Models

GLM 5

z-ai ↗ · 205K ctx · 17 providers · updated 2026-08-05 00:15 UTC

Cheapest
$0.930 via OpenRouter
Avg price
$1.42 /1M
providers
17
(3 × $0.600 + $1.92) ÷ 4 = $0.930/1M — 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 $0.600, 3:1 $0.930, 1:1 $1.26, output only $1.92 per 1M.

The board shows this model's cheapest measured offer ($0.930/1M); the smaller figure under it is the mean of the 21 offers listed below ($1.42/1M). Add those up and divide — it matches.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
StreamLake (fp8) OpenRouter $0.600$1.92 2252ms 51 99.9% API-measured
GMICloud (fp8) OpenRouter $0.600$1.92 1132ms 60 98.5% API-measured
0g-teetls 0G Router $0.504$2.27 API-measured
deepinfra HuggingFace Router $0.600$2.08 839ms 21 API-measured
DeepInfra (fp4) OpenRouter $0.600$2.08 1031ms 24 100% API-measured
Baidu (fp8) OpenRouter $0.700$2.24 1105ms 36 98.3% API-measured
DigitalOcean OpenRouter $0.750$2.40 912ms 7 97.6% API-measured
openrouter Pricebook (LiteLLM) $0.800$2.56 Official list
SiliconFlow (fp8) OpenRouter $0.950$2.55 1936ms 52 98.1% API-measured
baseten Pricebook (LiteLLM) $0.950$3.15 Official list
AtlasCloud (fp8) OpenRouter $0.950$3.15 1453ms 38 99.2% API-measured
zai Pricebook (LiteLLM) $1.00$3.20 Official list
Amazon Bedrock OpenRouter $1.00$3.20 846ms 104 100% API-measured
Novita (fp8) OpenRouter $1.00$3.20 1884ms 34 100% API-measured
Z.AI (fp8) OpenRouter $1.00$3.20 7239ms 31 99.4% API-measured
Venice (fp8) OpenRouter $1.00$3.20 1533ms 21 99.5% API-measured
novita HuggingFace Router $1.00$3.20 1040ms 39 API-measured
novita-ai Novita AI $1.00$3.20 API-measured
requesty Requesty $1.00$3.20 API-measured
Phala OpenRouter $1.20$3.50 API-measured
burncloud burncloud $2.00$6.40 API-measured

Price trend

$0.93 $0.93 2026-07-06 → 2026-08-05 · 31d 2026-07-06 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-07 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-08 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-09 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-10 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-11 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-12 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-13 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-14 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-15 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-16 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-17 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-18 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-19 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-20 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-21 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-22 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-23 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-24 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-25 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-26 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-27 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-28 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-29 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-30 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-07-31 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-08-01 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-08-02 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-08-03 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-08-04 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M2026-08-05 · O 0.93 H 0.93 L 0.93 C 0.93 $/1M

Cheapest blended price, last 31 days (USD/1M): $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93 → $0.93

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-5.json. Free reuse requires attribution to tkx.org.

About

GLM 5 is an AI 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 5 cost?

Cheapest measured offer right now: $0.6/1M input, $1.92/1M output via StreamLake (fp8) — across 17 tracked providers, refreshed hourly.

Who serves GLM 5?

17 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 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