Evan
541052dc79
* chore: prune deprecated models across providers Remove old-generation models that are strictly superseded by current versions on the same provider/family. Affected providers: anthropic, bedrock, vertex-ai, xai, moonshot, zhipu, baichuan, stepfun, volcengine, minimax, cohere, together, fireworks, deepinfra, openrouter. Also clean up orphan aliases (grok3, grok-mini, minimax-m2.1) and remap moonshot alias to kimi-k2.5. Net: -42 model entries across 18 files. Provider model counts and README rows updated accordingly. * chore: remove redundant and orphan aliases from aliases.toml Provider TOML files auto-register their model.aliases at load time, so re-declaring them globally is duplication. Also drop entries pointing to models that no longer exist after the prune. - 45 redundant entries duplicating provider-defined aliases - 11 orphan targets (gpt-4o, gpt-4o-mini, grok-2-mini, grok-3, mixtral-8x7b-32768, copilot/gpt-4, open-mistral-nemo, pixtral-large-latest, jamba-1.5-large, palmyra-x5, venice-uncensored) Net: 100 lines down to 21. The file is now what the header comment always claimed it was: 'additional global aliases not tied to a specific model entry.' * chore: second pass — prune more deprecated models Apply the same 'strictly superseded by same-provider/family successor' rule to providers missed in the first pass: - openai: gpt-4.1 / -mini / -nano, o3, o4-mini (5) - meta-llama: llama-3.3-70b-instruct (1) - zhipu: glm-4v-plus (1) - together: Llama-3.3-70B-Instruct-Turbo (1) - xiaomi: mimo-v2-flash / -omni / -pro (3) - aion-labs: aion-1.0 / -mini (2) - qianfan: ernie-speed-128k, ernie-4.0-turbo-8k (2) - cerebras: cerebras/llama3.1-8b (1) - qwen-code: qwen-code/qwq-32b (1) - nvidia-nim: 12 models (llama-3.1/3.2 series, mixtral-8x22b, mistral-small-3.1, phi-4-mini, qwq-32b, r1-distill-32b, qwen2.5-coder, nemotron-mini-4b, nemotron-70b-instruct) - openrouter: meta-llama/llama-3.3-70b (paid), rekaai/reka-edge (2) - alibaba-coding-plan: qwen3.5-plus, qwen3-max-2026-01-23, MiniMax-M2.5, kimi-k2.5 (4) Net: -35 model entries. providers/README.md model counts updated. 220 models remain.
72 lines
1.7 KiB
TOML
72 lines
1.7 KiB
TOML
# Volcano Engine / Doubao — https://volcengine.com
|
|
# Models: 5
|
|
|
|
[provider]
|
|
id = "volcengine"
|
|
display_name = "Volcano Engine (Doubao)"
|
|
api_key_env = "VOLCENGINE_API_KEY"
|
|
base_url = "https://ark.cn-beijing.volces.com/api/v3"
|
|
key_required = true
|
|
|
|
[[models]]
|
|
id = "doubao-seed-2-0-pro-260215"
|
|
display_name = "Doubao Seed 2.0 Pro"
|
|
tier = "frontier"
|
|
context_window = 262144
|
|
max_output_tokens = 131072
|
|
input_cost_per_m = 0.47
|
|
output_cost_per_m = 2.37
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = ["doubao-pro", "doubao-seed-pro", "doubao-2-pro"]
|
|
|
|
[[models]]
|
|
id = "doubao-seed-2-0-lite-260215"
|
|
display_name = "Doubao Seed 2.0 Lite"
|
|
tier = "smart"
|
|
context_window = 262144
|
|
max_output_tokens = 131072
|
|
input_cost_per_m = 0.09
|
|
output_cost_per_m = 0.53
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = ["doubao-lite", "doubao-seed-lite", "doubao-2-lite"]
|
|
|
|
[[models]]
|
|
id = "doubao-seed-2-0-mini-260215"
|
|
display_name = "Doubao Seed 2.0 Mini"
|
|
tier = "fast"
|
|
context_window = 262144
|
|
max_output_tokens = 131072
|
|
input_cost_per_m = 0.03
|
|
output_cost_per_m = 0.31
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = ["doubao-mini", "doubao-seed-mini", "doubao-2-mini"]
|
|
|
|
[[models]]
|
|
id = "doubao-seed-2-0-code"
|
|
display_name = "Doubao Seed 2.0 Code"
|
|
tier = "smart"
|
|
context_window = 262144
|
|
max_output_tokens = 131072
|
|
input_cost_per_m = 0.47
|
|
output_cost_per_m = 2.37
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = ["doubao-code", "doubao-seed-code"]
|
|
|
|
[[models]]
|
|
id = "ui-tars-1.5-7b"
|
|
display_name = "ByteDance: UI-TARS 7B"
|
|
tier = "fast"
|
|
context_window = 128000
|
|
max_output_tokens = 2048
|
|
input_cost_per_m = 0.1
|
|
output_cost_per_m = 0.2
|
|
supports_streaming = true
|