Models

Inkling

deepinfra · 1049K ctx · 7 providers · updated 2026-09-19 02:15 UTC

Cheapest
$1.73 Official list · DeepInfra
Avg price
$1.84 /1M
providers
7
Tokens (24h)
51B
Volume (24h)
$0 est.
(3 × $0.950 + $4.05) ÷ 4 = $1.73/1M — the $/1M figure blends input and output at 3:1 — that is the only way models with two different rates can be ranked on one axis. Your actual rate depends on your own input:output mix — input only $0.950, 3:1 $1.72, 1:1 $2.50, output only $4.05 per 1M.

The board shows this model's cheapest measured offer ($1.73/1M); the smaller figure under it is the mean of the 9 offers listed below ($1.84/1M). Add those up and divide — it matches. 24h token volume (51B) is sourced from OpenRouter public rankings — today's only public source of absolute per-model token counts (Vercel AI Gateway publishes share-of-traffic percentages); as more sources come online, the per-router breakdown will sum to this total here.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
deepinfra Pricebook (LiteLLM) $0.950$4.05 Official list
deepinfra HuggingFace Router $0.950$4.05 553ms 94 API-measured
together_ai Pricebook (LiteLLM) $1.00$4.05 Official list
fireworks_ai Pricebook (LiteLLM) $1.00$4.05 Official list
openrouter Pricebook (LiteLLM) $1.00$4.05 Official list
openrouter-best OpenRouter $1.00$4.05 API-measured
together HuggingFace Router $1.00$4.05 282ms 68 API-measured
baseten HuggingFace Router $1.00$4.05 225ms 124 API-measured
requesty Requesty $1.87$4.68 API-measured

Volume trend

68B 23d d-22 · 37B tokensd-21 · 35B tokensd-20 · 28B tokensd-19 · 29B tokensd-18 · 31B tokensd-17 · 32B tokensd-16 · 0 tokensd-15 · 0 tokensd-14 · 36B tokensd-13 · 38B tokensd-12 · 47B tokensd-11 · 50B tokensd-10 · 68B tokensd-9 · 59B tokensd-8 · 57B tokensd-7 · 0 tokensd-6 · 50B tokensd-5 · 54B tokensd-4 · 54B tokensd-3 · 52B tokensd-2 · 48B tokensd-1 · 52B tokensd-0 · 51B tokens

Last 23 days: 37B → 51B (+39%); range 0–68B tokens/day. Source: OpenRouter public rankings; refreshed hourly.

Data & method

Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/inkling.json. Free reuse requires attribution to tkx.org.

FAQ

How much does Inkling cost?

Cheapest measured offer right now: $0.95/1M input, $4.05/1M output via deepinfra — across 7 tracked providers, refreshed hourly.

Who serves Inkling?

7 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.

How heavily is Inkling used?

Inkling routed 51B tokens in the last 24h. The daily bars above show routed volume over recent days. Source: OpenRouter public rankings — one of the few routers publishing per-model usage; TKX refreshes hourly.

Related analysis

Back to rankings