DeepSeek V2.5
DeepSeek V2.5 is DeepSeek's language model with a 33K context window, starting at $1.20 / 1M input and $1.20 / 1M output. An upgraded DeepSeek model merging the capabilities of DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct into a single unified assistant.
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
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
 Fireworks AI | $1.20 | $1.20 |
Cost Calculator
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| DeepSeek V2.5 | — | 33K | $1.20 | $1.20 | Current |
| DeepSeek Coder V2 Lite Base | — | 164K | $0.500 | $0.500 | Available |
| DeepSeek Coder V2 Lite Instruct | — | 164K | $0.500 | $0.500 | Available |
| DeepSeek V2 Lite Chat | — | 164K | $0.500 | $0.500 | Available |