About
Ling-2.6-1T is an instant (instruct) model from inclusionAI and the company’s trillion-parameter flagship, designed for real-world agents that require fast execution and high efficiency at scale. It uses a “fast...
Related Models
Pricing
Input
$0.07
per 1M tokens
Output
$0.63
per 1M tokens
Blended
$0.21
per 1M tokens
Cheaper than 68% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.21
Monthly
$6.38
vs. Similar Models
Hy3-preview (Non-reasoning)Q:0.0
$0.20-6%
GPT-5.2 (Non-reasoning)Q:-0.1
$4.81+2165%
StepFun: Step 3.5 FlashQ:-0.1
$0.14-33%
DeepSeek V3.1 Terminus (Reasoning)Q:+0.2
$1.91+801%
Performance
67
tokens/sec
Faster than 34% of models
1.38
seconds
Faster than 37% of models
1.38
seconds
Faster than 58% of models
Market Median
94 tok/s
29% slower
Median TTFT
1.11s
24% slower
Throughput/Dollar
313
tok/s per $/1M
Speed Comparison
GPT-5.2 (Non-reasoning)
67 tok/s+0%
Qwen3 235B A22B (Reasoning)
66 tok/s-1%
GPT-5 (minimal)
66 tok/s-1%
Context Window
262K
tokens
Larger than 62% of models
Max Output
33K
tokens
13% of context
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
75.2%
HLE
8.2%
LiveCodeBenchNot evaluated
SciCode
37.0%
TerminalBench Hard
31.1%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
56.9%
Long Context Recall
34.7%
Tau2
89.8%
Market AverageTop Score