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
94 lines
2.1 KiB
TOML
94 lines
2.1 KiB
TOML
[provider]
|
|
id = "vertex-ai"
|
|
display_name = "Google Cloud Vertex AI"
|
|
# Points to a service-account JSON file path, not a raw API key.
|
|
api_key_env = "GOOGLE_APPLICATION_CREDENTIALS"
|
|
base_url = "https://us-central1-aiplatform.googleapis.com"
|
|
key_required = true
|
|
|
|
[[models]]
|
|
id = "vertex-ai/gemini-2.5-pro"
|
|
display_name = "Gemini 2.5 Pro (Vertex AI)"
|
|
provider = "vertex-ai"
|
|
tier = "frontier"
|
|
context_window = 1048576
|
|
max_output_tokens = 65536
|
|
input_cost_per_m = 1.25
|
|
output_cost_per_m = 10.0
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
supports_thinking = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "vertex-ai/gemini-2.5-flash"
|
|
display_name = "Gemini 2.5 Flash (Vertex AI)"
|
|
provider = "vertex-ai"
|
|
tier = "smart"
|
|
context_window = 1048576
|
|
max_output_tokens = 65536
|
|
input_cost_per_m = 0.15
|
|
output_cost_per_m = 0.6
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
supports_thinking = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "vertex-ai/gemini-2.0-flash"
|
|
display_name = "Gemini 2.0 Flash (Vertex AI)"
|
|
provider = "vertex-ai"
|
|
tier = "fast"
|
|
context_window = 1048576
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.1
|
|
output_cost_per_m = 0.4
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "vertex-ai/gemini-2.0-flash-lite"
|
|
display_name = "Gemini 2.0 Flash Lite (Vertex AI)"
|
|
provider = "vertex-ai"
|
|
tier = "fast"
|
|
context_window = 1048576
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.075
|
|
output_cost_per_m = 0.3
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "vertex-ai/gemini-1.5-pro"
|
|
display_name = "Gemini 1.5 Pro (Vertex AI)"
|
|
provider = "vertex-ai"
|
|
tier = "smart"
|
|
context_window = 2097152
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 1.25
|
|
output_cost_per_m = 5.0
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "vertex-ai/gemini-1.5-flash"
|
|
display_name = "Gemini 1.5 Flash (Vertex AI)"
|
|
provider = "vertex-ai"
|
|
tier = "fast"
|
|
context_window = 1048576
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.075
|
|
output_cost_per_m = 0.3
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = []
|