GLM 5.2
Z.ai · Open weights · Released Jun 16, 2026 · z-ai/glm-5.2
1.05M contextToolsReasoningStructured outputPrompt cachingOpen weights
Available from 34 providersUSD / MTOK · VERIFIED 12 HOURS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | SMOKE | UPTIME |
|---|---|---|---|---|---|---|---|---|---|
| STStreamLake | $0.336 | $1.06 | $0.062 | 1.02M | fp8 | 4.2s° | 71° tok/s | 1/5 | 99.9% |
| SRSail Research | $0.50 | $3.15 | $0.115 | 1.05M | fp8 | 1.5s° | 38° tok/s | 2/5 | 100.0% |
| AMAmbient | $0.60 | $2.00 | $0.15 | 203K | fp8 | 1.5s° | 167° tok/s | 2/5 | 94.4% |
| DEDecart | $0.684 | $2.28 | $0.114 | 1.05M | fp4 | 1.1s° | 189° tok/s | 2/5 | 98.5% |
 Novita | $0.70 | $2.20 | $0.13 | 1.05M | fp8 | 1.6s° | 72° tok/s | 2/5 | 99.4% |
| DIDigitalOcean | $0.70 | $2.20 | $0.105 | 262K | — | 0.67s° | 70° tok/s | — | 99.7% |
 DeepInfra | $0.75 | $2.40 | $0.14 | 1.05M | fp4 | 1.1s° | 66° tok/s | — | 99.8% |
| INInceptron | $0.75 | $2.90 | $0.17 | 1.05M | fp4 | 0.63s° | 55° tok/s | — | 98.1% |
| CWCoreWeave | $0.76 | $2.42 | $0.14 | 262K | fp4 | ✕ | ✕ | — | 99.8% |
| MOMorph | $0.842 | $3.14 | $0.168 | 1.05M | fp4 | 4.3s° | 30° tok/s | — | 94.8% |
 Alibaba | $0.966 | $3.04 | $0.193 | 1.05M | fp8 | 0.94s° | 75° tok/s | — | 100.0% |
| REReka | $1.10 | $3.75 | — | 262K | fp8 | — | — | — | 100.0% |
 SiliconFlow | $1.19 | $3.74 | $0.221 | 1.05M | fp8 | 1.7s° | 87° tok/s | — | 100.0% |
| PHPhala | $1.26 | $3.00 | $0.22 | 1.05M | fp8 | 1.8s° | 84° tok/s | — | 100.0% |
| ATAtlasCloud | $1.26 | $3.96 | $0.234 | 1.05M | fp8 | 1.1s° | 59° tok/s | — | 100.0% |
| WAWafer | $1.26 | $3.96 | $0.234 | 1.05M | fp4 | 5.2s° | 100° tok/s | — | 99.8% |
| BABaidu | $1.40 | $4.40 | $0.26 | 1.05M | fp8 | 0.82s° | 72° tok/s | 2/5 | 99.6% |
 Mistral | $1.40 | $4.40 | $0.14 | 1.05M | — | 0.95s° | 121° tok/s | — | 98.9% |
| RERelace | $1.40 | $4.40 | $0.14 | 1.05M | fp8 | — | — | — | 96.0% |
| GMIGMICloud | $1.40 | $4.40 | $0.26 | 1.05M | fp8 | 1.5s° | 99° tok/s | — | 99.9% |
 Fireworks | $1.40 | $4.40 | $0.14 | 1.05M | — | 1.4s | 101 tok/s | — | 99.8% |
 Cloudflare | $1.40 | $4.40 | $0.26 | 262K | — | 1.1s° | 75° tok/s | — | 100.0% |
 Z.AI1ST PARTY | $1.40 | $4.40 | $0.26 | 1.05M | fp8 | ✕ | ✕ | — | 100.0% |
 Parasail | $1.40 | $4.40 | $0.26 | 262K | fp4 | 0.69s° | 280° tok/s | — | 100.0% |
 Together | $1.40 | $4.40 | $0.26 | 512K | — | 0.54s° | 131° tok/s | — | 99.6% |
 Crusoe | $1.40 | $4.40 | $0.26 | 1.05M | fp8 | 0.7s° | 177° tok/s | — | 99.2% |
 BaseTen | $1.40 | $4.40 | $0.14 | 1.05M | fp8 | 0.96s° | 96° tok/s | — | 99.8% |
 Venice | $1.40 | $4.40 | $0.26 | 1M | fp8 | 1.5s° | 77° tok/s | — | 97.8% |
 Friendli | $1.40 | $4.40 | $0.26 | 1.05M | — | 1.1s° | 200° tok/s | — | 99.9% |
| Cloudflare | $2.10 | $6.60 | $0.21 | 262K | — | — | — | — | 99.9% |
| Fireworks | $2.10 | $6.60 | $0.21 | 1.05M | — | — | — | — | 97.9% |
| Fireworks | $2.10 | $6.60 | $0.21 | 1.05M | — | — | — | — | 99.0% |
| BaseTen | $2.10 | $6.60 | $0.21 | 1.05M | fp8 | — | — | — | 99.8% |
| Alibaba | $2.31 | $7.26 | $0.462 | 1.05M | fp8 | — | — | — | 100.0% |
TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured against the provider API directly; ° = routed via OpenRouter (adds a hop) · ✕ = probed, endpoint returned no measurable stream · SMOKE: of 5 programmatic capability probes passed (JSON schema, instruction following, tool call, long-context, benign compliance; retry-once) · screened via OpenRouter routing · v0.1 · methodology v1.1 · measured 42 hours ago
Pricing variants · USD / MTok in / out
STANDARD
$0.336 / $1.06
per MTok in / out
BATCH
$1.40 / $4.40
async batch
FREE
Free / Free
per MTok in / out
CACHE READ $0.062
Recent changesRSS ↗
Aug 24, 2026endpoint added32 → 34
About
GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...
Specifications
Context window1,048,576
Max output131,072
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedJun 16, 2026
TokenizerOther
WeightsHugging Face ↗
Embed badge
[](https://modelindex.ai/models/z-ai/glm-5.2)Sources
OpenRouter API12 hours ago
AGGREGATORHugging Face12 hours ago
COMMUNITYModelIndex benchmarks42 hours ago
MEASUREDVerified 12 hours ago · list prices, not negotiated rates.