Fireworks lists 1 models and Reflection 1. Reflection is cheaper on a typical model ($1.50 per 1M tokens median). Below: line-up, price tiers, the cheapest model for each capability, and what each costs for five real workloads.
| Fireworks | Reflection | |
|---|---|---|
| Models listed | 1 | 1 |
| Models with published pricing | 1 | 1 |
| Typical price (median, 3:1 blend per 1M) | $6.00 | $1.50 |
| Cheapest paid model | Fireworks: Ember-1 ($6.00) | Reflection: Beam 1.0 501B A23B ($1.50) |
| Longest context | Fireworks: Ember-1 (1.0M) | Reflection: Beam 1.0 501B A23B (1.0M) |
| Free models | 0 | 0 |
| Newest model | Fireworks: Ember-1 (2026-09-24) | Reflection: Beam 1.0 501B A23B (2026-10-16) |
| 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) | Fireworks | Reflection |
|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation | $525 with Fireworks: Ember-1 | $135 with Reflection: Beam 1.0 501B A23B |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages | $510 with Fireworks: Ember-1 | $150 with Reflection: Beam 1.0 501B A23B |
| Coding / tool-using agent 2,000 tasks — each a multi-step task with tool calls and file context | $540 with Fireworks: Ember-1 | $156 with Reflection: Beam 1.0 501B A23B |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page | $330 with Fireworks: Ember-1 | $98.00 with Reflection: Beam 1.0 501B A23B |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass | $165 with Fireworks: Ember-1 | $53.00 with Reflection: Beam 1.0 501B A23B |
| You need | Fireworks | Reflection |
|---|---|---|
| Any model | Fireworks: Ember-1 ($6.00) | Reflection: Beam 1.0 501B A23B ($1.50) |
| With tool calling | Fireworks: Ember-1 ($6.00) | Reflection: Beam 1.0 501B A23B ($1.50) |
| With image input | Fireworks: Ember-1 ($6.00) | none listed |
| With reasoning mode | Fireworks: Ember-1 ($6.00) | Reflection: Beam 1.0 501B A23B ($1.50) |
| 128K+ context | Fireworks: Ember-1 ($6.00) | Reflection: Beam 1.0 501B A23B ($1.50) |
| 1M+ context | Fireworks: Ember-1 ($6.00) | Reflection: Beam 1.0 501B A23B ($1.50) |
| Model type | Fireworks | Reflection |
|---|---|---|
| text+image->text | 1 | 0 |
| text->text | 0 | 1 |
| Price per 1M (3:1 blend) | Fireworks | Reflection |
|---|---|---|
| Free | 0 | 0 |
| Under $0.50 | 0 | 0 |
| $0.50 – $3 | 0 | 1 |
| $3 – $10 | 1 | 0 |
| $10 and up | 0 | 0 |
Reflection is cheaper on a typical model: a median of $1.50 per 1M tokens (3:1 input/output) against $6.00 for Fireworks. The cheapest paid models are Fireworks: Ember-1 at $6.00 and Reflection: Beam 1.0 501B A23B at $1.50.
It depends on the job: both list 1 models, Reflection the lower typical price. The workload table above shows which wins for chat, RAG, agents, batch jobs and long documents.
Neither — both list 1 models.
It is a tie: Fireworks's longest is Fireworks: Ember-1 at 1.0M tokens; Reflection's is Reflection: Beam 1.0 501B A23B at 1.0M.
Neither lists a free model; both are pay-per-token.
Fireworks: 1 of 1 models accept images. Reflection: 0 of 1.