Inkling pricing.
Prices checked
Inkling costs $1.87 in and $4.68 out per million tokens from Thinking Machines; the cheapest price is $1.72 at DeepInfra, checked .
Thinking Machines's own price
Thinking Machines
$1.87 in · $4.68 out
192% above the typical price of the 392 text models we track.
Cheapest price
DeepInfra
$0.95 in · $4.05 out
33% less than Thinking Machines, and the provider says why.
Every provider selling Inkling
- 1
$1 in · $0.17 out · 1M context here
$0.79/M tokens - 2
$1 in · $0.17 out · 1M context here
$0.79/M tokens - 3
$0.95 in · $4.05 out
$1.72/M tokens - 4
$1 in · $4.05 out
$1.76/M tokens - 5Runs it themselves
$1 in · $4.05 out · 256k context here
$1.76/M tokens - 6
$1 in · $4.05 out · 256k context here
$1.76/M tokens - 7
$1 in · $4.05 out · 1M context here
$1.76/M tokens - 8
$1 in · $4.05 out · 1M context here
$1.76/M tokens - 9
$1 in · $4.05 out
$1.76/M tokens - 10
$1 in · $4.05 out · 1M context here
$1.76/M tokens - 11
$1 in · $4.05 out · 1M context here
$1.76/M tokens - 12
$1 in · $4.05 out
$1.76/M tokens - 13
$1 in · $4.05 out · 1M context here
$1.76/M tokens - 14
$1 in · $4.05 out · 1M context here
$1.76/M tokens - 15
$1 in · $4.05 out
$1.76/M tokens - 16
$1.01 in · $4.09 out · 256k context here
$1.78/M tokens - 17
$1.06 in · $4.27 out
$1.86/M tokens - 18Runs it themselves
$1.06 in · $4.28 out · 1M context here
$1.86/M tokens - 19
Charm Hyper
Runs it themselves$1.09 in · $4.41 out · 1M context here
$1.92/M tokens - 20
Modal
Lower precision (nvfp4)$1.20 in · $5 out · 1M context here
$2.15/M tokens - 21
$1.87 in · $4.68 out · 66k context here
$2.57/M tokens - 22
Thinking Machines
Same as maker$1.87 in · $4.68 out · 66k context here
$2.57/M tokens - 23
$1.87 in · $4.68 out · 66k context here
$2.57/M tokens - 24
$1.87 in · $4.68 out · 262k context here
$2.57/M tokens - 25
$3.74 in · $9.36 out · 262k context here
$5.15/M tokens
What it costs for your work
A month at Thinking Machines's own price
A month at DeepInfra, the cheapest
What you save
A page is about 600 tokens in and 60 out, a support reply 200 in and 300 out, an email 150 in and 250 out. Nothing else is counted: no cache discount, no batch rate, no free tier.
How we count
Prices are per million tokens. The big number on each row is blended 3 in : 1 out, the way most work uses a model. A price below Thinking Machines's own is listed as cheapest only when the provider says why.
- Resells
- The provider sells another company's endpoint, at a margin of its own or at the maker's price.
- Runs it themselves
- The provider runs the open weights on hardware of its own, so the price is its own rather than a resale.
- Credits
- Priced in credits or points that convert to dollars, so the rate moves when the conversion does.
- Lower precision
- The open weights, served at a lower precision than the maker's, so not quite the same product.
- Same as maker
- Sold by someone else at the price the maker charges.
- Costs more
- Sold by someone else for more than the maker charges.
Similar models
Models from other labs that do what Inkling does, cheapest first. Each percentage is against Inkling's cheapest price, $1.72 per M tokens.
Frequently asked
- Who sells Inkling cheapest?
- DeepInfra, at $0.95 in and $4.05 out per million tokens, checked 31 Oct 2026. The provider runs the open weights on hardware of its own, so the price is its own rather than a resale.
- Is Inkling open weights?
- Yes. Thinking Machines publishes the weights, so anyone may host Inkling, which is why 24 providers sell it and why their prices differ so much.
- How much context does Inkling hold?
- 524,288 tokens in one call, which is about 524k, and it can call your own functions.
- How does Inkling compare with the rest of the market?
- At $2.57 per million tokens, Thinking Machines's own price is 192% above the typical $0.88 across the 392 text models we track.
More from Thinking Machines