Models

glm-4.7

openrouter · 205K ctx · 13 providers · updated 2026-08-05 00:15 UTC

Cheapest
$0.675 Official list · OpenRouter
Avg price
$1.07 /1M
providers
13
(3 × $0.400 + $1.50) ÷ 4 = $0.675/1M — 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 $0.675, 1:1 $0.950, output only $1.50 per 1M.

The board shows this model's cheapest measured offer ($0.675/1M); the smaller figure under it is the mean of the 20 offers listed below ($1.07/1M). Add those up and divide — it matches.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
openrouter Pricebook (LiteLLM) $0.400$1.50 — — — Official list
deepinfra HuggingFace Router $0.400$1.75 2337ms 23 — API-measured
DeepInfra (fp4) OpenRouter $0.400$1.75 775ms 27 100.0% API-measured
StreamLake (fp8) OpenRouter $0.480$1.76 2035ms 39 90.5% API-measured
together_ai Pricebook (LiteLLM) $0.450$2.00 — — — Official list
AtlasCloud (fp8) OpenRouter $0.520$1.85 2003ms 44 93.2% API-measured
Novita (fp8) OpenRouter $0.540$1.98 2053ms 29 96.0% API-measured
baseten 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
novita HuggingFace Router $0.600$2.20 1542ms 52 — API-measured
baseten HuggingFace Router $0.600$2.20 511ms 84 — 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
Z.AI (fp4) OpenRouter $0.600$2.20 13014ms 31 90.2% API-measured
Google OpenRouter $0.600$2.20 7553ms 45 94.8% API-measured
Venice (fp4) OpenRouter $0.550$2.65 1280ms 26 99.7% API-measured
cerebras HuggingFace Router $2.25$2.75 127ms 389 — API-measured
Cerebras (fp16) OpenRouter $2.25$2.75 526ms 121 100% API-measured

Price trend

$0.675 $0.675 2026-07-06 → 2026-08-05 · 31d 2026-07-06 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-07 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-08 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-09 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-10 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-11 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-12 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-13 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-14 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-15 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-16 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-17 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-18 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-19 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-20 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-21 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-22 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-23 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-24 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-25 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-26 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-27 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-28 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-29 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-30 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-07-31 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-08-01 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-08-02 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-08-03 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-08-04 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M2026-08-05 · O 0.675 H 0.675 L 0.675 C 0.675 $/1M

Cheapest blended price, last 31 days (USD/1M): $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675 → $0.675

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-4.7.json. Free reuse requires attribution to tkx.org.

About

GLM-4.7 is a large language model (LLM) designed for natural language processing tasks, served by multiple inference providers on AI model marketplaces and listed under the "openrouter" serving-platform tag.

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

FAQ

How much does glm-4.7 cost?

Cheapest measured offer right now: $0.4/1M input, $1.5/1M output via openrouter — across 13 tracked providers, refreshed hourly.

Who serves glm-4.7?

13 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-4.7 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