Beam 1.0 501B A23B
Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...
Model card on Hugging Face- Input / output price
- $0.25 / $1.00 per 1M
- Context
- 1M tokens
- Released
- Oct 16, 2026
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
5 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Nebius nebius/beam-1.0-501b-a23b | $0.25/M | $1.00/M |
IO.net ionet/reflection/Beam-1.0-501B-A23B | $0.3375/M | $1.10/M |
Baseten baseten/beam-1.0-501b-a23b | $0.40/M | $1.20/M |
TogetherAI togetherai/beam-1.0-501b-a23b | $0.40/M | $1.20/M |
OpenRouter openrouter/beam-1.0-501b-a23b | $0.30/M | $1.00/M |
Is a provider down? OpenRouter status
Pricing
Averaged across 5 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $0.34 per 1M
- Average output
- $1.10 per 1M
- Average cache read
- $0.07 per 1M
Cost by volume
Total cost from 0 to 1T tokens on the cheapest and most expensive provider.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better45tokens/sacross providers
Response latency
Lower is better0.5sacross providers
Benchmarks
The Respan Index plus 27 published scores from 4 sources, each linked to where it was published.
39.2/ 100
Respan Index#65 of 167
- 65Beam 1.039.2
- 63Gemini 3 Pro Preview39.5
- 66Claude Sonnet 4.637.3
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveCodeBenchhuggingface.co | 88.3% | huggingface.co | Oct 16, 2026 |
| SWEBench Verifiedhuggingface.co | 81.6% | huggingface.co | Oct 16, 2026 |
| Terminal Bench v2.1huggingface.co | 80.1% | huggingface.co | Oct 16, 2026 |
| SWEBench Multilingualhuggingface.co | 78.3% | huggingface.co | Oct 16, 2026 |
| SWE Bench Pro v2-Hardhuggingface.co | 76.5% | huggingface.co | Oct 16, 2026 |
| SWE Bench Pro v1huggingface.co | 66.1% | huggingface.co | Oct 16, 2026 |
| SciCodehuggingface.co | 49.2% | huggingface.co | Oct 16, 2026 |
| DeepSWE v1.1huggingface.co | 43.3% | huggingface.co | Oct 16, 2026 |
| SWE Atlas Codebase QnAhuggingface.co | 31.8% | huggingface.co | Oct 16, 2026 |
| Terminal-Bench 4.0Vals AI | 4% | Vals AI | Oct 28, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MCP Atlashuggingface.co | 80.8% | huggingface.co | Oct 16, 2026 |
| DeepSearchQA (w/ context management)huggingface.co | 80.5% | huggingface.co | Oct 16, 2026 |
| BrowseComp (w/ context management)huggingface.co | 76.8% | huggingface.co | Oct 16, 2026 |
| APEX-AgentsMercor | 48.8% | Mercor | Oct 31, 2026 |
| AutomationBench (public split)huggingface.co | 39.3% | huggingface.co | Oct 16, 2026 |
| Tau3 Bankinghuggingface.co | 36.1% | huggingface.co | Oct 16, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA Diamondhuggingface.co | 90.6% | huggingface.co | Oct 16, 2026 |
| AA-LCRhuggingface.co | 78.2% | huggingface.co | Oct 16, 2026 |
| LongBench v2huggingface.co | 67.5% | huggingface.co | Oct 16, 2026 |
| HLE (with tools)huggingface.co | 51.1% | huggingface.co | Oct 16, 2026 |
| HLE (no tools)huggingface.co | 36% | huggingface.co | Oct 16, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| AIME 2026huggingface.co | 97.7% | huggingface.co | Oct 16, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| IFBenchhuggingface.co | 79.6% | huggingface.co | Oct 16, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena WebDevLMArena | 1438 Elo · #68 of 116 | LMArena | Nov 9, 2026 |
| LMArena EloLMArena | 1435 Elo · #78 of 172 | LMArena | Nov 9, 2026 |
| LMArena AgentLMArena | -0.0642 · #46 of 59 | LMArena | Nov 8, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| CriPT AAhuggingface.co | 16.3% | huggingface.co | Oct 16, 2026 |
Apps
Use Beam 1.0 501B A23B in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Beam 1.0 501B A23B FAQ
Short answers, built from the data on this page.
Beam 1.0 501B A23B is a model from Reflection AI, released on Oct 16, 2026. Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...
On the Respan gateway, input starts at $0.25 per 1M tokens on Nebius, and output starts at $1.00 per 1M tokens on Nebius and OpenRouter, after gateway discounts. Averaged across its 5 providers, it costs $0.34 per 1M input tokens and $1.10 per 1M output tokens.
Beam 1.0 501B A23B is available through 5 providers: Nebius, IO.net, Baseten, TogetherAI, and OpenRouter.
Beam 1.0 501B A23B accepts up to 1M tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "beam-1.0-501b-a23b". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Beam 1.0 501B A23B scores 39.2 out of 100 on the Respan Index v1.1, ranking #65 of 167 models. By category: Coding 16.9, Agents 55.8, Reasoning 38.7, Knowledge & language 35.4 (estimated), and Human preference 52.0. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.
Beam 1.0 501B A23B has 27 published benchmark scores, including LiveCodeBench 88.3%, MCP Atlas 80.8%, and GPQA Diamond 90.6%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.