Models

GLM-4.5

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

Cheapest
$0.700 Official list · DeepInfra
Avg price
$0.963 /1M
providers
7
(3 × $0.400 + $1.60) ÷ 4 = $0.700/1M — 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 $0.400, 3:1 $0.700, 1:1 $1.00, output only $1.60 per 1M.

The board shows this model's cheapest measured offer ($0.700/1M); the smaller figure under it is the mean of the 8 offers listed below ($0.963/1M). Add those up and divide — it matches.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
deepinfra Pricebook (LiteLLM) $0.400$1.60 Official list
vercel_ai_gateway Pricebook (LiteLLM) $0.600$2.20 Official list
zai Pricebook (LiteLLM) $0.600$2.20 Official list
novita Pricebook (LiteLLM) $0.600$2.20 Official list
openrouter-best OpenRouter $0.600$2.20 API-measured
novita-ai Novita AI $0.600$2.20 API-measured
requesty Requesty $0.600$2.20 API-measured
burncloud burncloud $0.600$2.20 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 329M 8244
pi 233M 6546
SillyTavern 167M 11K
OpenClaw 140M 2431
Cline 125M 2148

Price trend

$0.7 $0.7 2026-07-06 → 2026-08-05 · 31d 2026-07-06 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-07 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-08 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-09 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-10 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-11 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-12 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-13 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-14 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-15 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-16 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-17 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-18 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-19 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-20 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-21 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-22 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-23 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-24 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-25 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-26 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-27 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-28 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-29 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-30 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-07-31 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-08-01 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-08-02 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-08-03 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-08-04 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M2026-08-05 · O 0.7 H 0.7 L 0.7 C 0.7 $/1M

Cheapest blended price, last 31 days (USD/1M): $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7 → $0.7

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.json. Free reuse requires attribution to tkx.org.

About

GLM-4.5 is a large language model served by multiple inference providers on AI model marketplaces, known for its capabilities in natural language processing tasks.

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

FAQ

How much does GLM-4.5 cost?

Cheapest measured offer right now: $0.4/1M input, $1.6/1M output via deepinfra — across 7 tracked providers, refreshed hourly.

Who serves GLM-4.5?

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 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