LLM Pricing
← All models

gpt-4.5-preview

Azure · chat model

Input
$75.0000 / 1M tokens
Output
$150.0000 / 1M tokens
Cached input
$37.5000 / 1M tokens
Context
16.4K

Pricing

Item Raw value (per token) Normalized
Input 0.000075 $75.0000 / 1M tokens
Output 0.00015 $150.0000 / 1M tokens
Cached input 0.0000375 $37.5000 / 1M tokens
Embedding 0.000075 $75.0000 / 1M tokens
Batch input 0.0000375 $37.5000 / 1M tokens
Batch output 0.000075 $75.0000 / 1M tokens

Token limits

Context window
16.4K
Max input tokens
128.0K
Max output tokens
16.4K
Max tokens
16.4K

Capabilities

Capability Supported
Vision Yes
Function calling Yes
Parallel function calling Yes
Tool choice Yes
Prompt caching Yes
Reasoning No
Response schema Yes
System messages Yes
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
gpt-4-32k Azure $60.0000 / 1M tokens $120.0000 / 1M tokens 4.1K N/A
gpt-4-32k-0613 Azure $60.0000 / 1M tokens $120.0000 / 1M tokens 4.1K N/A
gpt-5.2-pro OpenRouter $21.0000 / 1M tokens $168.0000 / 1M tokens 128.0K N/A Vision Tools Reasoning
claude-4-opus deepinfra $16.5000 / 1M tokens $82.5000 / 1M tokens 200.0K N/A Tools
Qwen2-Audio-7B-Instruct sambanova $0.5000 / 1M tokens $100.0000 / 1M tokens 4.1K N/A
databricks-claude-opus-4 databricks $15.0000 / 1M tokens $75.0000 / 1M tokens 32.0K N/A Tools Reasoning

Sources

Pricing source LiteLLM model cost map
Synced at 2026-05-27
Manual review Not reviewed
Raw LiteLLM fields
{
  "cache_read_input_token_cost": 0.0000375,
  "input_cost_per_token": 0.000075,
  "input_cost_per_token_batches": 0.0000375,
  "litellm_provider": "azure",
  "max_input_tokens": 128000,
  "max_output_tokens": 16384,
  "max_tokens": 16384,
  "mode": "chat",
  "output_cost_per_token": 0.00015,
  "output_cost_per_token_batches": 0.000075,
  "supports_function_calling": true,
  "supports_parallel_function_calling": true,
  "supports_prompt_caching": true,
  "supports_response_schema": true,
  "supports_system_messages": true,
  "supports_tool_choice": true,
  "supports_vision": true
}