BazaarLinkBazaarLink
Sign in

Beam API Pricing & Quick Start

IntelligenceSpeedInput PriceOutput PriceFirst-token latency
#122 / 696
30
Artificial Analysis Intelligence Index
#12 / 372
329.6
Output tokens per second (median)
#244 / 444
$0.00NT$ 0
USD / 1M tokens
#207 / 444
$0.00NT$ 0
USD / 1M tokens
#33 / 372
0.79s
Time to first token (AA median)

Hosts & performance

Several hosts run this model. BazaarLink picks one by speed and stability and switches to the next if a host has trouble. The price is the same whichever host serves your request.

Loading host data…

Data: BazaarLink request statistics (refreshed every 5 minutes); hosts with too few requests use public monitoring data. Individual host prices are not shown.

High-performance AI language model, available via BazaarLink with USD billing (TWD-quoted).

Providerreflection
Released—
Model IDreflection/beam

Technical specifications

Context window
1M tokens
Reasoning
—
Input → Output
TextText

Pricing comparison

BazaarLink retail price alongside AA's observed market standard.

BazaarLink price our site

Input$0.00NT$ 0
Output$0.00NT$ 0
Cache read—
Cache write—
3:1 blended (est.)$0.00NT$ 0
All prices per 1M tokens. Supports TWD credit card / official invoice.

Market reference Artificial Analysis

Input$0.70
Output$2.10
Cache readAA not tracked
Cache writeAA not tracked
3:1 blended—
Our price differs from AA reference by ~100%.
Source: artificialanalysis.ai

Independent benchmarks

Scores below come from Artificial Analysis, an independent third party. BazaarLink does not participate in the testing.

Intelligence 30
Coding
Math
MMLU
GPQA
This modelCategory leader
Overall intelligence
#122out of 696 models
Aggregated across academic benchmarks
Time to first token
#33out of 372 models
AA 全球 p50:0.79 秒
Intelligence
Intelligence
AA composite intelligence index across MMLU-Pro / GPQA / HLE / MATH
30
Top 18%
This model
30
Category leader
58
Median
13

Top 5 — CodingCoding Index leaderboard

1Claude Fable 5.1 (Max, Default Fallback)?/claude-fable-5-182$10 / $50
2Claude Fable 5.1 (Xhigh, Default Fallback)?/claude-fable-5-1-xhigh81$10 / $50
4GPT-5.6 Sol (Xhigh)openai/gpt-5-6-sol-xhigh78$4 / $20
5Claude Opus 5 (Max)anthropic/claude-opus-578$5 / $25
AASource: Artificial Analysis · Independent third-party evaluation; not influenced by BazaarLinkView full evaluation on AA →

Quick Start

Use Beam via BazaarLink API — just change the base_url:

Python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.bazaarlink.ai/v1",
    api_key="sk-bl-YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="reflection/beam",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
TypeScript
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.bazaarlink.ai/v1",
  apiKey: "sk-bl-YOUR_API_KEY",
});

const response = await client.chat.completions.create({
  model: "reflection/beam",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Why use Beam via BazaarLink?

  • ✓Clear usage records and itemized billing
  • ✓OpenAI-compatible API — zero code changes required
  • ✓When an upstream source has a problem, a request can try another available source. If none is available, the request returns an error.
  • ✓Support resources for teams
Try Now← All Models

Frequently Asked Questions

What is Beam?

Beam is an AI language model by reflection, available via BazaarLink's OpenAI-compatible API.

How much does the Beam API cost?

Beam costs $0.00 per 1M input tokens and $0.00 per 1M output tokens when accessed through BazaarLink.

How do I use Beam with the OpenAI SDK?

Set base_url to "https://api.bazaarlink.ai/v1" and use model ID "reflection/beam". All OpenAI SDK methods (chat.completions, embeddings, streaming) work without code changes.

What is the context window for Beam?

Beam supports a context window of 1,048,576 tokens.

Is Beam available for free?

Yes — Beam is available at no cost through BazaarLink's free tier. No credit card required.

Relay integrity checks

Tested endpoints
1 runs
Independent hosts
1
Model-family fingerprint match
0%
Anomalies detected
1 runs
Data range
past 90 days

BazaarLink Probe verifies endpoints that claim to serve this model and flags behavior that differs from the reference baseline.

View the full integrity report →

Related models and links

More from this provider: reflection

Beam FreeDeepSeek V4.1 Flash 1017Qwen3.8 MaxDeepSeek V4 FlashGLM 5V TurboDeepSeek V4 Pro
ModelsAPI documentationAPI latency probe
Support
Support
Hi! How can we help you?
Send a message and we'll get back to you soon.