|
Google Vertex AI
vertex
|
Gemini 2.5 Flash-Lite
gemini-2.5-flash-lite
|
Fast chat and routing
Current runtime target in the Coolbits model registry.
|
8,192 tokens |
750 / 3,000
blended: 1,312 cbT
|
$0.0750 / $0.3000
|
$0.1312
75% input / 25% output
|
2026-03-08 |
|
Google Vertex AI
vertex
|
Gemini 2.5 Pro
gemini-2.5-pro
|
Deep analysis
Current runtime target in the Coolbits model registry.
|
8,192 tokens |
35,000 / 70,000
blended: 43,750 cbT
|
$3.5000 / $7.0000
|
$4.3750
75% input / 25% output
|
2026-03-08 |
|
OpenAI
openai
|
GPT-4.1 mini
gpt-4.1-mini
|
Light reasoning and routing
Server-side only; shown as the current provider target, not a browser key flow.
|
16,384 tokens |
1,500 / 6,000
blended: 2,625 cbT
|
$0.1500 / $0.6000
|
$0.2625
75% input / 25% output
|
2026-03-08 |
|
OpenAI
openai
|
GPT-4.1
gpt-4.1
|
General reasoning
Server-side only; managed or BYOK billing is resolved inside the backend layer.
|
8,192 tokens |
50,000 / 150,000
blended: 75,000 cbT
|
$5.0000 / $15.0000
|
$7.5000
75% input / 25% output
|
2026-03-08 |
|
Anthropic
anthropic
|
Claude Sonnet 4
claude-sonnet-4-20250514
|
Balanced reasoning and writing
Current runtime target in the Coolbits model registry.
|
8,192 tokens |
30,000 / 150,000
blended: 60,000 cbT
|
$3.0000 / $15.0000
|
$6.0000
75% input / 25% output
|
2026-03-08 |
|
Anthropic
anthropic
|
Claude 3.5 Haiku
claude-3-5-haiku-20241022
|
Fast tasks
Current runtime target in the Coolbits model registry.
|
8,192 tokens |
8,000 / 40,000
blended: 16,000 cbT
|
$0.8000 / $4.0000
|
$1.6000
75% input / 25% output
|
2026-03-08 |
|
xAI
xai
|
Grok 3 Mini Fast
grok-3-mini-fast
|
Fast reasoning
Current runtime target in the Coolbits model registry.
|
8,192 tokens |
3,000 / 5,000
blended: 3,500 cbT
|
$0.3000 / $0.5000
|
$0.3500
75% input / 25% output
|
2026-03-08 |
|
xAI
xai
|
Grok 3
grok-3
|
Deep analysis
Current runtime target in the Coolbits model registry.
|
16,384 tokens |
30,000 / 150,000
blended: 60,000 cbT
|
$3.0000 / $15.0000
|
$6.0000
75% input / 25% output
|
2026-03-08 |