Saltar al contenido principal
AITier

Inkling Small

Thinking MachinesOpen WeightApache 2.0 · Uso Comercial

Descripción

Inkling-Small is Thinking Machines Lab's efficient open-weights MoE multimodal model (276B total / 12B active parameters) released under Apache 2.0. It accepts text, image, and audio inputs and generates text, with native reasoning, variable thinking effort, and a context window up to 1M tokens (Tinker exposes 64K and 256K configurations). Hugging Face weights: thinkingmachines/Inkling-Small and thinkingmachines/Inkling-Small-NVFP4. Vendor self-host VRAM: BF16 ≥ ~600 GB aggregated; NVFP4 ≥ ~180 GB aggregated. SWE-Bench Verified 80.2% vs Inkling 77.6% (same bash-only harness). Fine-tuning and playground chat are available via Tinker. Official Tinker serverless inference (256K, list): $0.30 / $1.20 per 1M input/output tokens ($0.06 cached).

Fecha de lanzamiento
2026-07-30
Parámetros
276.0B
Longitud del contexto
1.0M
Modalidades
audio, image, text

Radar de capacidades

28
general
52
coding
90
reasoning
64
science
50
agents
80
multimodal

Rankings

Dominio#PosiciónPuntuaciónFuente
Capacidad agéntica43
49.0
LS
Ranking de codificación127
72.0
AA
Ranking general260
45.0
AA
Ranking multimodal82
49.0
LS
Ciencia90
73.0
AA

Puntuaciones de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Agents

AA-Briefcase917.00 / 3000Aut.
Toolathlon54.4%Aut.
Tau3 Banking15.5%Aut.

Audio

MMAU77.0%Aut.

Chat

VoiceBench Avg90.1%Aut.

Factuality

SimpleQA Verified20.6%Aut.

General

GDPval-AA1269.00 / 3000Aut.
Global-MMLU-Lite86.7%Aut.
Artificial Analysis40.0%Aut.

Instruction Following

IFBench82.2%Aut.

Math

AIME 202695.5%Aut.

Reasoning

GPQANYU + Cohere + Anthropic (2023)89.5%Aut.
ARC-AGI84.0%Aut.
SWE-Bench Verified80.2%Aut.
MCP Atlas79.6%Aut.
CharXiv-R77.4%Aut.
BrowseCompOpenAI (2025)77.4%Aut.
Terminal-Bench 2.164.7%Aut.
SWE-Bench ProPrinceton NLP (2024)55.9%Aut.
SciCode48.7%Aut.
ARC-AGI v240.1%Aut.
Humanity's Last Exam31.6%Aut.
CritPT8.3%Aut.

Vision

MMMU-Pro74.0%Aut.

Índices de evaluación AA

(Artificial Analysis)
Gpqa(NYU + Cohere + Anthropic (2023))
89.5
Lcr(Artificial Analysis)
75.7
Terminalbench V2 1
55.1
Coding Index(Artificial Analysis)
52.9
Scicode(UIUC + Argonne National Lab (2024))
49.7
Hle(Center for AI Safety + Scale AI (2025))
33.3
Intelligence Index(Artificial Analysis)
26.1
Tau Banking
18.8

Puntuaciones por categoría LLM Stats

(LLM Stats (zeroeval))
Legal
100
Finance
100
Productivity
100
Agents
100
Reasoning
100
General
92
Chat
90
Language
90
Safety
90
Speech To Text
90
Communication
90
Multimodal
80
Search
80
Instruction Following
80
Frontend Development
80
Audio
80
Physics
70
Biology
70
Chemistry
70
Code
70
Spatial Reasoning
60
Vision
60
Math
50
Tool Calling
50
Factuality
20

Precios

Precio de entrada$0.3 / 1M tokens
Precio de salida$1.2 / 1M tokens
Precio mixto (3:1)$0.525 / 1M tokens
Precio de lectura caché$0.1 / 1M tokens

Velocidad

Tokens/seg162.1
Retraso del primer token1.90s
Tiempo hasta la respuesta14.24s

Ranking de Precios por Proveedor

Ranking de Precios por Proveedor

10 proveedores

Más barato: Thinking Machines LabMás caro: LLMTR
ProveedorEntradaSalida
1Thinking Machines LabMás barato
$0
$0
2DeepInfra
$0
$0
3Thinking MachinesPRINCIPAL
$0.3
$1.2
4OpenRouter
$0.45
$1.2
5Kilo Gateway
$0.45
$1.2
6Baseten
$0.5
$1.2
7Vercel AI Gateway
$0.5
$1.2
8Pioneer
$0.5
$1.2
9Arcee
$0.5
$1.2
10LLMTR
$0.58
$1.44

Comparar precios entre diferentes proveedores de API para este modelo.

Fuentes externas

LLM StatsArtificial Analysis