DeepSeek logo

DeepSeek Coder V2 Lite Base


DeepSeek Coder V2 Lite Base is DeepSeek logoDeepSeek's language model with a 164K context window and up to 8K output tokens, starting at $0.500 / 1M input and $0.500 / 1M output. The base pre-trained variant of DeepSeek Coder V2 Lite, a 16B-parameter MoE code LLM with 2.4B active parameters for code completion.
Spec
Canonical IDdeepseek-coder-v2-lite-base
TypeLanguage
StatusActive
CreatorDeepSeekDeepSeek
Providers
Context Window164K tokens
Max Output8K tokens
Input ModalitiesText
Output ModalitiesText

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities1/13
Reasoning·
Adaptive Reasoning·
Function Calling
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

ProviderStandard
Input
$ / 1M
Output
$ / 1M
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-base
$0.500$0.500

Cost Calculator

Preset:
Compares every provider & tier in USD

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
DeepSeek Coder V2 Lite Base164K$0.500$0.500Current
DeepSeek Coder V2 Lite Instruct164K$0.500$0.500Available
DeepSeek V2 Lite Chat164K$0.500$0.500Available

Other models

ModelTierReleasedContextInput / 1MOutput / 1M
DeepSeek V2.533K$1.20$1.20

Model IDs