Overview

Model specifications

Context: 1,048,576 tokens
Maximum output: 131,072 tokens
Architecture: text->text
Tokenizer: Other
Knowledge cutoff: 2026-06-30
Moderated: No

OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input: $0.25
Output: $1
Cache read: $0.05

API

Model configuration

Reasoning

Reasoning required: Yes
Default parameters: max
Capabilities: max, xhigh, high, medium, low

API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body 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!"}]}'

Capabilities

Input → Output

Input

text

Output

text

Reasoning

No · max · xhigh · high · medium · low

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Available providers

4 providers

Checked: October 22, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

Nebius

fp8

Context: 1.0M
Maximum output: 131K
Input: $0.25
Output: $1
Cache read: $0.05
Cache write: Not provided

CoreWeave

fp4

Context: 1.0M
Maximum output: 944K
Input: $0.3
Output: $1
Cache read: $0.04
Cache write: Not provided

BaseTen

fp4

Context: 1.0M
Maximum output: 131K
Input: $0.4
Output: $1.2
Cache read: $0.04
Cache write: Not provided

Together

Not provided

Context: 1.0M
Maximum output: 131K
Input: $0.4
Output: $1.2
Cache read: $0.04
Cache write: Not provided

Reflection: Beam 1.0 501B A23B