Models

claude-4.5-haiku

replicate ↗ · 1 providers · updated 2026-08-05 00:15 UTC

Cheapest
$2.00 Official list · Replicate
Avg price
$2.00 /1M
providers
1
Tokens (24h)
38B
Volume (24h)
$76.2K est.
(3 × $1.00 + $5.00) ÷ 4 = $2.00/1M — 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 $1.00, 3:1 $2.00, 1:1 $3.00, output only $5.00 per 1M.

The board shows this model's cheapest measured offer ($2.00/1M); the smaller figure under it is the mean of the 1 offers listed below ($2.00/1M). Add those up and divide — it matches. 24h token volume (38B) 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
replicate Pricebook (LiteLLM) $1.00$5.00 Official list

Volume trend

40B 30d d-29 · 35B tokensd-28 · 39B tokensd-27 · 38B tokensd-26 · 37B tokensd-25 · 36B tokensd-24 · 27B tokensd-23 · 25B tokensd-22 · 35B tokensd-21 · 37B tokensd-20 · 35B tokensd-19 · 37B tokensd-18 · 37B tokensd-17 · 31B tokensd-16 · 34B tokensd-15 · 38B tokensd-14 · 36B tokensd-13 · 38B tokensd-12 · 35B tokensd-11 · 36B tokensd-10 · 24B tokensd-9 · 25B tokensd-8 · 36B tokensd-7 · 36B tokensd-6 · 34B tokensd-5 · 36B tokensd-4 · 40B tokensd-3 · 36B tokensd-2 · 25B tokensd-1 · 39B tokensd-0 · 38B tokens

Last 30 days: 35B → 38B (+7%); range 24B–40B 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/claude-4.5-haiku.json. Free reuse requires attribution to tkx.org.

About

Claude-4.5-haiku is a language model designed for text generation tasks, served by multiple inference providers on AI model marketplaces under the "replicate" serving-platform tag.

AI-generated summary from public information — is this yours?

FAQ

How much does claude-4.5-haiku cost?

Cheapest measured offer right now: $1/1M input, $5/1M output via replicate — across 1 tracked providers, refreshed hourly.

Who serves claude-4.5-haiku?

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

How heavily is claude-4.5-haiku used?

claude-4.5-haiku routed 38B 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