Inkling Small

thinkingmachines· 2026-07-30· 524K ctx· apache-2.0

open weightstool call quant: unknown

spread (output)

1.2×

$1.20 – $1.44 · 11 providers

11 providers priced · 1 omitted (stale)

Provider	Input	Output	Cache rd	Blended
Kilo Gateway relay router	free/—	free/—	—	free/—
OpenRouter unknown	free/—	free/—	—	free/—
Deep Infra open weights host	$0.450	$1.20	$0.100	$0.296
Eden AI relay router	$0.450	$1.20	$0.100	$0.296
Eden AIstale relay router	$0.500	$1.20	$0.100	$0.309
Hugging Face relay router	$0.500	$1.20	—	$0.564^*
Kilo Gateway relay router	$0.450	$1.20	$0.100	$0.296
NanoGPT relay router	$0.500	$1.20	$0.100	$0.309
OpenRouter unknown	$0.450	$1.20	$0.100	$0.296
Vercel AI Gateway unknown	$0.500	$1.20	$0.100	$0.309
Baseten relay router	$0.500	$1.20	$0.100	$0.309
Arcee relay router	$0.500	$1.20	$0.100	$0.309
Pioneer relay router	$0.500	$1.20	$0.100	$0.350
LLMTRoutlier relay router	$0.580	$1.44	—	$0.658^*

Cheapest (output)

Deep Infra

$1.20 /M

opencode.json

{
  "provider": {
    "deepinfra": {
      "npm": "@ai-sdk/deepinfra",
      "models": {
        "thinkingmachines/Inkling-Small": {}
      }
    }
  }
}

Set DEEPINFRA_API_KEY in your environment. Generated — verify against the OpenCode docs.

Output $/M over time7-day preview

Median line, min–max band. Pre-2026-09 points are catalog-recorded dates from models.dev git history, not provider effective dates.

Full price history & dynamics

This is a 7-day preview. Sign in for 30 days free; the full series and export are the API subscription.

Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.