Is Reflection better than Stealth?
It depends on the job: Stealth offers the broader line-up (1 models vs 3). The workload table above shows which wins for chat, RAG, agents, batch jobs and long documents.
Reflection vs Stealth
Reflection lists 1 models and Stealth 3. Below: line-up, price tiers, the cheapest model for each capability, and what each costs for five real workloads.
At a glance
| Reflection | Stealth | |
|---|---|---|
| Models listed | 1 | 3 |
| Models with published pricing | 1 | 3 |
| Typical price (median, 3:1 blend per 1M) | $1.50 | n/a |
| Cheapest paid model | Reflection: Beam 1.0 501B A23B ($1.50) | n/a |
| Longest context | Reflection: Beam 1.0 501B A23B (1.0M) | Ox Alpha (1.0M) |
| Free models | 0 | 3 |
| Newest model | Reflection: Beam 1.0 501B A23B (2026-10-16) | Space Bunny Alpha (2026-09-23) |
| Price changes in the last 90 days | 0 | 0 |
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) | Reflection | Stealth |
|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation | $135 with Reflection: Beam 1.0 501B A23B | no suitable model |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages | $150 with Reflection: Beam 1.0 501B A23B | no suitable model |
| Coding / tool-using agent 2,000 tasks — each a multi-step task with tool calls and file context | $156 with Reflection: Beam 1.0 501B A23B | no suitable model |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page | $98.00 with Reflection: Beam 1.0 501B A23B | no suitable model |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass | $53.00 with Reflection: Beam 1.0 501B A23B | no suitable model |
Cheapest model for each capability
| You need | Reflection | Stealth |
|---|---|---|
| Any model | Reflection: Beam 1.0 501B A23B ($1.50) | none listed |
| With tool calling | Reflection: Beam 1.0 501B A23B ($1.50) | none listed |
| With image input | none listed | none listed |
| With reasoning mode | Reflection: Beam 1.0 501B A23B ($1.50) | none listed |
| 128K+ context | Reflection: Beam 1.0 501B A23B ($1.50) | none listed |
| 1M+ context | Reflection: Beam 1.0 501B A23B ($1.50) | none listed |
Line-up by type and price tier
| Model type | Reflection | Stealth |
|---|---|---|
| text+image+video->text | 0 | 2 |
| text+image->text | 0 | 1 |
| text->text | 1 | 0 |
| Price per 1M (3:1 blend) | Reflection | Stealth |
|---|---|---|
| Free | 0 | 3 |
| Under $0.50 | 0 | 0 |
| $0.50 – $3 | 1 | 0 |
| $3 – $10 | 0 | 0 |
| $10 and up | 0 | 0 |
Frequently asked questions
Which has more models, Reflection or Stealth?
Stealth: Reflection lists 1 models and Stealth lists 3.
Which provider has the longest context window?
It is a tie: Reflection's longest is Reflection: Beam 1.0 501B A23B at 1.0M tokens; Stealth's is Ox Alpha at 1.0M.
Do Reflection or Stealth offer free models?
Reflection: none. Stealth: 3 free models (e.g. Ox Alpha).
Which provider has models that can read images?
Reflection: 0 of 1 models accept images. Stealth: 3 of 3.