InferIndex
Language, English, EN
Account

ModelsThinking MachinesInkling Small

Inkling Small

thinkingmachines/inkling-small64k context Compare →
MedianThe median blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
$0.638
Most expensiveThe highest blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
$0.638
Offers
11
Providers
6

Cheapest right now

$0.525 blended / 1M tokens

No change7D
in
$0.30
out
$1.20
Cached input
$0.06
Go to offer Go to offer at Vercel AI Gateway (opens in a new tab)via Vercel AI Gateway

Public leaderboards

  • Text Arena, style controlThe series the source publishes by default for text since 16 May 2025: ranks corrected for the style of the answers (style control). #143 of 419Best rank in the source's rank spread, 143rd to 171st, given the confidence intervals of all ranked models. 158th by score. 1,406 1,401 to 1,410Arena Score · 36,999 votes
  • Code Arena (WebDev)The Code Arena ranking (WebDev). The source publishes no style-corrected series (as read on 9 October 2026). #91 of 152Best rank in the source's rank spread, 91st to 106th, given the confidence intervals of all ranked models. 95th by score. 1,409 1,400 to 1,418Arena Score · 5,295 votes
  • Agent Arena aggregateThe Agent Arena aggregate score: a score of another kind (not an Arena score), on a scale of its own; it cannot be compared with the other series. #53 of 57Best rank in the source's rank spread, 53rd to 57th, given the confidence intervals of all ranked models. 56th by score. −0.170 −0.188 to −0.152IPS score · 552,386 observations

Source: Arena (opens in a new tab) · Data under the CC BY 4.0 license (creativecommons.org/licenses/by/4.0) · CC BY 4.0 (opens in a new tab) · scores and ranks as published on 28 Oct 2026; the presentation is ours

Inkling Small costs from $0.525 per million tokens (at a 3:1 input:output mix): the cheapest of 3 comparable offers, at Thinking Machines, checked on ; 11 offers are listed.

Listed offers, by price

Comparable offersOther offersSolid steps are comparable offers; dashed steps are the other offers, which are not counted in cheapest, median or most expensive.

Offers not counted in cheapest, median or most expensive (8)

  • $0.638 · DeepInfra via Hugging Face · another route of the same provider
  • $0.638 · DeepInfra via Eden AI · cannot be designated the cheapest
  • $0.638 · DeepInfra via Kilo Gateway · cannot be designated the cheapest
  • $0.638 · DeepInfra via Vercel AI Gateway · another route of the same provider
  • $0.638 · Glama via Glama · cannot be designated the cheapest
  • $0.638 · Martian via Martian · cannot be designated the cheapest
  • $0.638 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $0.638 · DeepInfra via OpenRouter · another route of the same provider

Cheapest that confirms no training on your prompts. The provider's published policy: prompts are not used for training.

DeepInfra

directYou buy access straight from the company that runs the model on its servers. · fp8 · 524k

$0.638 blended / 1M tokens

in
$0.45
out
$1.20
Cached input
$0.10
Go to offer Go to offer at DeepInfra (opens in a new tab)at DeepInfra

Price historyThe cheapest offer each day, against the lab's official list price when it publishes one. Each day at 00:00 UTC, the offer the API would have selected as the cheapest, with the same exclusions as /cheapest. Blended price, promotions included.

Cheapest offer and official list price, by day, 30 days
DayCheapest offerOfficial list price
2026-10-02$0.525, Thinking Machines–
2026-10-03$0.525, Thinking Machines–
2026-10-04$0.525, Thinking Machines–
2026-10-05$0.525, Thinking Machines–
2026-10-06$0.525, Thinking Machines–
2026-10-07$0.525, Thinking Machines–
2026-10-08$0.525, Thinking Machines–
2026-10-09$0.525, Thinking Machines–
2026-10-10$0.525, Thinking Machines–
2026-10-11$0.525, Thinking Machines–
2026-10-12$0.525, Thinking Machines–
2026-10-13$0.525, Thinking Machines–
2026-10-14$0.525, Thinking Machines–
2026-10-15$0.525, Thinking Machines–
2026-10-16$0.525, Thinking Machines–
2026-10-17$0.525, Thinking Machines–
2026-10-18$0.525, Thinking Machines–
2026-10-19$0.525, Thinking Machines–
2026-10-20$0.525, Thinking Machines–
2026-10-21$0.525, Thinking Machines–
2026-10-22$0.525, Thinking Machines–
2026-10-23$0.525, Thinking Machines–
2026-10-24$0.525, Thinking Machines–
2026-10-25$0.525, Thinking Machines–
2026-10-26$0.525, Thinking Machines–
2026-10-27$0.525, Thinking Machines–
2026-10-28$0.525, Thinking Machines–
2026-10-29$0.525, Thinking Machines–
2026-10-30$0.525, Thinking Machines–
2026-10-31$0.525, Thinking Machines–

Cheapest offer

Offers

11 of 11 offers

Offers for Inkling Small, one row per offer, sorted by blended price.
RankProvider · viaYou buy access through an aggregator: one account and one API that forward your requests to other providers. "Via" names the aggregator; the price is the one it charges you. When "via" says "hosted API", no aggregator is involved: the model belongs to a lab and another provider sells it.Input $/1MOutput $/1MBlended $/1MA single price that mixes input and output: 3 input tokens for 1 output token, per million tokens. It makes offers easy to rank; your real cost depends on your own mix.PrecisionHow finely the model's numbers are stored on the provider's servers. Lower precision (fp8, fp4) is cheaper to run and can slightly change answer quality; "unknown" means the provider doesn't say. ContextThe maximum amount of text, counted in tokens, the model can take in and write in a single request. Past this limit, the request is refused or cut.ConditionsWhat a provider says about how it handles your data and who can sign up: training on prompts, processing region, sign-up requirements. Each comes from the provider's published documents; when nothing is published, it stays unknown.SignalsOffer
1 Thinking Machinesvia Vercel AI Gateway 0.30 1.20 0.525 – 64k
Go to offer at Vercel AI Gateway (opens in a new tab)
2 DeepInfra 0.45 1.20 0.638 fp8 524k United States
Go to offer at DeepInfra (opens in a new tab)
3 DeepInfravia Hugging Face 0.45 1.20 0.638 fp8 524k United States
See pricing at Hugging Face (opens in a new tab)
4 DeepInfravia Eden AI 0.45 1.20 0.638 fp8 524k United States Unverified. No public page for this offer: listed, not designated cheapest
: Eden AI (opens in a new tab). No public price page for this model
5 DeepInfravia Kilo Gateway 0.45 1.20 0.638 fp8 524k United States Unverified. No public page for this offer: listed, not designated cheapest
: Kilo Gateway (opens in a new tab). No public price page for this model
6 DeepInfravia Vercel AI Gateway 0.45 1.20 0.638 fp8 1M United States
Go to offer at Vercel AI Gateway (opens in a new tab)
7 Glama 0.45 1.20 0.638 – 524k Unverified. No public page for this offer: listed, not designated cheapest
: Glama (opens in a new tab). No public price page for this model
8 Martian 0.45 1.20 0.638 – – worldwide Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
See pricing at Martian (opens in a new tab)
9 NanoGPT 0.45 1.20 0.638 – 524k Thinking: Thinking: a mode of the model, not its standard offer. Never designated cheapest while a standard offer exists
Go to offer at NanoGPT (opens in a new tab)
10 Nous Portal 0.45 1.20 0.638 – 524k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
See pricing at Nous Portal (opens in a new tab)
11 DeepInfravia OpenRouter 0.45 1.20 0.638 fp8 524k United States Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at OpenRouter (opens in a new tab)

No training on promptsPrompts may be used for trainingTraining terms not published

backend not named. The router bills this price itself without naming who serves the model.

Blended = (3 × input + output) / 4, per million tokens. Prices in USD, converted at the ECB rate when the provider bills in another currency.

Method

Monthly cost for your workload

Computed by the API for the three cheapest offers, per 30-day month.
  1. Thinking Machines$36.00per month
  2. DeepInfra$45.00per month+$9.00 vs the cheapest
  3. NanoGPT$45.00per month+$9.00 vs the cheapest

Host it yourself instead? See the break-even

Compare Inkling Small with

Related models

More from Thinking Machines

All Thinking Machines models

Same index family

Use this data

The index is queryable. The API is free to use.
Free API
curl https://api.inferindex.dev/cheapest?model=thinkingmachines/inkling-small
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

Also works in Cursor and Codex: see the MCP page.