# Chutes.ai — https://chutes.ai
# Models: 5

[provider]
id = "chutes"
display_name = "Chutes.ai"
api_key_env = "CHUTES_API_KEY"
base_url = "https://llm.chutes.ai/v1"
key_required = true

[[models]]
id = "chutes/deepseek-ai/DeepSeek-V3"
display_name = "DeepSeek V3 (Chutes)"
tier = "smart"
context_window = 128000
max_output_tokens = 8192
input_cost_per_m = 0.25
output_cost_per_m = 0.35
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = ["chutes-deepseek-v3"]

[[models]]
id = "chutes/deepseek-ai/DeepSeek-R1"
display_name = "DeepSeek R1 (Chutes)"
tier = "smart"
context_window = 128000
max_output_tokens = 8192
input_cost_per_m = 0.55
output_cost_per_m = 2.19
supports_tools = false
supports_vision = false
supports_streaming = true
aliases = ["chutes-deepseek-r1"]

[[models]]
id = "chutes/meta-llama/Llama-4-Maverick-17B-128E-Instruct"
display_name = "Llama 4 Maverick (Chutes)"
tier = "balanced"
context_window = 128000
max_output_tokens = 8192
input_cost_per_m = 0.20
output_cost_per_m = 0.30
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = ["chutes-llama-maverick"]

[[models]]
id = "chutes/Qwen/Qwen3-235B-A22B"
display_name = "Qwen3 235B (Chutes)"
tier = "smart"
context_window = 128000
max_output_tokens = 8192
input_cost_per_m = 0.25
output_cost_per_m = 0.35
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = ["chutes-qwen3"]

[[models]]
id = "chutes/meta-llama/Llama-3.3-70B-Instruct"
display_name = "Llama 3.3 70B (Chutes)"
tier = "balanced"
context_window = 128000
max_output_tokens = 8192
input_cost_per_m = 0.10
output_cost_per_m = 0.15
supports_tools = true
supports_vision = false
supports_streaming = true
aliases = ["chutes-llama-70b"]