GLM 5.1
Z.ai · Open weights · Released Apr 7, 2026 · z-ai/glm-5.1
205K contextToolsReasoningStructured outputPrompt cachingOpen weights
Available from 17 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 |
|---|---|---|---|---|---|---|---|---|---|
| GMIGMICloud | $0.91 | $2.86 | $0.169 | 203K | fp8 | 1.1s | 87 tok/s | 2/5 | 99.8% |
| STStreamLake | $0.966 | $3.04 | $0.179 | 200K | fp8 | 1.1s | 48 tok/s | 1/5 | 99.9% |
| CHChutes | $0.98 | $3.08 | $0.098 | 203K | fp8 | 1.9s | 79 tok/s | 2/5 | 94.0% |
 DeepInfra | $1.05 | $3.50 | $0.205 | 203K | fp4 | 1s | 13 tok/s | 2/5 | 100.0% |
 SiliconFlow | $1.19 | $3.74 | $0.60 | 205K | fp8 | 1.1s | 54 tok/s | 1/5 | 100.0% |
 Crusoe | $1.20 | $4.40 | $0.25 | 203K | fp8 | 1.5s | 110 tok/s | — | 99.2% |
| PHPhala | $1.21 | $4.20 | $0.60 | 203K | — | 1.2s | 83 tok/s | — | 94.0% |
| ATAtlasCloud | $1.26 | $3.96 | $0.234 | 203K | fp8 | 0.95s | 68 tok/s | — | 100.0% |
| DIDigitalOcean | $1.30 | $4.30 | $0.26 | 164K | — | 2.1s | 18 tok/s | — | 99.0% |
 Alibaba | $1.33 | $4.18 | $0.247 | 203K | fp8 | 1.9s | 49 tok/s | — | 100.0% |
 Novita | $1.38 | $4.40 | $0.26 | 205K | fp8 | 2.5s | 38 tok/s | — | 100.0% |
 Nebius | $1.40 | $4.40 | — | 203K | fp8 | 1.8s | 31 tok/s | — | 99.0% |
| BABaidu | $1.40 | $4.40 | $0.26 | 203K | fp8 | 0.79s | 59 tok/s | 2/5 | 100.0% |
 Z.AI1ST PARTY | $1.40 | $4.40 | $0.26 | 203K | fp8 | 4s | 44 tok/s | — | 100.0% |
 Parasail | $1.40 | $4.40 | $0.26 | 203K | fp8 | 1.3s | 132 tok/s | — | 98.9% |
 Friendli | $1.40 | $4.40 | $0.26 | 203K | — | 0.66s | 190 tok/s | — | 100.0% |
 Venice | $1.54 | $4.84 | $0.286 | 200K | fp8 | 1s | 21 tok/s | — | 96.7% |
TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · 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
$0.91 / $2.86
per MTok in / out
CACHE READ $0.169
About
GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...
Specifications
Context window204,800
Max output128,000
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedApr 7, 2026
TokenizerOther
WeightsHugging Face ↗
Embed badge
[](https://modelindex.ai/models/z-ai/glm-5.1)Sources
OpenRouter API12 hours ago
AGGREGATORHugging Face12 hours ago
COMMUNITYModelIndex benchmarks42 hours ago
MEASUREDVerified 12 hours ago · list prices, not negotiated rates.