models/providers/google-vertex/anthropic/claude-sonnet-4-6@default.yaml at 34cc78002d35c9cbf53ea4c8a537bf708173d2f4 · truefoundry/models · 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
82
83
84
85
86
87
88
89
90
costs:
    - cache_creation_input_token_cost: 0.000004125
      cache_creation_input_token_cost_per_hour: 0.0000066
      cache_read_input_token_cost: 3.3e-7
      input_cost_per_token: 0.0000033
      input_cost_per_token_batches: 0.00000165
      output_cost_per_token: 0.0000165
      output_cost_per_token_batches: 0.00000825
      region: us-east5
    - cache_creation_input_token_cost: 0.000004125
      cache_creation_input_token_cost_per_hour: 0.0000066
      cache_read_input_token_cost: 3.3e-7
      input_cost_per_token: 0.0000033
      input_cost_per_token_batches: 0.00000165
      output_cost_per_token: 0.0000165
      output_cost_per_token_batches: 0.00000825
      region: us
    - cache_creation_input_token_cost: 0.00000375
      cache_creation_input_token_cost_per_hour: 0.000006
      cache_read_input_token_cost: 3e-7
      input_cost_per_token: 0.000003
      input_cost_per_token_batches: 0.0000015
      output_cost_per_token: 0.000015
      output_cost_per_token_batches: 0.0000075
      region: global
    - cache_creation_input_token_cost: 0.000004125
      cache_creation_input_token_cost_per_hour: 0.0000066
      cache_read_input_token_cost: 3.3e-7
      input_cost_per_token: 0.0000033
      input_cost_per_token_batches: 0.00000165
      output_cost_per_token: 0.0000165
      output_cost_per_token_batches: 0.00000825
      region: europe-west1
    - cache_creation_input_token_cost: 0.000004125
      cache_creation_input_token_cost_per_hour: 0.0000066
      cache_read_input_token_cost: 3.3e-7
      input_cost_per_token: 0.0000033
      input_cost_per_token_batches: 0.00000165
      output_cost_per_token: 0.0000165
      output_cost_per_token_batches: 0.00000825
      region: eu
    - cache_creation_input_token_cost: 0.000004125
      cache_creation_input_token_cost_per_hour: 0.0000066
      cache_read_input_token_cost: 3.3e-7
      input_cost_per_token: 0.0000033
      input_cost_per_token_batches: 0.00000165
      output_cost_per_token: 0.0000165
      output_cost_per_token_batches: 0.00000825
      region: asia-southeast1
features:
    - function_calling
    - parallel_function_calling
    - tool_choice
    - prompt_caching
    - cache_control
    - structured_output
    - assistant_prefill
    - system_messages
limits:
    context_window: 1000000
    max_input_tokens: 1000000
    max_output_tokens: 128000
    max_tokens: 128000
    tool_use_system_prompt_tokens: 497
modalities:
    input:
        - text
        - image
        - pdf
    output:
        - text
mode: chat
model: anthropic/claude-sonnet-4-6@default
params:
    - key: max_tokens
      maxValue: 128000
    - key: temperature
      maxValue: 1
provisioning: serverless
removeParams:
    - "n"
sources:
    - https://docs.cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/sonnet-4-6
    - https://platform.claude.com/docs/en/about-claude/pricing
    - https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai
    - https://platform.claude.com/docs/en/about-claude/models/overview
status: active
supportedModes:
    - chat
thinking: true