AI TOOLS RADAR
Explorer
Tous les modèles / THINKINGMACHINES
thinkingmachines logo
thinkingmachines

Thinking Machines: Inkling

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...

Voir la source sur OpenRouter Hugging Face
Présentation

Caractéristiques du modèle

Context
1 048 576 tokens
Sortie maximale
471 859 tokens
Architecture
text+image+audio->text
Tokenizer
Other
Limite des connaissances
Not provided
Modéré
Non
Capacités et modalités

Input → Output

Input
textimageaudio
Output
text
Raisonnement

Oui · max · high · medium · low · minimal · none

API

Paramètres API pris en charge

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstoptemperaturetool_choicetoolstop_ktop_p
Fournisseurs disponibles

3 fournisseurs

DeepInfra

fp8
Context
524K
Sortie maximale
262K
Input
$0.950
Output
$4.05
Lecture du cache
$0.160
Écriture du cache
Not provided

Together

unknown
Context
524K
Sortie maximale
472K
Input
$1.00
Output
$4.05
Lecture du cache
$0.170
Écriture du cache
Not provided

BaseTen

fp8
Context
1.0M
Sortie maximale
33K
Input
$1.00
Output
$4.05
Lecture du cache
$0.170
Écriture du cache
Not provided
thinkingmachines

models

Tous les modèles
thinkingmachines logothinkingmachines

Thinking Machines: Inkling Small

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

Context
1.0M
Input
text · image · audio
Output
text
Input: $0.450Output: $1.20per 1M tokens
Voir la fiche du modèle →
thinkingmachines logothinkingmachines

Thinking Machines: Inkling Small (batch)

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

Context
524K
Input
text · image · audio
Output
text
Input: $0.500Output: $1.20per 1M tokens
Voir la fiche du modèle →
thinkingmachines logothinkingmachines

Thinking Machines: Inkling Small (free)

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

Context
1.0M
Input
text · image · audio
Output
text
Input: FreeOutput: Freeper 1M tokens
Voir la fiche du modèle →
thinkingmachines logothinkingmachines

Thinking Machines: Inkling (batch)

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...

Context
524K
Input
text · image · audio
Output
text
Input: $1.00Output: $4.05per 1M tokens
Voir la fiche du modèle →