per 1M tokens
Reflection: Beam 1.0 501B A23B
reflection/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...
Price
per 1M tokens
Providers
Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.
| Provider | Tag | Quant | Input | Output | Context | Uptime | Status | Source |
|---|---|---|---|---|---|---|---|---|
| Nebius | nebius/fp4 | fp4 | $0.25/1M | $1/1M | 1.0M | 100% | Live | openrouter-endpoints |
| CoreWeave | coreweave/fp4 | fp4 | $0.3/1M | $1/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Io Net | — | fp4 | $0.35/1M | $1.12/1M | 1.0M | — | Listed | ionet |
| BaseTen | baseten/fp4 | fp4 | $0.4/1M | $1.2/1M | 1.0M | — | Live | openrouter-endpoints |
| DigitalOcean | digitalocean | — | $0.4/1M | $1.2/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Together | — | — | $0.4/1M | $1.2/1M | 1.0M | — | Listed | together |
| Together | together | — | $0.4/1M | $1.2/1M | 1.0M | 100% | Live | openrouter-endpoints |
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$1.25 at list price for this workload
Cache
per 1M tokens
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.25/1M | $1/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-10-16 | token | $0.25 | $1 | Not published— |
| 2026-10-17 | token | $1 | $3 | Not published— |
| 2026-10-18 | token | $1 | $3 | Not published— |
| 2026-10-19 | token | $1 | $3 | Not published— |
| 2026-10-20 | token | $0.3 | $1 | Not published— |
| 2026-10-21 | token | $0.3 | $1 | Not published— |
| 2026-10-22 | token | $0.25 | $1 | Not published— |
| 2026-10-23 | token | $0.25 | $1 | Not published— |
| 2026-10-24 | token | $0.25 | $1 | Not published— |
| 2026-10-25 | token | $0.25 | $1 | Not published— |
| 2026-10-26 | token | $0.25 | $1 | Not published— |
| 2026-10-27 | token | $0.25 | $1 | Not published— |
| 2026-10-28 | token | $0.25 | $1 | Not published— |
| 2026-10-29 | token | $0.25 | $1 | Not published— |
| 2026-10-30 | token | $0.25 | $1 | Not published— |
Alternatives
- ByteDance Seed: Seed 1.6$0.25/1M · Compare
- ByteDance Seed: Seed-2.0-Lite$0.25/1M · Compare
- ByteDance/Seed-1.8$0.25/1M · Compare
- Claude 3 Haiku$0.25/1M · Compare
- deepseek-ai/DeepSeek-V3.1$0.25/1M · Compare
- DeepSeek: DeepSeek V3.1$0.25/1M · Compare
Parameters (20)
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Call this model
OpenRouter id reflection/beam-1.0-501b-a23b. InferenceList does not send the request.
curl
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"reflection/beam-1.0-501b-a23b","messages":[{"role":"user","content":"Hello"}]}'
JavaScript
await fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "reflection/beam-1.0-501b-a23b",
messages: [{ role: "user", content: "Hello" }],
}),
});
Python
import os, json, urllib.request
req = urllib.request.Request(
"https://openrouter.ai/api/v1/chat/completions",
data=json.dumps({"model": "reflection/beam-1.0-501b-a23b", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())