Perplexity lists 5 models and Recursive 1. Below: line-up, price tiers, the cheapest model for each capability, and what each costs for five real workloads.
| Perplexity | Recursive | |
|---|---|---|
| Models listed | 5 | 1 |
| Models with published pricing | 5 | 1 |
| Typical price (median, 3:1 blend per 1M) | $3.50 | n/a |
| Cheapest paid model | Perplexity: Sonar ($1.00) | n/a |
| Longest context | Perplexity: Sonar Pro (200K) | Recursive: Flint (free) (262K) |
| Free models | 0 | 1 |
| Newest model | Perplexity: Sonar Pro Search (2025-10-30) | Recursive: Flint (free) (2026-10-21) |
| Price changes in the last 90 days | 0 | 0 |
For each workload: the cheapest model from each provider that can actually do it (fits the context window; tool calling required for the agent), and its monthly cost at list price.
| Workload (per month) | Perplexity | Recursive |
|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation | $95.00 with Perplexity: Sonar | no suitable model |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages | $130 with Perplexity: Sonar | no suitable model |
| Coding / tool-using agent 2,000 tasks — each a multi-step task with tool calls and file context | no suitable model | no suitable model |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page | $86.00 with Perplexity: Sonar | no suitable model |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass | $51.00 with Perplexity: Sonar | no suitable model |
| You need | Perplexity | Recursive |
|---|---|---|
| Any model | Perplexity: Sonar ($1.00) | none listed |
| With tool calling | none listed | none listed |
| With image input | Perplexity: Sonar ($1.00) | none listed |
| With reasoning mode | Perplexity: Sonar Deep Research ($3.50) | none listed |
| 128K+ context | Perplexity: Sonar Deep Research ($3.50) | none listed |
| 1M+ context | none listed | none listed |
| Model type | Perplexity | Recursive |
|---|---|---|
| text+image->text | 4 | 0 |
| text->text | 1 | 1 |
| Price per 1M (3:1 blend) | Perplexity | Recursive |
|---|---|---|
| Free | 0 | 1 |
| Under $0.50 | 0 | 0 |
| $0.50 – $3 | 1 | 0 |
| $3 – $10 | 4 | 0 |
| $10 and up | 0 | 0 |
It depends on the job: Perplexity offers the broader line-up (5 models vs 1), Recursive the longest context (262K tokens). The workload table above shows which wins for chat, RAG, agents, batch jobs and long documents.
Perplexity: Perplexity lists 5 models and Recursive lists 1.
Recursive: Perplexity's longest is Perplexity: Sonar Pro at 200K tokens; Recursive's is Recursive: Flint (free) at 262K.
Perplexity: none. Recursive: 1 free model (e.g. Recursive: Flint (free)).
Perplexity: 4 of 5 models accept images. Recursive: 0 of 1.