LLM Pricing
← All models

deepseek-v3

DeepSeek · chat model

Input
$0.2700 / 1M tokens
Output
$1.1000 / 1M tokens
Cached input
$0.0700 / 1M tokens
Context
8.2K

Pricing

Item Raw value (per token) Normalized
Input 2.7e-7 $0.2700 / 1M tokens
Output 0.0000011 $1.1000 / 1M tokens
Cached input 7e-8 $0.0700 / 1M tokens
Embedding 2.7e-7 $0.2700 / 1M tokens

Token limits

Context window
8.2K
Max input tokens
65.5K
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 No
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
ernie-4.5-300b-a47b-paddle novita $0.2800 / 1M tokens $1.1000 / 1M tokens 12.0K N/A
deepseek-v3-0324 novita $0.2700 / 1M tokens $1.1200 / 1M tokens 163.8K N/A Tools
minimax-m2.5 OpenRouter $0.3000 / 1M tokens $1.1000 / 1M tokens 65.5K N/A Tools Cache Reasoning
qwen3-235b-a22b-instruct-2507 replicate $0.2640 / 1M tokens $1.0600 / 1M tokens N/A N/A Tools
GLM-4.5-Air-FP8 Together AI $0.2000 / 1M tokens $1.1000 / 1M tokens N/A N/A Tools
glm-4.5-air vercel_ai_gateway $0.2000 / 1M tokens $1.1000 / 1M tokens 96.0K N/A Tools

Sources

Pricing source LiteLLM model cost map
Synced at 2026-05-27
Manual review Not reviewed
Raw LiteLLM fields
{
  "cache_creation_input_token_cost": 0,
  "cache_read_input_token_cost": 7e-8,
  "input_cost_per_token": 2.7e-7,
  "input_cost_per_token_cache_hit": 7e-8,
  "litellm_provider": "deepseek",
  "max_input_tokens": 65536,
  "max_output_tokens": 8192,
  "max_tokens": 8192,
  "mode": "chat",
  "output_cost_per_token": 0.0000011,
  "supports_assistant_prefill": true,
  "supports_function_calling": true,
  "supports_prompt_caching": true,
  "supports_tool_choice": true
}