BReflection: Beam 1.0 501B A23B
reflection/beam-1-0-501b-a23bBeam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows.
Modalities
In / out per 1M$1.00 / $3.00
Context1M
ReleasedOct 16, 2026
Providers
4 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
 Basetenfp4 | $1.30 | $4.30 | $0.13 | 0.29s | 478 tps | 100% |
| $0.40 | $1.20 | $0.04 | 0.11s | 154 tps | 99.52% | |
 CoreWeavefp4 | $1.00 | $3.00 | $0.10 | — | — | 96.62% |
| $0.25 | $1.00 | Variable | 0.66s | 132 tps | 96.04% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Beam 1.0 501B A23B in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Beam 1.0 501B A23B costs pay-as-you-go elsewhere, not what you pay here.
Input
$1.00
per 1M tokens
Output
$3.00
per 1M tokens
Cache read
$0.10
per 1M cached tokens
Included in every pass
Beam 1.0 501B A23B is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s20.0s40.0s60.0s80.0s
Oct 16, 3 PMOct 16, 11 PMOct 17, 7 AMOct 17, 3 PMOct 17, 11 PMOct 18, 7 AMOct 18, 3 PMOct 18, 11 PMOct 19, 7 AM
Nebius Token Factory Together Baseten CoreWeave
0 tok/s500 tok/s1000 tok/s1500 tok/s2000 tok/s
Oct 16, 3 PMOct 16, 11 PMOct 17, 7 AMOct 17, 3 PMOct 17, 11 PMOct 18, 7 AMOct 18, 3 PMOct 18, 11 PMOct 19, 7 AM
Nebius Token Factory Together Baseten CoreWeave
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.88%
Oct 16, 9:00 AMNow
Availability over the last 24 hoursAvailability 99.98%
100% 98% 97% 95%
Oct 18, 9:00 AMNow
Apps
Tools that most often run Beam 1.0 501B A23B, by tokens this week.
Activity
72.2B tokens processed market-wide in the last month.
010.0B20.0B30.0B40.0B
Oct 16Oct 17Oct 18Oct 19
Tokens
FAQ
Which model id do I use for Beam 1.0 501B A23B?
reflection/beam-1.0-501b-a23b. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Beam 1.0 501B A23B hold?
1,048,576 tokens per request, of which up to 943,718 can be the response.
What can it accept and return?
Input: text. Output: text.
What does Beam 1.0 501B A23B cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $1.00 per 1M input tokens and $3.00 per 1M output tokens.
How current is its knowledge?
Training data runs to Jun 2026. Anything later has to come from your prompt or a tool call.
Who built Beam 1.0 501B A23B?
Reflection, in the Beam family.
Explore
Other models your pass can call.
