Beam 1.0 501B A23BOpen weights
Reflection · released 2026-10-05
No price from the maker itself is on record for Beam 1.0 501B A23B. The lowest of 13 providers is Kilo Gateway: $0.25 per 1M input tokens and $1 per 1M output tokens (as of 2026-11-12). Context window: 1.05M tokens, up to 131K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| ReflectionOfficialBeam-1.0-501B-A23B | $0 | $0 | $0 | Official | Official docs |
KKilo GatewayLowestreflection/ | $0.25 | $1 | $0.05 | Lowest | Official docs |
 Nebius Token Factoryreflection/ | $0.25 | $1 | $0.05 | Official docs | |
 OpenRouterreflection/ | $0.3 | $1 | $0.04 | Official docs | |
 CoreWeavereflection/ | $0.3 | $1 | $0.04 | Official docs | |
EEden AItogether_ | $0.4 | $1.2 | $0.04 | Official docs | |
 Together AIreflection/ | $0.4 | $1.2 | $0.04 | Official docs | |
NNanoGPTreflection/ | $0.5 | $1.5 | $0.05 | Official docs | |
 Cloudflare AI Gatewayreflection-ai/ | $0 | $0 | $0 | Official docs | |
 OpenCodebeam-free | $0 | $0 | $0 | Official docs | |
OOpenCode Gobeam-free | $0 | $0 | $0 | Official docs | |
 Vercel AI Gatewayreflection/ | $0 | $0 | — | Official docs |
2 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| Vercel AI Gatewayreflection/ | $0 | $0 | — | Official docs | |
 Ollama Cloudbeam | — | — | — | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows
Description from models.dev.
Specs
- Type
- Text
- Context
- 1.05M
- Max output
- 131K
- Input
- Text
- Output
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2026-06-30
- Open weights
- Yes
- Released
- 2026-10-05
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.