llm-engine/providers.yml at main · houhuawei23/llm-engine · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
providers:
  deepseek:
    base_url: "https://api.deepseek.com/v1"
    api_key: ${DEEPSEEK_API_KEY}
    default_model: "deepseek-chat"
    models:
      - name: "deepseek-chat"
        provider: deepseek
        context_length: 128000
        max_output:
          default: 4000
          maximum: 8000
        speed_tokens_per_second: 30
        token_per_character:
          english: 0.3
          chinese: 0.6
        pricing_per_million_tokens: # 人民币/元
          input: 2 # ￥/百万，cache miss
          input_cache_hit: 0.2 # ￥/百万
          output: 3 # ￥/百万
        functions:
          json_output: true
      - name: "deepseek-reasoner"
        context_length: 128000
        max_output:
          default: 4000
          maximum: 8000
        speed_tokens_per_second: 30
        token_per_character:
          english: 0.3
          chinese: 0.6
        pricing_per_million_tokens: # 人民币/元
          input: 2 # ￥/百万，cache miss
          input_cache_hit: 0.2 # ￥/百万
          output: 3 # ￥/百万
        functions:
          json_output: true
  openai:
    base_url: "https://api.openai.com/v1"
    api_key: ${OPENAI_API_KEY}
    default_model: "gpt-4"
    models:
      - name: "gpt-4"
      - name: "gpt-3.5-turbo"
  ollama:
    base_url: "http://localhost:11434"
    api_key: null
    default_model: "llama2"
    models:
      - name: "llama2"
      - name: "mistral"
  kimi:
    base_url: "https://api.moonshot.cn/v1"
    api_key: "${KIMI_API_KEY}"
    default_model: "moonshot-v1-8k"
    models:
      - name: "moonshot-v1-8k"
      - name: "moonshot-v1-32k"
  kimi-code:
    base_url: "https://api.kimi.com/coding"
    api_key: "${KIMI_CODE_API_KEY}"
    default_model: "kimi-k2-0711-preview"
    models:
      - name: "kimi-k2-0711-preview"
        context_length: 256000
        max_output:
          default: 8000
          maximum: 32000
        speed_tokens_per_second: 40
      - name: "kimi-k2-0711-preview-longcontext"
        context_length: 2000000
        max_output:
          default: 8000
          maximum: 32000
        speed_tokens_per_second: 30
      - name: "kimi-k2.5-preview"
        context_length: 256000
        max_output:
          default: 8000
          maximum: 32000
        speed_tokens_per_second: 50