Models

qwen3.8-max

1000K ctx · 4 providers · updated 2026-08-05 00:15 UTC

Cheapest
$2.48 via 0G Router
Avg price
$2.87 /1M
providers
4
Tokens (24h)
36B
Volume (24h)
$108.5K est.
(3 × $1.65 + $4.95) ÷ 4 = $2.48/1M — 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 $1.65, 3:1 $2.48, 1:1 $3.30, output only $4.95 per 1M.

The board shows this model's cheapest measured offer ($2.48/1M); the smaller figure under it is the mean of the 4 offers listed below ($2.87/1M). Add those up and divide — it matches. 24h token volume (36B) 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
0g-teetls 0G Router $1.65$4.95 API-measured
openrouter-best OpenRouter $2.00$6.00 API-measured
novita-ai Novita AI $2.00$6.00 API-measured
requesty Requesty $2.00$6.00 API-measured

Price trend

$2.4753 $2.4753 2026-08-03 → 2026-08-05 · 3d 2026-08-03 · O 2.4753 H 2.4753 L 2.4753 C 2.4753 $/1M2026-08-04 · O 2.4753 H 2.4753 L 2.4753 C 2.4753 $/1M2026-08-05 · O 2.4753 H 2.4753 L 2.4753 C 2.4753 $/1M

Cheapest blended price, last 3 days (USD/1M): $2.4753 → $2.4753 → $2.4753

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/qwen3.8-max.json. Free reuse requires attribution to tkx.org.

FAQ

How much does qwen3.8-max cost?

Cheapest measured offer right now: $1.65/1M input, $4.951/1M output via 0g-teetls — across 4 tracked providers, refreshed hourly.

Who serves qwen3.8-max?

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

How heavily is qwen3.8-max used?

qwen3.8-max routed 36B 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