DeepSeek Coder V2 Lite Instruct
DeepSeek Coder V2 Lite Instruct is DeepSeek's language model with a 164K context window and up to 8K output tokens, starting at $0.5 / 1M input and $0.5 / 1M output. A 16B-parameter MoE code LLM with 2.4B active parameters, fine-tuned on instruction data for responsive code generation and chat.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities1/13
Reasoning·
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
| $0.5 | $0.5 | |
Cost Calculator
US Dollar ($)
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| DeepSeek Coder V2 Lite Instruct | — | 164K | $0.500 | $0.500 | Current |
| DeepSeek Coder V2 Lite Base | — | 164K | $0.500 | $0.500 | Available |
| DeepSeek Coder V2 Lite Instruct | — | — | — | — | Available |
Other Models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| DeepSeek Coder 2 Base | — | — | 8K | — | — |
| DeepSeek Coder 2 Instruct | — | — | 66K | $1.20 | $1.20 |
| DeepSeek Coder 7B Base v1.5 | — | — | 4K | $0.200 | $0.200 |
| DeepSeek Coder 7B Instruct v1.5 | — | — | 4K | $0.200 | $0.200 |
| DeepSeek Coder | — | — | 128K | $0.140 | $0.280 |
| DeepSeek Coder 1.3B Base | — | — | 16K | $0.100 | $0.100 |
| DeepSeek Coder 33B Instruct | — | — | 16K | $0.900 | $0.900 |
| DeepSeek Coder 6.7B | — | — | 16K | $0.060 | $0.120 |
| DeepSeek Coder 7B Base | — | — | 4K | $0.200 | $0.200 |
| DeepSeek Coder V2 | — | — | — | — | — |