Beam 1.0 API
Nanogpt's Beam 1.0, through an OpenAI-compatible API. Providers quote it on an open exchange, and each request goes to the offer with the lowest estimated charge that meets your rules.
- Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
- The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send beam-1.0 as the model.
- Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.
Facts
- Model name
- beam-1.0
- Maker
- Nanogpt
- Context window
- 1M tokens
- Input price
- $0.500 per million tokens
- Output price
- $1.501 per million tokens
- Providers
- 1 independent provider
- Regions
- us
Providers
- Architect: us, $0.500 input and $1.501 output per million tokens, $0.050 cache read per million tokens, 1M tokens of context
Request
curl https://router.inference.ai.exchange/v1/chat/completions \
-H "Authorization: Bearer $LIQUID_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "beam-1.0",
"messages": [{"role":"user","content":"Say hello."}]
}'Questions
- What is Beam 1.0?
- Beam 1.0 is a model from Nanogpt.
- How much does Beam 1.0 cost?
- Offers now ask $0.500 per million input tokens and $1.501 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
- What is the context length of Beam 1.0?
- The largest offer takes 1,048,576 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
- What can Beam 1.0 do?
- Its providers list Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
- What inputs and outputs does Beam 1.0 support?
- Text → Text.
- Which providers serve Beam 1.0?
- 1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.
- How do I call Beam 1.0?
- Send "beam-1.0" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
- When was Beam 1.0 listed?
- The exchange first listed it on 10/17/2026. This is not its release date.