Is Recursive better than Undi95?
It depends on the job: both list 1 models, Recursive the longest context (262K tokens). The workload table above shows which wins for chat, RAG, agents, batch jobs and long documents.
Recursive vs Undi95
Recursive lists 1 models and Undi95 1. Below: line-up, price tiers, the cheapest model for each capability, and what each costs for five real workloads.
At a glance
| Recursive | Undi95 | |
|---|---|---|
| Models listed | 1 | 1 |
| Models with published pricing | 1 | 1 |
| Typical price (median, 3:1 blend per 1M) | n/a | $0.42 |
| Cheapest paid model | n/a | ReMM SLERP 13B ($0.42) |
| Longest context | Recursive: Flint (free) (262K) | ReMM SLERP 13B (6K) |
| Free models | 1 | 0 |
| Newest model | Recursive: Flint (free) (2026-10-21) | ReMM SLERP 13B (2023-07-22) |
| Price changes in the last 90 days | 0 | 1 |
Advertisement
What each costs for real workloads
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) | Recursive | Undi95 |
|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation | no suitable model | $39.25 with ReMM SLERP 13B |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages | no suitable model | 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 | no suitable model | no suitable model |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass | no suitable model | no suitable model |
Cheapest model for each capability
| You need | Recursive | Undi95 |
|---|---|---|
| Any model | none listed | ReMM SLERP 13B ($0.42) |
| With tool calling | none listed | none listed |
| With image input | none listed | none listed |
| With reasoning mode | none listed | none listed |
| 128K+ context | none listed | none listed |
| 1M+ context | none listed | none listed |
Line-up by type and price tier
| Model type | Recursive | Undi95 |
|---|---|---|
| text->text | 1 | 1 |
| Price per 1M (3:1 blend) | Recursive | Undi95 |
|---|---|---|
| Free | 1 | 0 |
| Under $0.50 | 0 | 1 |
| $0.50 – $3 | 0 | 0 |
| $3 – $10 | 0 | 0 |
| $10 and up | 0 | 0 |
Frequently asked questions
Which has more models, Recursive or Undi95?
Neither — both list 1 models.
Which provider has the longest context window?
Recursive: Recursive's longest is Recursive: Flint (free) at 262K tokens; Undi95's is ReMM SLERP 13B at 6K.
Do Recursive or Undi95 offer free models?
Recursive: 1 free model (e.g. Recursive: Flint (free)). Undi95: none.
Which provider has models that can read images?
Recursive: 0 of 1 models accept images. Undi95: 0 of 1.