LLM Pricing
← All models

deepseek-r1-0528-maas

vertex_ai-deepseek_models · chat model

Input
$1.3500 / 1M tokens
Output
$5.4000 / 1M tokens
Cached input
N/A
Context
8.2K

Pricing

Item Raw value (per token) Normalized
Input 0.00000135 $1.3500 / 1M tokens
Output 0.0000054 $5.4000 / 1M tokens
Embedding 0.00000135 $1.3500 / 1M tokens

Token limits

Context window
8.2K
Max input tokens
65.3K
Max output tokens
8.2K
Max tokens
8.2K

Capabilities

Capability Supported
Vision No
Function calling Yes
Parallel function calling No
Tool choice Yes
Prompt caching Yes
Reasoning Yes
Response schema No
System messages No
Audio input No
Audio output No
Web search No
PDF input No
Video input No

Similar models

Models with comparable pricing in the same mode (chat).

Model Provider Input Output Context Coding Features
MAI-DS-R1 azure_ai $1.3500 / 1M tokens $5.4000 / 1M tokens 8.2K N/A Reasoning
deepseek-r1 azure_ai $1.3500 / 1M tokens $5.4000 / 1M tokens 8.2K N/A Reasoning
us.deepseek.r1-v1:0 bedrock_converse $1.3500 / 1M tokens $5.4000 / 1M tokens 4.1K N/A Reasoning
deepseek-v3.1-maas vertex_ai-deepseek_models $1.3500 / 1M tokens $5.4000 / 1M tokens 32.8K N/A Tools Cache Reasoning
apac.anthropic.claude-haiku-4-5-20251001-v1:0 bedrock_converse $1.1000 / 1M tokens $5.5000 / 1M tokens 64.0K N/A Vision Tools Cache Reasoning
eu.anthropic.claude-haiku-4-5-20251001-v1:0 bedrock_converse $1.1000 / 1M tokens $5.5000 / 1M tokens 64.0K N/A Vision Tools Cache Reasoning

Sources

Pricing source LiteLLM model cost map
Synced at 2026-05-27
Manual review Not reviewed
Raw LiteLLM fields
{
  "input_cost_per_token": 0.00000135,
  "litellm_provider": "vertex_ai-deepseek_models",
  "max_input_tokens": 65336,
  "max_output_tokens": 8192,
  "max_tokens": 8192,
  "mode": "chat",
  "output_cost_per_token": 0.0000054,
  "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
  "supported_regions": [
    "us-central1"
  ],
  "supports_assistant_prefill": true,
  "supports_function_calling": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_tool_choice": true
}