Beam 1.0 501B A23B
Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows.
Beam-1.0-501B-A23BReleased 16 Oct 2026 (5 weeks ago)Pricing
List prices at W&B Inference, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.30 | $1.00 | |
| Cached input 87% off input | $0.04 | 87% off input |
What it costs a month
At W&B Inference list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$142
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$118
- Coding agent1,000 requests a day, 40K in / 2K out, cached$202
- Overnight batch20,000 requests a day, 4K in / 0.4K out$960
Where to run it
2 hosts serve Beam 1.0 501B A23B. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
W&B InferenceInference Beam-1.0-501B-A23B | $0.30 / $1.00 | Beam-1.0-501B-A23B | |
Together AIInference Beam-1.0-501B-A23B | $0.40 / $1.20 +26% vs headline | Beam-1.0-501B-A23B |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Features
- Prompt caching
- Open weights
- License: Apache-2.0Runs in about 1203 GB of GPU memory
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than W&B Inference.
Smaller Independent models
No cheaper Independent model keeps its key capabilities.
Other frontier labs
- 3% less
- 58% less
- 58% less
- 45% less
Open-weight picks
- 8% less
- 26% less
- 46% less
- 47% less
Call it
Using W&B Inference's API.
from litellm import completion
response = completion(
model="wandb/Beam-1.0-501B-A23B",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Beam 1.0 501B A23B cost?
On W&B Inference, Beam 1.0 501B A23B costs $0.30 per million input tokens and $1.00 per million output tokens. Cached input costs $0.04 per million tokens.
Which APIs offer Beam 1.0 501B A23B?
Beam 1.0 501B A23B runs on 2 APIs: W&B Inference and Together AI.
What is Beam 1.0 501B A23B's context window?
1M tokens, with up to 1M tokens in one reply.
Is Beam 1.0 501B A23B being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Beam 1.0 501B A23B?
Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (3% less), Claude Haiku 5.5 on Anthropic (58% less) and MiMo V2.6 Pro on GMI Cloud (8% less). Savings are on a mix of 3 input tokens to 1 output token.
When was Beam 1.0 501B A23B released?
Independent released it on 16 Oct 2026.
What is Beam 1.0 501B A23B's API model id?
Use Beam-1.0-501B-A23B with W&B Inference.
Sources
Raw catalog entry for Beam-1.0-501B-A23B on W&B Inference
{
"cache_read_input_token_cost": 4e-8,
"input_cost_per_token": 3e-7,
"litellm_provider": "wandb",
"max_input_tokens": 1049000,
"mode": "chat",
"output_cost_per_token": 0.000001,
"source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": false
}