Models

glm-4.5-air

pinstripes · 131K ctx · 7 providers · updated 2026-08-05 00:15 UTC

Cheapest
$0.206 Official list · Pinstripes
Avg price
$0.354 /1M
providers
7
(3 × $0.125 + $0.450) ÷ 4 = $0.206/1M — 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 $0.125, 3:1 $0.206, 1:1 $0.287, output only $0.450 per 1M.

The board shows this model's cheapest measured offer ($0.206/1M); the smaller figure under it is the mean of the 11 offers listed below ($0.354/1M). Add those up and divide — it matches.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
pinstripes Pricebook (LiteLLM) $0.125$0.450 Official list
novita Pricebook (LiteLLM) $0.130$0.850 Official list
novita HuggingFace Router $0.130$0.850 598ms 62 API-measured
novita-ai Novita AI $0.130$0.850 API-measured
Novita (bf16) OpenRouter $0.130$0.850 1770ms 24 99.6% API-measured
SiliconFlow (fp8) OpenRouter $0.140$0.860 1187ms 30 99.5% API-measured
vercel_ai_gateway Pricebook (LiteLLM) $0.200$1.10 Official list
zai Pricebook (LiteLLM) $0.200$1.10 Official list
requesty Requesty $0.200$1.10 API-measured
burncloud burncloud $0.200$1.10 API-measured
Z.AI (fp8) OpenRouter $0.200$1.10 1643ms 24 98.5% API-measured

Who burns this model

Top apps routing traffic to this model over the last 30 days, via OpenRouter's public stats. Only apps that opted into tracking appear, and only the top few are published — this is not the full demand picture. These figures are a 30-day window and are NOT comparable with the cumulative totals on the Apps board.

AppTokens (30d)Requests
Hermes Agent 2B 42K
OpenSquilla 869M 43K
Janitor AI 738M 70K
tanneur 653M 13K
OpenClaw 617M 14K

Price trend

$0.2063 $0.2063 2026-07-06 → 2026-08-05 · 31d 2026-07-06 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-07 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-08 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-09 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-10 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-11 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-12 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-13 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-14 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-15 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-16 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-17 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-18 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-19 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-20 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-21 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-22 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-23 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-24 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-25 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-26 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-27 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-28 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-29 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-30 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-07-31 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-08-01 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-08-02 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-08-03 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-08-04 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M2026-08-05 · O 0.2063 H 0.2063 L 0.2063 C 0.2063 $/1M

Cheapest blended price, last 31 days (USD/1M): $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063 → $0.2063

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/glm-4.5-air.json. Free reuse requires attribution to tkx.org.

About

"glm-4.5-air" is a machine-learning system designed for natural language processing tasks. It is served by multiple inference providers on AI model marketplaces and is listed under the "pinstripes" tag.

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

FAQ

How much does glm-4.5-air cost?

Cheapest measured offer right now: $0.125/1M input, $0.45/1M output via pinstripes — across 7 tracked providers, refreshed hourly.

Who serves glm-4.5-air?

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

Is the price of glm-4.5-air 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