| Input / 1M tokens | Output / 1M tokens | Relative Cost | |
|---|---|---|---|
| DeepSeek V3.2 | $0.28 | $0.42 | 1x (baseline) |
| Gemini 1.5 Pro | $1.25 | $5.00 | ~4x to 12x more |
| GPT-4o | $2.50 | $10.00 | ~9x to 24x more |
| Claude Sonnet 4.6 | $3.00 | $15.00 | ~11x to 36x more |
| Claude Opus 4.6 | $5.00 | $25.00 | ~18x to 60x more |
$0
V3.2 input per 1M tokens
$0
Cache hit input per 1M tokens
$0
V3.2 output per 1M tokens
OpenAI compatibility
DeepSeek's API uses the OpenAI API format. Switch from OpenAI by changing the base URL to https://api.deepseek.com and swapping your API key. No code rewrite needed. The model IDs are deepseek-chat (V3.2) and deepseek-reasoner (R1).
| Notes | |
|---|---|
| OpenRouter | Unified API for 100+ models; useful for comparing models side by side |
| Together AI | US hosted infrastructure; good for data sovereignty concerns |
| Fireworks AI | Fast inference optimized for low latency applications |
| Groq | Ultra fast inference on custom LPU hardware |
| Ollama | Run locally on your own machine; supports distilled R1 variants |