DeepSeek Coder 2 Instruct
DeepSeek Coder 2 Instruct is DeepSeek's language model with a 66K context window and up to 8K output tokens, starting at $1.20 / 1M input and $1.20 / 1M output. The instruction-tuned variant of DeepSeek Coder V2, a MoE code LLM achieving GPT-4-Turbo-level performance on code-specific benchmarks.
Capabilities
Input1/5
✓
·
·
·
·
Output1/5
✓
·
·
·
·
Capabilities2/13
·
·
✓
·
✓
·
·
·
·
·
·
·
·
Pricing by Provider
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
 Fireworks AI | $1.20 | $1.20 |
Cost Calculator
Preset:
Compares every provider & tier in USD
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| DeepSeek Coder 2 Instruct | — | 66K | $1.20 | $1.20 | Current |
| DeepSeek Coder 2 Base | — | 8K | — | — | Available |
| DeepSeek Coder | — | 128K | $0.140 | $0.280 | Available |
| DeepSeek Coder 6.7B | — | 16K | $0.060 | $0.120 | Available |
| DeepSeek Coder V2 | — | — | — | — | Available |
| DeepSeek Coder V2 Lite Instruct | — | — | — | — | Available |