Pricing
Frontier performance,
without the frontier price
Frontier performance at a fundamentally lower cost
Hal 1.0
Maximum
Capability
Capability
Designed for complex
reasoning, agent workflows,
and software tasks.
Pricing
input Tokens
$2.75 / MTok
output Tokens
$13.75 / MTok
Cost optimization
Significant savings with prompt caching (up to 90%) on repeated prompts.
When to use Hal
Hal is best suited for:
- Item A
- Item B
- Item C
Equivilancy
Comparable to Opus 4.7
and GPT-5.5
Clarke 1.0
Balanced
Performance
Performance
Strong performance with the best balance of speed and cost.
Pricing
input Tokens
$1.50 / MTok
output Tokens
$7.00 / MTok
Cost optimization
Significant savings with prompt caching (up to 90%) on repeated prompts.
When to use Hal
Hal is best suited for:
- Item A
- Item B
- Item C
Equivilancy
Comparable to Sonnet 4.6
and GPT-5.4
Tycho 1.0
High-efficiency
Scale
Scale
Ultra-efficient inference for high-throughput applications, early development, and lightweight agents.
Pricing
input Tokens
$0.50 / MTok
output Tokens
$2.25 / MTok
Cost optimization
Significant savings with prompt caching (up to 90%) on repeated prompts.
When to use Hal
Hal is best suited for:
- Item A
- Item B
- Item C
Equivilancy
Comparable to Opus 4.7
and GPT-5.5
A better cost floor for
production AI
Monthly token volume:
320M Tokens
Model tier
Anthropic opus 4.6
$3,200
/ month
OPENAI GPT-5.4
$3,200
/ month
Radium HAL 1.0
$1,600
/ month
Anthropic sonnet 4.6
$3,200
/ month
OPENAI GPT-5.4
$3,200
/ month
Radium Clarke 1.0
$1,600
/ month
Anthropic Haiku 4.5
$3,200
/ month
OPENAI GPT-5.4 Mini
$3,200
/ month
Radium Tycho 1.0
$1,600
/ month
Start running inference
on Radium
The economics of enterprise AI
Understanding
the hidden
costs of AI
Discover TokenomicsSwitching
from OpenAI
or Anthropic
Compare RadiumArticles
Resources
Resources for teams evaluating, integrating, and operating Radium
View All Resources
Get Started
One line of code to switch.
A different class of performance.
Swap OpenAI for Radium in your API call. That's it.