Skip to content
Updated minutes ago
Inflection

Inflection 3

Inflection AI · dense · 100B parameters · 8,192 context

Quality
74.0

Parameters

100B

Context Window

8K tokens

Architecture

Dense

Best GPU

B200 SXM

Cheapest API

$15.00/M

Quality Score

74/100

Intelligence Brief

Inflection 3 is a 100B parameter DENSE model from Inflection AI, featuring Grouped Query Attention (GQA) with 72 layers and 10,240 hidden dimensions. With a 8,192 token context window, it supports structured output, code, math, multilingual. On standardized benchmarks, it achieves MMLU 78, HumanEval 48, GSM8K 80. The most cost-effective API deployment is via inflection at $15.00/M output tokens. For self-hosted inference, B200 SXM delivers optimal throughput at $8522/month.

Architecture Details

TypeDENSE
Total Parameters100B
Active Parameters100B
Layers72
Hidden Dimension10,240
Attention Heads80
KV Heads10
Head Dimension128
Vocab Size128,000

Memory Requirements

BF16 Weights

200.0 GB

FP8 Weights

100.0 GB

INT4 Weights

50.0 GB

KV-Cache per Token184320 bytes
Activation Estimate3.50 GB

GPU Compatibility Matrix

Inflection 3 is compatible with 21% of GPU configurations across 41 GPUs at 3 precision levels.

BF16 (Full)
FP8 (Half)
INT4 (Quarter)
Blackwell(7 GPUs)
B200 NVL (pair)360GB
B300288GB
B100 SXM192GB
GB200 NVL72 (per GPU)192GB
Hopper(7 GPUs)
H100 NVL 94GB (per GPU pair)188GB
H200 SXM141GB
H2096GB
GH20096GB
Ada Lovelace(11 GPUs)
L40S48GB
L4048GB
RTX 6000 Ada48GB
L2048GB
Ampere(16 GPUs)
A100 80GB SXM80GB
A100 80GB PCIe80GB
A1664GB
RTX A600048GB
Legend:No fitVery tightTightModerateGoodExcellent

GPU Recommendations

B200 SXMoptimal

BF16 · 2 GPUs · tensorrt-llm

93/100

score

Throughput

280.0 tok/s

Latency (ITL)

3.6ms

Est. TTFT

1ms

Cost/Month

$8522

Cost/M Tokens

$11.58

Use this config →
B100 SXMoptimal

BF16 · 2 GPUs · tensorrt-llm

93/100

score

Throughput

280.0 tok/s

Latency (ITL)

3.6ms

Est. TTFT

1ms

Cost/Month

$8541

Cost/M Tokens

$11.61

Use this config →
H200 SXMoptimal

BF16 · 2 GPUs · tensorrt-llm

90/100

score

Throughput

280.0 tok/s

Latency (ITL)

3.6ms

Est. TTFT

1ms

Cost/Month

$5106

Cost/M Tokens

$6.94

Use this config →

Deployment Options

API

API Deployment

inflection

$15.00/M

output tokens

Self-Hosted

Single GPU

B200 NVL (pair)

$9965/mo

Min VRAM: 100 GB

Scale

Multi-GPU

B200 SXM x2

280.0 tok/s

TP· $8522/mo

API Pricing Comparison

ProviderInput $/MOutput $/MBadges
inflection$5.00$15.00
Cheapest

Cost Analysis

ProviderInput $/MOutput $/M~Monthly Cost
inflectionBest Value$5.00$15.00$100

Cost per 1,000 Requests

Short (500 tok)

$5.50

via inflection

Medium (2K tok)

$22.00

via inflection

Long (8K tok)

$70.00

via inflection

Performance Estimates

Throughput by GPU

B200 SXM
280.0 tok/s
B100 SXM
280.0 tok/s
H200 SXM
280.0 tok/s

VRAM Breakdown (B200 SXM, BF16)

Weights
Act
Weights 100.0 GBKV-Cache 6.0 GBActivations 28.0 GBOverhead 5.0 GB

Quality Benchmarks

Above Average
78th percentile across all models
MMLU
78.0
Average (50th pctile)
HumanEval
48.0
Below Average (43th pctile)
GSM8K
80.0
Below Average (47th pctile)
MT-Bench
80.0
Bottom 25% (0th pctile)

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

Supported Precisions

BF16 (default)

Where to Deploy Inflection 3

Similar Models

Smaller context, Lower qualityCompare →

Yi-Large

102.6B params · moe

Quality: 74

from $3.00/M

Larger context, CheaperCompare →

Command R+

104B params · dense

Quality: 68

from $2.00/M

Larger context, Lower quality, CheaperCompare →

Llama 4 Scout

109B params · moe

Quality: 73

from $0.30/M

Larger context, CheaperCompare →
Larger context, Higher quality, CheaperCompare →

Frequently Asked Questions

How much VRAM does Inflection 3 need for inference?

Inflection 3 requires approximately 200.0 GB of VRAM at BF16 precision, 100.0 GB at FP8, or 50.0 GB at INT4 quantization. Additional VRAM is needed for KV-cache (184320 bytes per token) and activations (~3.50 GB).

What is the best GPU for Inflection 3?

The top recommended GPU for Inflection 3 is the B200 SXM (x2) using BF16 precision. It achieves approximately 280.0 tokens/sec at an estimated cost of $8522/month ($11.58/M tokens). Score: 93/100.

How much does Inflection 3 inference cost?

Inflection 3 API inference starts from $5.00/M input tokens and $15.00/M output tokens. Self-hosted inference costs depend on your GPU configuration — use our ROI calculator for a detailed breakdown.