Beam 1.0 501B A23B
by ReflectionChat
Reflection's Apache 2.0 open-weight text model with 501.3B total and 23.4B active parameters, built for coding, reasoning and tool use. It supports a shared 1,048,576-token context window, up to 131,072 output tokens, JSON mode and structured output. Reasoning is always enabled with low, medium, high, xhigh and max effort; NanoGPT defaults to max. Knowledge cutoff: June 30, 2026.
- Context
- 1.05M tokens
- Max output
- 131,072 tokens
- Released
- 2026-10-16
- Weights
- Open
reflection/beam-1-0
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2026-10-16
- Weights
- Open
- Input
- Text
- Output
- Text
- Context window
- 1,048,576 max across endpoints
- Max output
- 131,072
- Providers
- 1 + 1 gateway, not counted as providers
- Epoch Capabilities Index
- not evaluated
- Direct price range
- $1.30 in · $4.30 out per 1M tokens · from its one provider
More details
- Last updated
- 2026-10-16
- Knowledge cutoff
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel toolsunknown
- Structured output
- Reasoning
- Image input
- PDF input
- Audio input
- Audio outputunknown
- Video input
- Prompt caching
- Web searchunknown
- Computer useunknown
- System messagesunknown
- Assistant prefillunknown
- Temperatureunknown
- Streamingunknown
- Attachments
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Price history
Atom feedNo change since 19 Oct 2026. The cheapest direct price has been $1.30 in / $4.30 out per 1M tokens at Baseten on every data refresh since then.
Tracked from 19 Oct 2026. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON
Cost calculator
Loading endpoints…
Similarly priced models
Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).
| Model | Blended/1M | In/1M | Out/1M | Context | vs Beam 1.0 501B A23B |
|---|---|---|---|---|---|
| Nova 2 LiteAmazon | $0.667 | $0.30 | $2.50 | 1M | +0% |
| Aya Expanse 32BCohere | $0.667 | $0.50 | $1.50 | 128K | +0% |
| Nano BananaGoogle | $0.667 | $0.30 | $2.50 | 32.8K | +0% |
| ring-2.6-1tinclusionAI | $0.667 | $0.30 | $2.50 | 262K | +0% |
| Devstral 2Mistral AI | $0.667 | $0.40 | $2.00 | 262K | +0% |
| Magistral SmallMistral AI | $0.667 | $0.50 | $1.50 | 262K | +0% |
| Magistral Small 2506Mistral AI | $0.667 | $0.50 | $1.50 | 128K | +0% |
| Mistral Code Agent LatestMistral AI | $0.667 | $0.40 | $2.00 | 256K | +0% |
More from Reflection
Newest Reflection models in the catalogue. All Reflection models
| Model | Released | Context | Listed price |
|---|---|---|---|
| Beam 1.0 | 2025-08-26 | 1.05M | unpriced |