86 lines
3.6 KiB
YAML
86 lines
3.6 KiB
YAML
# 豆包 Seed 2.1 文本/Agent 模型档案(火山方舟 Ark)
|
|
# 走 Ark 的 OpenAI 兼容 /chat/completions:litellm 用 `openai/` 前缀 + api_base 覆盖,
|
|
# 与 config/models/local.yaml 同范式(避免 litellm volcengine provider 的版本/字段差异)。
|
|
# api_key 复用媒体侧的 ARK_API_KEY(同一火山账号),env 见 RUN.md。
|
|
#
|
|
# Seed 2.1 的 thinking 走统一 extra_body 协议；保持既有深度思考行为，但由服务端默认
|
|
# 改为显式 enabled。方舟未声明 effort 等级，故只传 thinking、不猜 reasoning_effort。
|
|
# 单价见各 variant(元/百万 tokens,来源:火山方舟 2026-06 发布价)。
|
|
family: doubao
|
|
|
|
variants:
|
|
turbo:
|
|
display_name: 豆包 Seed 2.1 Turbo
|
|
model_id: openai/doubao-seed-2-1-turbo-260628
|
|
api_base: https://ark.cn-beijing.volces.com/api/v3
|
|
api_key_env: ARK_API_KEY
|
|
max_context: 262144 # 256K
|
|
reliable_context: 131072
|
|
max_output: 16384 # 模型上限 128K(含思考),这里保守取值,需要长输出可调高
|
|
parallel_tools: true # Ark 兼容 parallel_tool_calls,默认 true
|
|
tool_calling_quality: good
|
|
thinking_enabled: true
|
|
thinking_transport: extra_body
|
|
reasoning_effort_levels: []
|
|
default_reasoning_effort: ""
|
|
code_quality: good
|
|
enable_run_python: true
|
|
max_iterations: 120 # backstop 兜底,非"轮"预算;真正的空转防护是 loop 的无进展熔断 + _RepeatGuard
|
|
optimal_temperature: 0.3
|
|
prompt_caching: false
|
|
extended_thinking: false
|
|
input_cny_per_mtoken: 3.0
|
|
output_cny_per_mtoken: 15.0
|
|
cache_hit_cny_per_mtoken: 0.6
|
|
|
|
pro:
|
|
display_name: 豆包 Seed 2.1 Pro
|
|
model_id: openai/doubao-seed-2-1-pro-260628
|
|
api_base: https://ark.cn-beijing.volces.com/api/v3
|
|
api_key_env: ARK_API_KEY
|
|
max_context: 262144 # 256K
|
|
reliable_context: 131072
|
|
max_output: 16384 # 模型上限 128K(含思考),这里保守取值,需要长输出可调高
|
|
parallel_tools: true
|
|
tool_calling_quality: excellent
|
|
thinking_enabled: true
|
|
thinking_transport: extra_body
|
|
reasoning_effort_levels: []
|
|
default_reasoning_effort: ""
|
|
code_quality: excellent
|
|
enable_run_python: true
|
|
max_iterations: 150 # backstop 兜底,非"轮"预算;真正的空转防护是 loop 的无进展熔断 + _RepeatGuard
|
|
optimal_temperature: 0.3
|
|
prompt_caching: false
|
|
extended_thinking: false
|
|
input_cny_per_mtoken: 6.0
|
|
output_cny_per_mtoken: 30.0
|
|
cache_hit_cny_per_mtoken: 1.2
|
|
|
|
evolving:
|
|
# 自进化版:统一 model_id `doubao-seed-evolving`,每周至少迭代一次,始终指向最新版。
|
|
# 面向 Coding/Agent 持续优化,覆盖全场景(与 pro 旗舰、turbo 低成本并列)。
|
|
display_name: 豆包 Seed Evolving(自进化)
|
|
model_id: openai/doubao-seed-evolving
|
|
api_base: https://ark.cn-beijing.volces.com/api/v3
|
|
api_key_env: ARK_API_KEY
|
|
max_context: 262144 # 256K(随版本可能变,按 Seed 2.1 家族取值)
|
|
reliable_context: 131072
|
|
max_output: 16384
|
|
parallel_tools: true
|
|
tool_calling_quality: excellent
|
|
thinking_enabled: true
|
|
thinking_transport: extra_body
|
|
reasoning_effort_levels: []
|
|
default_reasoning_effort: ""
|
|
code_quality: excellent
|
|
enable_run_python: true
|
|
max_iterations: 150 # backstop 兜底,非"轮"预算;真正的空转防护是 loop 的无进展熔断 + _RepeatGuard
|
|
optimal_temperature: 0.3
|
|
prompt_caching: false
|
|
extended_thinking: false
|
|
# evolving 官方未单独公布单价,暂按 pro 估值兜底(宁高勿低,不少记成本);公布后校正。
|
|
input_cny_per_mtoken: 6.0
|
|
output_cny_per_mtoken: 30.0
|
|
cache_hit_cny_per_mtoken: 1.2
|