The Orchestrator › Models › Reflection
Reflection: Beam 1.0 (Free)
Beam is Reflection’s reasoning model for coding and agentic workflows, combining strong coding capabilities with fast, low-latency inference.
Specifications
| Provider | Reflection |
| Model ID | reflection/beam-free |
| Context window | 1.0M tokens (1,048,576) |
| Modalities | text → text |
| Tokenizer | — |
| Router sources | Vercel AI Gateway |
| Released | 2026-10-16 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | Vercel AI Gateway | reflection/beam-free | Free | Free | 1.0M |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | Free | Free | 1.0M |
Capabilities
Agentic tool useStructured outputs1M+ context windowControllable reasoning
Supported parameters
max_tokens, temperature, stop, tools, tool_choice, reasoning, include_reasoning, response_format, structured_outputs