JT-4.1 Flash 236B A21B Non-Reasoning

Pricing & Specs API
Free REST API for prices, specs and benchmarks
JT-4.1 Flash 236B A21B Non-Reasoning is Jt's language model. A large mixture-of-experts LLM from China Mobile with 236B total and 21B active parameters, tuned for fast non-reasoning responses.
Specifications
Canonical IDjt-4-1-flash-236b-a21b-non-reasoning
TypeLanguage
StatusActive
CreatorJt
Input ModalitiesText
Output ModalitiesText
Parameters236B
Benchmarks
Intelligence Index
#97
Coding Index
#64
GPQA
#110
HLE
#154
Time to First Token
#172
LCR
#131
Output TPS
#399

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 JT-4.1 Flash 236B A21B Non-Reasoning, ranked by cheapest on-demand price. The model needs about 566 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
p4de.24xlargeAWS8× A100640 GB$27.45/hr
Standard_ND96amsr_A100_v4Azure8× NVIDIA A100 (80GB)640 GB$32.77/hr
g7e.48xlargeAWS8× RTX PRO Server 6000768 GB$33.14/hr
7 more instances can run JT-4.1 Flash 236B A21B Non-Reasoning
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
JT-4.1 Flash 236B A21B Non-Reasoning————Current
JT Flash 35B————Available

Other Models

ModelTierReleasedContextInput / 1MOutput / 1M
JT-35B-FlashMini————
JT-MINIMini————

Model IDs

jt-4-1-flash-236b-a21b-non-reasoning