Evan
85db9c8d78
* feat(providers): add supports_thinking field to thinking-capable models Mark models that support extended thinking / reasoning with supports_thinking = true so the dashboard can conditionally show thinking toggles. Providers updated: anthropic (8), codex-cli (7), gemini (6), openai (3), qwen (2), deepseek (1). Schema updated accordingly. * feat(providers): add supports_thinking to remaining thinking-capable models Cover 19 additional providers: alibaba-coding-plan, allenai, arcee-ai, fireworks, gemini-cli, groq, liquid, nvidia-nim, ollama, openai (codex), openrouter, perplexity, qwen-code, replicate, sambanova, tngtech, venice, vertex-ai, xai. Total: 62 models across 24 providers now have supports_thinking = true. * feat(providers): add supports_thinking to chutes, huggingface, together Missed in prior commits: DeepSeek-R1 on chutes/huggingface/together, Qwen3-235B on chutes. Total now 66 models across 27 providers. * feat(providers): add supports_thinking to bedrock, claude-code, aider, moonshot, stepfun - bedrock: all 5 Claude models - claude-code: all 3 models (opus/sonnet/haiku wrappers) - aider: aider/sonnet (Claude-backed) - moonshot: kimi-k2.5 (reasoning mode) - stepfun: step-1o-turbo-vision (reasoning model) Total: 77 models across 32 providers. * feat(providers): add supports_thinking to alibaba kimi-k2.5, openrouter claude-sonnet-4
141 lines
2.9 KiB
TOML
141 lines
2.9 KiB
TOML
# Groq — https://groq.com
|
|
# Models: 10
|
|
|
|
[provider]
|
|
id = "groq"
|
|
display_name = "Groq"
|
|
api_key_env = "GROQ_API_KEY"
|
|
base_url = "https://api.groq.com/openai/v1"
|
|
key_required = true
|
|
|
|
[[models]]
|
|
id = "llama-3.3-70b-versatile"
|
|
display_name = "Llama 3.3 70B"
|
|
tier = "balanced"
|
|
context_window = 128000
|
|
max_output_tokens = 32768
|
|
input_cost_per_m = 0.059
|
|
output_cost_per_m = 0.079
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = ["llama", "llama-70b"]
|
|
|
|
[[models]]
|
|
id = "llama-3.1-8b-instant"
|
|
display_name = "Llama 3.1 8B"
|
|
tier = "fast"
|
|
context_window = 128000
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.05
|
|
output_cost_per_m = 0.08
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "llama-3.2-90b-vision-preview"
|
|
display_name = "Llama 3.2 90B Vision"
|
|
tier = "smart"
|
|
context_window = 128000
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.90
|
|
output_cost_per_m = 0.90
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "llama-3.2-11b-vision-preview"
|
|
display_name = "Llama 3.2 11B Vision"
|
|
tier = "balanced"
|
|
context_window = 128000
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.18
|
|
output_cost_per_m = 0.18
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "llama-3.2-3b-preview"
|
|
display_name = "Llama 3.2 3B"
|
|
tier = "fast"
|
|
context_window = 128000
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.06
|
|
output_cost_per_m = 0.06
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "llama-3.2-1b-preview"
|
|
display_name = "Llama 3.2 1B"
|
|
tier = "fast"
|
|
context_window = 128000
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.04
|
|
output_cost_per_m = 0.04
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "mixtral-8x7b-32768"
|
|
display_name = "Mixtral 8x7B"
|
|
tier = "balanced"
|
|
context_window = 32768
|
|
max_output_tokens = 4096
|
|
input_cost_per_m = 0.024
|
|
output_cost_per_m = 0.024
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = ["mixtral"]
|
|
|
|
[[models]]
|
|
id = "gemma2-9b-it"
|
|
display_name = "Gemma 2 9B"
|
|
tier = "fast"
|
|
context_window = 8192
|
|
max_output_tokens = 4096
|
|
input_cost_per_m = 0.02
|
|
output_cost_per_m = 0.02
|
|
supports_tools = false
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "qwen-qwq-32b"
|
|
display_name = "Qwen QWQ 32B"
|
|
tier = "balanced"
|
|
context_window = 128000
|
|
max_output_tokens = 16384
|
|
input_cost_per_m = 0.20
|
|
output_cost_per_m = 0.20
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
supports_thinking = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "meta-llama/llama-4-scout-17b-16e-instruct"
|
|
display_name = "Llama 4 Scout 17B"
|
|
tier = "balanced"
|
|
context_window = 128000
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.11
|
|
output_cost_per_m = 0.34
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = []
|