Models

Qwen3-4B

nebius · 41K ctx · 3 providers · updated 2026-08-05 00:15 UTC

Cheapest
$0.120 Official list · Nebius
Avg price
$0.432 /1M
providers
3
(3 × $0.080 + $0.240) ÷ 4 = $0.120/1M — 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 $0.080, 3:1 $0.120, 1:1 $0.160, output only $0.240 per 1M.

The board shows this model's cheapest measured offer ($0.120/1M); the smaller figure under it is the mean of the 3 offers listed below ($0.432/1M). Add those up and divide — it matches.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
nebius Pricebook (LiteLLM) $0.080$0.240 Official list
fireworks_ai Pricebook (LiteLLM) $0.200$0.200 Official list
burncloud burncloud $0.300$3.00 API-measured

Price trend

Cheapest blended price, last 31 days (USD/1M): $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12 → $0.12

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/qwen3-4b.json. Free reuse requires attribution to tkx.org.

FAQ

How much does Qwen3-4B cost?

Cheapest measured offer right now: $0.08/1M input, $0.24/1M output via nebius — across 3 tracked providers, refreshed hourly.

Who serves Qwen3-4B?

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

Is the price of Qwen3-4B going up or down?

The daily candles above track the cheapest blended price ($/1M, 3:1 in:out). TKX snapshots every hour, so drops and hikes show up the same day they happen.

Related analysis

Back to rankings