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
115 lines
2.5 KiB
TOML
115 lines
2.5 KiB
TOML
# Together AI — https://together.ai
|
|
# Models: 8
|
|
|
|
[provider]
|
|
id = "together"
|
|
display_name = "Together AI"
|
|
api_key_env = "TOGETHER_API_KEY"
|
|
base_url = "https://api.together.xyz/v1"
|
|
key_required = true
|
|
|
|
[[models]]
|
|
id = "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo"
|
|
display_name = "Llama 3.1 405B (Together)"
|
|
tier = "frontier"
|
|
context_window = 130000
|
|
max_output_tokens = 4096
|
|
input_cost_per_m = 3.50
|
|
output_cost_per_m = 3.50
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "meta-llama/Llama-3.3-70B-Instruct-Turbo"
|
|
display_name = "Llama 3.3 70B (Together)"
|
|
tier = "smart"
|
|
context_window = 128000
|
|
max_output_tokens = 4096
|
|
input_cost_per_m = 0.88
|
|
output_cost_per_m = 0.88
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"
|
|
display_name = "Llama 4 Maverick (Together)"
|
|
tier = "smart"
|
|
context_window = 1048576
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.27
|
|
output_cost_per_m = 0.35
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "meta-llama/Llama-4-Scout-17B-16E-Instruct"
|
|
display_name = "Llama 4 Scout (Together)"
|
|
tier = "balanced"
|
|
context_window = 512000
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.18
|
|
output_cost_per_m = 0.30
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "deepseek-ai/DeepSeek-R1"
|
|
display_name = "DeepSeek R1 (Together)"
|
|
tier = "frontier"
|
|
context_window = 64000
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 3.00
|
|
output_cost_per_m = 7.00
|
|
supports_tools = false
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
supports_thinking = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "deepseek-ai/DeepSeek-V3"
|
|
display_name = "DeepSeek V3 (Together)"
|
|
tier = "smart"
|
|
context_window = 64000
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.90
|
|
output_cost_per_m = 0.90
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "Qwen/Qwen2.5-72B-Instruct-Turbo"
|
|
display_name = "Qwen 2.5 72B (Together)"
|
|
tier = "smart"
|
|
context_window = 32768
|
|
max_output_tokens = 4096
|
|
input_cost_per_m = 0.20
|
|
output_cost_per_m = 0.60
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "mistralai/Mixtral-8x22B-Instruct-v0.1"
|
|
display_name = "Mixtral 8x22B (Together)"
|
|
tier = "balanced"
|
|
context_window = 65536
|
|
max_output_tokens = 4096
|
|
input_cost_per_m = 0.60
|
|
output_cost_per_m = 0.60
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|