modelbenchmark.io

Inkling 2 Small

inkling-2-small

Compare

Multimodal MoE reasoning model (594B total, 17B active) for agentic coding, vision, and knowledge work

Specification

most-agreed values

Context
1M
Max output
1M
Released
2026-11-05
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.30
Output
$1.00
Cache read
$0.06
Cache write
$0.15

Available from 13 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
openrouter · freefreefree——1M131K—
kilo · thinkingmachines$0.15$0.50$0.03—1M944K—
prime · thinkingmachines$0.15$0.50$0.03$0.151M1M—
cloudflare-workers-ai · cf$0.30$1.00$0.10—1M1M—
deepinfra · thinkingmachines$0.30$1.00$0.03—1M131K—
edenai$0.30$1.00
$0.30
$0.10
$0.03
—1M131K—
huggingface · thinkingmachines$0.30$1.00——1M131K—
nebius · thinkingmachines$0.30$1.00$0.06—1M1M—
ollama-cloud$0.30$1.00$0.03—1M131K—
openrouter · thinkingmachines$0.30$1.00$0.03—1M944K—
together_ai$0.30$1.00$0.03—1M1M—
vercel · thinkingmachines$0.30$1.00$0.03—1M262K—
cortecs$0.306$1.023$0.061—1M131K—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-11-13kilo · thinkingmachinesCache read$0.06
2026-11-14kilo · thinkingmachinesCache read$0.03
2026-11-13kilo · thinkingmachinesInput$0.30
2026-11-14kilo · thinkingmachinesInput$0.15
2026-11-13kilo · thinkingmachinesOutput$1.00
2026-11-14kilo · thinkingmachinesOutput$0.50
2026-11-14edenaiCache read$0.30
2026-11-15edenaiCache read$0.30