Text model
sonar-medium-online pricing
Perplexity charges $0.00 per million input tokens and $1.80 per million output tokens for sonar-medium-online. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $0.00/ 1M
- Output
- $1.80/ 1M
- Context
- 12Ktokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $0.00 | $1.80 | — | — |
USD per million tokens. Long-context tiers apply when the whole prompt, cached tokens included, passes the threshold.
Work it out
What common workloads cost
| Workload | Per call | Cost per call | Calls a month | Per month |
|---|---|---|---|---|
| Chat reply | 1,500 input and 400 output tokens | $0.00072 | 100,000 | $72.00 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.0009 | 100,000 | $90.00 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.00144 | 250,000 | $360.00 |
| Batch summary | 3,000 input and 300 output tokens via the Batch API | — | 1,000,000 | — |
Planning a mix of models? Simulate a workload with sonar-medium-online, alongside anything else you run.
Cheaper options
Current models that cost at least 15% less for a typical chat reply. Cheaper isn't always equivalent: test quality on your own prompts, then use veqen diff to see the impact at your volume.
| Model | Chat reply | Saving |
|---|---|---|
| perplexity/llama-3.1-8b-instruct | $0.00038 | 47% |
| perplexity/sonar-small-chat | $0.000217 | 70% |
| deepinfra/Qwen/Qwen3.5-35B-A3B | $0.00061 | 15% |
| deepseek/deepseek-v3.2 | $0.00058 | 19% |
Price history
No price changes since Veqen started tracking this model.
Compare
Last verified with price book 2026-10-22. Sources: Perplexity pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.