Apriel V1.5 15B Thinker is Servicenow's language model. A 15B reasoning-focused LLM from ServiceNow's Apriel series, designed for enterprise workflow automation and structured thinking tasks.
Specifications
Canonical IDservicenow-apriel-1-5-15b-thinker
TypeLanguage
StatusActive
CreatorServicenow
Input ModalitiesText
Output ModalitiesText
Parameters15B
Benchmarks
Intelligence Index
21.2
#165
Math Index
87.5
#41
MMLU-Pro
0.8
#141
GPQA
0.7
#199
HLE
0.1
#136
LiveCodeBench
0.7
#52
IFBench
0.6
#103
Time to First Token
0.00s
#330
SciCode
0.3
#200
AIME 2025
0.9
#41
LCR
0.2
#273
TerminalBench Hard
0.1
#204
TAU2
0.7
#143
Output TPS
0.0
#454

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Cheapest Instances to Run It

Cloud GPU instances that can host Apriel V1.5 15B Thinker, ranked by cheapest on-demand price. The model needs about 36 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
Standard_NP10sAzureAMD Alveo U250 FPGA (64GB)64 GB$1.65/hreastus
g6e.xlargeAWSL40S45 GB$1.86/hrus-east-1
Standard_NV32as_v4AzureAMD Radeon Instinct MI2564 GB$1.86/hreastus
7 more instances can run Apriel V1.5 15B Thinker
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Apriel V1.5 15B ThinkerCurrent
Apriel V1.6 15B ThinkerAvailable

Model IDs

apriel-v1-5-15b-thinker
servicenow-apriel-1-5-15b-thinker