LLM Pricing
← All models

deepseek-reasoner

DeepSeek · chat model

Input
$0.2800 / 1M tokens
Output
$0.4200 / 1M tokens
Cached input
$0.0280 / 1M tokens
Context
65.5K

Pricing

Item Raw value (per token) Normalized
Input 2.8e-7 $0.2800 / 1M tokens
Output 4.2e-7 $0.4200 / 1M tokens
Cached input 2.8e-8 $0.0280 / 1M tokens
Embedding 2.8e-7 $0.2800 / 1M tokens

Token limits

Context window
65.5K
Max input tokens
131.1K
Max output tokens
65.5K
Max tokens
65.5K

Capabilities

Capability Supported
Vision No
Function calling No
Parallel function calling No
Tool choice No
Prompt caching Yes
Reasoning Yes
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
DeepSeek Chat DeepSeek $0.2800 / 1M tokens $0.4200 / 1M tokens 8.2K N/A Tools Cache
deepseek-chat DeepSeek $0.2800 / 1M tokens $0.4200 / 1M tokens 8.2K N/A Tools Cache
deepseek-reasoner DeepSeek $0.2800 / 1M tokens $0.4200 / 1M tokens 65.5K N/A Cache Reasoning
deepseek-v3.2-exp novita $0.2700 / 1M tokens $0.4100 / 1M tokens 65.5K N/A Tools Reasoning
deepseek-v3.2 DeepSeek $0.2800 / 1M tokens $0.4000 / 1M tokens 163.8K N/A Tools Cache Reasoning
DeepSeek-V3.2 gmi $0.2800 / 1M tokens $0.4000 / 1M tokens 16.4K N/A Tools

Sources

Pricing source LiteLLM model cost map
Synced at 2026-05-27
Manual review Not reviewed
Raw LiteLLM fields
{
  "cache_read_input_token_cost": 2.8e-8,
  "input_cost_per_token": 2.8e-7,
  "litellm_provider": "deepseek",
  "max_input_tokens": 131072,
  "max_output_tokens": 65536,
  "max_tokens": 65536,
  "mode": "chat",
  "output_cost_per_token": 4.2e-7,
  "source": "https://api-docs.deepseek.com/quick_start/pricing",
  "supported_endpoints": [
    "/v1/chat/completions"
  ],
  "supports_function_calling": false,
  "supports_native_streaming": true,
  "supports_parallel_function_calling": false,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_system_messages": true,
  "supports_tool_choice": false
}