DeepSeek-R1 vs Sonar Reasoning Pro
API pricing, benchmark indices and specs — updated 19 October 2026.
deepseek-ai · A · Open weights
Params
684.5 B
Context
163,840
30d
1.4 M
mit · commercial OK
perplexity · B · API-only
Input / 1M
$2.00
Output / 1M
$8.00
AA index
11.8
proprietary · 128K context
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | DeepSeek-R1 | Sonar Reasoning Pro |
|---|---|---|
| Deployment | Open weights · also via API | API-only (closed weights) |
| Parameters | 684.5 B | n/a — API-only |
| Architecture | DeepseekV3ForCausalLM | n/a — API-only |
| Context length | 163,840 | 128,000 |
| Licence | mit | Proprietary |
| Commercial use | Allowed | Per API terms |
| Languages | — | n/a — API-only |
| Downloads 30d | 1,391,551 | n/a — API-only |
| Downloads all time | 50.3 M | n/a — API-only |
| Quantizations on the Hub | SAFETENSORS | n/a — API-only |
| Gated | No | n/a — API-only |
| First seen on the Hub | 2025-01-20 | n/a — API-only |
| API input price / 1M tokens | $0.70 | $2.00 |
| API output price / 1M tokens | $2.50 | $8.00 |
| Est. cost per 1M input + 1M output tokens | $3.20 | $10.00 |
| Cached input / 1M tokens | — | — |
| AA Intelligence Index | 11.4 | 11.8 |
| AA Coding Index | 24.6 | — |
| AA Agentic Index | 1.1 | — |
| Max output tokens | 16,000 | 115,200 |
| API providers | — | 1 |
| Tool calling | Yes | No |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
DeepSeek-R1
$3.20
Sonar Reasoning Pro
$10.00
DeepSeek-R1 is 3.1× cheaper at list price.
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
DeepSeek-R1 · fp16 @ 160K ctx
2,811.5 GB / 24 GB