = "audio"
|
|
input_cost_per_m = 60.0
|
|
output_cost_per_m = 0.0
|
|
supports_tools = false
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = ["minimax-tts-turbo", "speech-turbo"]
|
|
|
|
# $100 per 1M characters
|
|
[[models]]
|
|
id = "speech-2.6-hd"
|
|
display_name = "MiniMax Speech 2.6 HD"
|
|
tier = "smart"
|
|
modality = "audio"
|
|
input_cost_per_m = 100.0
|
|
output_cost_per_m = 0.0
|
|
supports_tools = false
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
# $60 per 1M characters
|
|
[[models]]
|
|
id = "speech-2.6-turbo"
|
|
display_name = "MiniMax Speech 2.6 Turbo"
|
|
tier = "fast"
|
|
modality = "audio"
|
|
input_cost_per_m = 60.0
|
|
output_cost_per_m = 0.0
|
|
supports_tools = false
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
# --- Video generation (Hailuo) ---
|
|
|
|
# Per-call: $0.19 (768P/6s) up to $0.33 (1080P/6s)
|
|
[[models]]
|
|
id = "MiniMax-Hailuo-2.3-Fast"
|
|
display_name = "Hailuo 2.3 Fast"
|
|
tier = "fast"
|
|
modality = "video"
|
|
input_cost_per_m = 0.0
|
|
output_cost_per_m = 0.0
|
|
supports_tools = false
|
|
supports_vision = false
|
|
supports_streaming = false
|
|
aliases = ["hailuo-2.3-fast", "hailuo-fast"]
|
|
|
|
# Per-call: $0.28 (768P/6s) up to $0.56 (1080P/6s)
|
|
[[models]]
|
|
id = "MiniMax-Hailuo-2.3"
|
|
display_name = "Hailuo 2.3"
|
|
tier = "frontier"
|
|
modality = "video"
|
|
input_cost_per_m = 0.0
|
|
output_cost_per_m = 0.0
|
|
supports_tools = false
|
|
supports_vision = false
|
|
supports_streaming = false
|
|
aliases = ["hailuo-2.3", "hailuo"]
|
|
|
|
# Per-call: $0.10 (512P/6s) up to $0.56 (1080P/6s)
|
|
[[models]]
|
|
id = "MiniMax-Hailuo-02"
|
|
display_name = "Hailuo 02"
|
|
tier = "smart"
|
|
modality = "video"
|
|
input_cost_per_m = 0.0
|
|
output_cost_per_m = 0.0
|
|
supports_tools = false
|
|
supports_vision = false
|
|
supports_streaming = false
|
|
aliases = ["hailuo-02"]
|
|
|
|
# --- Music generation ---
|
|
|
|
# $0.15 per up-to-5-minute track
|
|
[[models]]
|
|
id = "music-2.6"
|
|
display_name = "MiniMax Music 2.6"
|
|
tier = "frontier"
|
|
modality = "music"
|
|
input_cost_per_m = 0.0
|
|
output_cost_per_m = 0.0
|
|
supports_tools = false
|
|
supports_vision = false
|
|
supports_streaming = false
|
|
aliases = ["minimax-music"]
|
|
|
|
# $0.01 per song
|
|
[[models]]
|
|
id = "lyrics_generation"
|
|
display_name = "MiniMax Lyrics Generation"
|
|
tier = "fast"
|
|
modality = "music"
|
|
input_cost_per_m = 0.0
|
|
output_cost_per_m = 0.0
|
|
supports_tools = false
|
|
supports_vision = false
|
|
supports_streaming = false
|
|
aliases = ["minimax-lyrics"]
|