Reflection: Beam 1.0 501B A23B
Beam 1.0 501B A23B is a reasoning model from Reflection released on Oct 5, 2026. It reads text and writes text, with a 1.05M token context window and up to 131K tokens per reply.
Show moreShow less
It costs $0.25 per million input tokens and $1 per million output tokens. Cached input bills at $0.25, 0% less than fresh input.
It supports tool calling, structured JSON output and prompt caching, and its weights are open, so you can host it yourself.
10 providers serve it, including Nebius Token Factory, Together AI and Vercel AI Gateway.
- Modalities
- In / out price
- $0.25 / $1 per 1M
- Context
- 1.05M
- Max output
- 131K
- Released
- Oct 5, 2026
- Knowledge cutoff
- Jun 2026
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
Beam 1.0 501B A23B pricing
USD, as listed on Oct 22, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $0.25 / 1M tokens | |
|---|---|---|
| Output | $1 / 1M tokens | |
| Cached input (read) | $0.25 / 1M tokens | 0% off input |
Beam 1.0 501B A23B providers
10 providers serve it, including Nebius Token Factory, Together AI and Vercel AI Gateway. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| Reflection First party | $0 | $0 | $0 | 1.05M | 131K |
| Nebius Token Factory | $0.25 | $1 | $0.25 | 1.05M | 131K |
| Together AI | $0.40 | $1.20 | $0.04 | 1.05M | 131K |
| Vercel AI Gateway | n/a | n/a | n/a | 1.05M | 131K |
| Kilo Gateway | $0.25 | $1 | $0.05 | 1.05M | 944K |
| CoreWeave | $0.30 | $1 | $0.04 | 1.05M | 1.05M |
| Eden AI | $0.40 | $1.20 | $0.04 | 1.05M | 131K |
| NanoGPT | $0.50 | $1.50 | $0.05 | 1.05M | 131K |
| Cloudflare AI Gateway | n/a | n/a | n/a | 262K | 131K |
| Ollama Cloud | n/a | n/a | n/a | 1.05M | 131K |
What Beam 1.0 501B A23B costs per month
Pick a workload close to yours or type your own volumes.
Supported request parameters
What you can set when you call Beam 1.0 501B A23B through an OpenAI compatible API.
- Tools
tools - Structured outputs
structured_outputs - Reasoning
reasoning - Temperature
temperature
Alternatives to Beam 1.0 501B A23B
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- 66K context
Reads text, images, audio and video. Tool calling, structured output, reasoning.
by qwenSep 22, 2025$0.25/M input tokens$0.97/M output tokens
- 164K context
Reads text. Tool calling, structured output, reasoning. Served by 13 providers.
by deepseekAug 21, 2025$0.25/M input tokens$0.95/M output tokens13 providers
- 1M context
Reads text. Tool calling, reasoning. Served by 2 providers.
by minimaxJan 15, 2025$0.20/M input tokens$1.10/M output tokens2 providers
- 66K context
Reads text. Tool calling, structured output, reasoning. Served by 5 providers.
by qwenSep 1, 2025$0.15/M input tokens$1.20/M output tokens5 providers
- 256K context
Reads text and images. Tool calling, reasoning.
by bytedanceNov 11, 2025$0.17/M input tokens$1.12/M output tokens
- Index 11.3
Reads text, images and files. Tool calling, structured output, reasoning. Served by 15 providers.
by mistralaiMar 16, 2026262K context$0.15/M input tokens$0.60/M output tokens15 providers
More from Reflection
- 1.05M context
Reads text. Tool calling, reasoning.
by reflectionAug 26, 2025$0/M input tokens$0/M output tokens
Beam 1.0 501B A23B questions
How much does the Beam 1.0 501B A23B API cost?
$0.25 per million input tokens and $1 per million output tokens, with cached input at $0.25. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of Beam 1.0 501B A23B?
1,048,576 tokens of input, and it can write up to 131,072 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve Beam 1.0 501B A23B?
10 providers serve it, including Nebius Token Factory, Together AI and Vercel AI Gateway. Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does Beam 1.0 501B A23B support tool calling?
Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.
Is Beam 1.0 501B A23B open source?
Its weights are published, so you can run it on your own hardware or a cloud of your choice. Read the license before commercial use.
When was Beam 1.0 501B A23B released?
Oct 5, 2026, with training data up to Jun 2026.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 22, 2026. The summary is written from these facts.