api_config.yaml

gpt-4o-mini-2024-07-18:
    model: gpt-4o-mini-2024-07-18
    endpoints: null
    api_type: openai
    max_tokens: 8192
    temperature: 0.7
    organization: OpenAI

gpt-4.1-mini-2025-04-14:
    model: gpt-4.1-mini-2025-04-14
    endpoints: null
    api_type: openai
    max_tokens: 8192
    temperature: 0.7
    organization: OpenAI

# gpt-5-mini-2025-08-07:
#     model: gpt-5-mini-2025-08-07
#     endpoints: null
#     api_type: openai
#     max_tokens: 8192
#     temperature: 0.7
#     organization: OpenAI

qwen3-max-2025-09-23:
    model: qwen3-max-2025-09-23
    endpoints:
        - api_base: https://dashscope.aliyuncs.com/compatible-mode/v1
          api_key: ${DASHSCOPE_API_KEY}
    api_type: openai
    max_tokens: 8192
    temperature: 0.7
    organization: Alibaba

qwen3-coder-plus-2025-09-23:
    model: qwen3-coder-plus-2025-09-23
    endpoints:
        - api_base: https://dashscope.aliyuncs.com/compatible-mode/v1
          api_key: ${DASHSCOPE_API_KEY}
    api_type: openai
    max_tokens: 8192
    temperature: 0.7
    organization: Alibaba

qwen3-coder-flash-2025-07-28:
    model: qwen3-coder-flash-2025-07-28
    endpoints:
        - api_base: https://dashscope.aliyuncs.com/compatible-mode/v1
          api_key: ${DASHSCOPE_API_KEY}
    api_type: openai
    max_tokens: 8192
    temperature: 0.7
    organization: Alibaba

qwen3-next-80b-a3b-thinking:
    model: qwen3-next-80b-a3b-thinking
    endpoints:
        - api_base: https://dashscope.aliyuncs.com/compatible-mode/v1
          api_key: ${DASHSCOPE_API_KEY}
    api_type: openai_thinking
    max_tokens: 8192
    temperature: 0.7
    organization: Alibaba

qwen3-next-80b-a3b-instruct:
    model: qwen3-next-80b-a3b-instruct
    endpoints:
        - api_base: https://dashscope.aliyuncs.com/compatible-mode/v1
          api_key: ${DASHSCOPE_API_KEY}
    api_type: openai
    max_tokens: 8192
    temperature: 0.7
    organization: Alibaba

qwen3-235b-a22b-thinking-2507:
    model: qwen3-235b-a22b-thinking-2507
    endpoints:
        - api_base: https://dashscope.aliyuncs.com/compatible-mode/v1
          api_key: ${DASHSCOPE_API_KEY}
    api_type: openai_thinking
    max_tokens: 8192
    temperature: 0.7
    organization: Alibaba

qwen3-235b-a22b-instruct-2507:
    model: qwen3-235b-a22b-instruct-2507
    endpoints:
        - api_base: https://dashscope.aliyuncs.com/compatible-mode/v1
          api_key: ${DASHSCOPE_API_KEY}
    api_type: openai
    max_tokens: 8192
    temperature: 0.7
    organization: Alibaba

qwen3-30b-a3b-thinking-2507:
    model: qwen3-30b-a3b-thinking-2507
    endpoints:
        - api_base: https://dashscope.aliyuncs.com/compatible-mode/v1
          api_key: ${DASHSCOPE_API_KEY}
    api_type: openai_thinking
    max_tokens: 8192
    temperature: 0.7
    organization: Alibaba

qwen3-30b-a3b-instruct-2507:
    model: qwen3-30b-a3b-instruct-2507
    endpoints:
        - api_base: https://dashscope.aliyuncs.com/compatible-mode/v1
          api_key: ${DASHSCOPE_API_KEY}
    api_type: openai
    max_tokens: 8192
    temperature: 0.7
    organization: Alibaba

DeepSeek-V3.1-Terminus:
    model: deepseek-chat
    endpoints:
        - api_base: https://api.deepseek.com/v3.1_terminus_expires_on_20251015
          api_key: ${DEEPSEEK_API_KEY}
    api_type: openai
    max_tokens: 8192
    temperature: 0.7
    organization: DeepSeek

DeepSeek-V3.2-Exp:
    model: deepseek-chat
    endpoints:
        - api_base: https://api.deepseek.com
          api_key: ${DEEPSEEK_API_KEY}
    api_type: openai
    max_tokens: 8192
    temperature: 0.7
    organization: DeepSeek

GLM-4.6:
    model: glm-4.6
    endpoints:
        - api_base: https://api.z.ai/api/paas/v4/
          api_key: ${Z_API_KEY}
    api_type: openai
    max_tokens: 8192
    temperature: 0.7
    organization: Zhipu AI
    weight: 3.0

# o1-2024-12-17:
#     model: o1-2024-12-17
#     endpoints: null
#     api_type: openai
#     parallel: 32
#     max_tokens: 8192
#     temperature: 0.7
#     organization: OpenAI
#     license: Proprietary

# o4-mini-2025-04-16:
#     model: o4-mini-2025-04-16
#     endpoints: null
#     api_type: openai_thinking
#     parallel: 32
#     max_tokens: 8192
#     temperature: 1.0
#     organization: OpenAI
#     license: Proprietary

# o3-mini-2025-01-31:
#     model: o3-mini-2025-01-31
#     endpoints: null
#     api_type: openai_thinking
#     parallel: 32
#     max_tokens: 8192
#     temperature: 0.7
#     organization: OpenAI
#     license: Proprietary

# gemini-2.0-flash-001:
#     model: google/gemini-2.0-flash-001
#     endpoints:
#         - api_base: https://openrouter.ai/api/v1
#           api_key: ${OPENROUTER_API_KEY}
#     api_type: openai
#     parallel: 32
#     max_tokens: 81920
#     temperature: 0.7
#     organization: Google
#     license: Proprietary

# gemini-2.5-pro:
#     model: google/gemini-2.5-pro
#     endpoints:
#         - api_base: https://openrouter.ai/api/v1
#           api_key: ${OPENROUTER_API_KEY}
#     api_type: openai
#     parallel: 32
#     max_tokens: 8192
#     temperature: 0.7
#     organization: Google
#     license: Proprietary

# gemini-2.5-flash:
#     model: google/gemini-2.5-flash
#     endpoints:
#         - api_base: https://openrouter.ai/api/v1
#           api_key: ${OPENROUTER_API_KEY}
#     api_type: openai
#     parallel: 32
#     max_tokens: 8192
#     temperature: 0.7
#     organization: Google
#     license: Proprietary

# claude35_haiku:
#     model: bedrock/anthropic.claude-3-5-haiku-20241022-v1:0
#     endpoints: null
#     api_type: litellm
#     parallel: 32
#     max_tokens: 8192
#     temperature: 0.7
#     organization: Anthropic
#     license: Proprietary

# claude35_sonnet:
#     model: bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0
#     endpoints: null
#     api_type: litellm
#     parallel: 32
#     max_tokens: 8192
#     temperature: 0.7
#     organization: Anthropic
#     license: Proprietary

# claude37_sonnet:
#     model: bedrock/us.anthropic.claude-3-7-sonnet-20250219-v1:0
#     endpoints: null
#     api_type: litellm
#     parallel: 32
#     max_tokens: 8192
#     temperature: 0.7
#     organization: Anthropic
#     license: Proprietary

# qwen3-coder:
#     model: qwen/qwen3-coder
#     endpoints:
#         - api_base: https://openrouter.ai/api/v1
#           api_key: ${OPENROUTER_API_KEY}
#     api_type: openai
#     parallel: 32
#     max_tokens: 8192
#     temperature: 0.7
#     organization: Alibaba
#     license: Apache 2.0

# kimi-k2:
#     model: moonshotai/kimi-k2
#     endpoints:
#         - api_base: https://openrouter.ai/api/v1
#           api_key: ${OPENROUTER_API_KEY}
#     api_type: openai
#     parallel: 32
#     max_tokens: 8192
#     temperature: 0.7
#     organization: Moonshot
#     license: Modified MIT

# claude-4-sonnet:
#     model: bedrock/us.anthropic.claude-sonnet-4-20250514-v1:0
#     endpoints: null
#     api_type: litellm
#     parallel: 16
#     max_tokens: 8192
#     temperature: 0.7
#     organization: Anthropic
#     license: Proprietary

# claude-4-opus:
#     model: bedrock/us.anthropic.claude-opus-4-20250514-v1:0
#     endpoints: null
#     api_type: litellm
#     parallel: 16
#     max_tokens: 8192
#     temperature: 0.7
#     organization: Anthropic
#     license: Proprietary

# gpt-oss-120b:
#     model: openai/gpt-oss-120b
#     endpoints:
#         - api_base: https://openrouter.ai/api/v1
#           api_key: ${OPENROUTER_API_KEY}
#     api_type: openai_thinking
#     parallel: 32
#     max_tokens: 8192
#     temperature: 1.0
#     organization: OpenAI
#     license: MIT

# gpt-oss-20b:
#     model: openai/gpt-oss-20b
#     endpoints:
#         - api_base: https://openrouter.ai/api/v1
#           api_key: ${OPENROUTER_API_KEY}
#     api_type: openai_thinking
#     parallel: 32
#     max_tokens: 8192
#     temperature: 1.0
#     organization: OpenAI
#     license: MIT

# deepseek-chat-v3-0324:
#     model: deepseek/deepseek-chat-v3-0324
#     endpoints:
#         - api_base: https://openrouter.ai/api/v1
#           api_key: ${OPENROUTER_API_KEY}
#     api_type: openai
#     parallel: 32
#     max_tokens: 8192
#     temperature: 0.7
#     organization: DeepSeek
#     license: MIT

# deepseek-chat-v3.1:
#     model: deepseek-chat
#     endpoints:
#         - api_base: https://api.deepseek.com
#           api_key: ${DEEPSEEK_API_KEY}
#     api_type: openai
#     parallel: 32
#     max_tokens: 8192
#     temperature: 0.7
#     organization: DeepSeek
#     license: MIT

# glm-4.5:
#     model: z-ai/glm-4.5
#     endpoints:
#         - api_base: https://openrouter.ai/api/v1
#           api_key: ${OPENROUTER_API_KEY}
#     api_type: openai
#     parallel: 32
#     max_tokens: 8192
#     temperature: 0.7
#     organization: Zhipu AI
#     license: Custom

# gpt-4.1-2025-04-14:
#     model: gpt-4.1-2025-04-14
#     endpoints: null
#     api_type: openai
#     parallel: 32
#     max_tokens: 8192
#     temperature: 0.7
#     organization: OpenAI
#     license: Proprietary


# deepseek-r1-0528:
#     model: deepseek/deepseek-r1-0528
#     endpoints:
#         - api_base: https://openrouter.ai/api/v1
#           api_key: ${OPENROUTER_API_KEY}
#     api_type: openai_thinking
#     parallel: 32
#     max_tokens: 81920
#     temperature: 1.0
#     organization: DeepSeek
#     license: MIT

# gpt-5-2025-08-07:
#     model: gpt-5-2025-08-07
#     endpoints: null
#     api_type: openai_thinking
#     parallel: 32
#     max_tokens: 8192
#     temperature: 1.0
#     organization: OpenAI
#     license: Proprietary

# grok-code:
#     model: x-ai/grok-code-fast-1
#     endpoints:
#         - api_base: https://openrouter.ai/api/v1
#           api_key: ${OPENROUTER_API_KEY}
#     api_type: openai_thinking
#     parallel: 32
#     max_tokens: 8192
#     temperature: 1.0
#     organization: xAI
#     license: Proprietary