Sonar Deep Research pricing
Sonar Deep Research, Reasoning-tier from Perplexity, costs $2.00 per 1M input tokens and $8.00 per 1M output tokens.
Input$2.00per 1M tokens
Output$8.00per 1M tokens
Context window—tokens
TierReasoningPerplexity
Price your own workload against Sonar Deep Research in the calculator →
Specs and pricing
| Provider | Perplexity |
| Tier | Reasoning |
| Context window | — |
| Max output | — |
| Input price | $2.00 / 1M tokens |
| Output price | $8.00 / 1M tokens |
| Modalities | text |
Note. Additionally bills citation tokens at $2 per 1M tokens, reasoning tokens at $3 per 1M tokens, and search queries at $5 per 1000 queries. Not listed in the per-request search-context-size fee table (Sonar/Sonar Pro/Sonar Reasoning Pro only).
What it costs at realistic volumes
Assuming a 4:1 input:output token ratio, a common shape for chat and RAG-style workloads:
| Volume (4:1 in:out ratio) | Input cost | Output cost | Total / month |
|---|---|---|---|
| 1,000,000 in / 250,000 out | $2.00 | $2.00 | $4.00 |
| 10,000,000 in / 2,500,000 out | $20.00 | $20.00 | $40.00 |
| 100,000,000 in / 25,000,000 out | $200.00 | $200.00 | $400.00 |
Cheaper alternatives
Same tier (Reasoning), a different provider, and a lower blended cost at the 4:1 ratio used above:
| Model | Provider | $/1M in | $/1M out | At the 4:1 ratio |
|---|---|---|---|---|
| Trinity Large (Thinking) | Parasail | $0.22 | $0.85 | 89.2% cheaper blended |
| GPT-5.1-codex-mini | Azure OpenAI Service | $0.25 | $2.00 | 81.3% cheaper blended |
| QwQ 32B | Cloudflare Workers AI | $0.66 | $1.00 | 77.3% cheaper blended |
| DeepSeek-R1-Distill-Llama-70B | SambaNova | $0.70 | $1.40 | 73.8% cheaper blended |
| Kimi K2 Thinking | Novita AI | $0.60 | $2.50 | 69.4% cheaper blended |