Beam 1.0
wandb/reflection/Beam-1.0-501B-A23B · family beam · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$1.50
Blended $/1M (3:1)
$1
Input $/1M
$3
Output $/1M
$4.00
1M in + 1M out
$0.1 −90%
Cache read $/1M
#5005 of 8,489
Cheapest rank
- Provider
- CoreWeave (
wandb) - Kind
- text (outputs text)
- Context
- 1,048,576 tokens
- Max output
- 1,048,576 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“Beam 1.0” is offered by 2 providers — cheapest-effective first. Vercel AI Gateway is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Vercel AI Gateway | free | free | $0.00 | 1M |
| CoreWeave (this) | $1 | $3 | $1.50 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at CoreWeave and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"reflection/Beam-1.0-501B-A23B","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):