DeepSeek Coder 33B Instruct is DeepSeek's language model with a 16K context window and up to 16K output tokens, starting at $0.9 / 1M input and $0.9 / 1M output. A 33B-parameter instruction-tuned code LLM trained from scratch on 2T tokens with 87% code content for advanced code generation and reasoning.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
| $0.9 | $0.9 | |
Cost Calculator
US Dollar ($)
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| DeepSeek Coder 2 Base | — | 8K | — | — | Available |
| DeepSeek Coder 2 Instruct | — | 66K | $1.20 | $1.20 | Available |
| DeepSeek Coder V2 Lite Base | — | 164K | $0.500 | $0.500 | Available |
| DeepSeek Coder V2 Lite Instruct | — | 164K | $0.500 | $0.500 | Available |
| DeepSeek Coder 7B Base v1.5 | — | 4K | $0.200 | $0.200 | Available |
| DeepSeek Coder 7B Instruct v1.5 | — | 4K | $0.200 | $0.200 | Available |
| DeepSeek Coder 33B Instruct | — | 16K | $0.900 | $0.900 | Current |
| DeepSeek Coder | — | 128K | $0.140 | $0.280 | Available |
| DeepSeek Coder 1.3B Base | — | 16K | $0.100 | $0.100 | Available |
| DeepSeek Coder 6.7B | — | 16K | $0.060 | $0.120 | Available |
| DeepSeek Coder 7B Base | — | 4K | $0.200 | $0.200 | Available |