GLM 5.3
by Z.ai · z-ai/glm-5.3
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...
- Input / 1M tokens
- $0.08
- Output / 1M tokens
- $3.60
- Context
- 1.05M
Specs
| Input price | $0.08 / 1M tokens |
|---|---|
| Output price | $3.60 / 1M tokens |
| Cached input | $0.076 / 1M tokens |
| Context window | 1.05M tokens |
| Max output | 944K tokens |
| Reads | text |
| Writes | text |
| Tool calling | Yes |
| Reasoning | Yes |
| Listed | Aug 18, 2026 |
List prices in USD, updated Oct 30, 2026. Providers may charge differently.
Providers
49 providers serve this model, as of Oct 30, 2026, 18:12 UTC.
| Provider | Quantization | Context | Max output | Input / 1M | Output / 1M | Cache read / 1M | Uptime (30 min) | Latency (median) | Throughput (median) | Supports | Status |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Baidu | fp8 | 1.05M | 131K | $0.28 | $0.88 | $0.052 | 100% | 1.13 s | 74 tok/s | Normal | |
| Wafer | fp4 | 1.05M | 944K | $0.0699 | $1.40 | $0.0689 | 100% | 501 ms | 106 tok/s | Normal | |
| Morph | fp8 | 1.05M | 944K | $0.086 | $1.40 | $0.069 | 100% | 1.19 s | 30 tok/s | Normal | |
| Wafer | fp4 | 1.05M | 944K | $0.179 | $1.40 | $0.178 | 100% | 307 ms | 97 tok/s | Normal | |
| Reka | — | 1.05M | 262K | $0.14 | $2.10 | $0.105 | 100% | 726 ms | 61 tok/s | Normal | |
| Sail Research | fp8 | 1.05M | 944K | $0.50 | $2.00 | $0.08 | 100% | 1.09 s | 44 tok/s | Normal | |
| Sail Research | fp8 | 1.05M | 944K | $0.50 | $2.00 | $0.08 | 100% | 880 ms | 45 tok/s | Normal | |
| Novita | fp8 | 1.05M | 131K | $0.63 | $1.98 | $0.117 | 100% | 2.30 s | 50 tok/s | Normal | |
| GMICloud | fp8 | 1.05M | 944K | $0.70 | $2.20 | $0.13 | 100% | 7.65 s | 22 tok/s | Normal | |
| SiliconFlow | fp8 | 1.05M | 262K | $0.70 | $2.20 | $0.13 | 100% | 2.01 s | 75 tok/s | Normal | |
| DeepInfra | fp4 | 1.05M | 131K | $0.563 | $2.50 | $0.125 | 100% | 748 ms | 63 tok/s | Normal | |
| Tenstorrent | fp8 | 1.04M | 131K | $0.60 | $2.50 | $0.10 | 100% | 1.16 s | 94 tok/s | Normal | |
| DekaLLM | — | 1.05M | 944K | $0.18 | $2.95 | $0.15 | 100% | 1.27 s | 55 tok/s | Normal | |
| Makora | fp4 | 1.05M | 128K | $0.14 | $3.00 | $0.10 | 100% | 842 ms | 86 tok/s | Normal | |
| Phala | — | 1.05M | 944K | $0.84 | $2.64 | $0.156 | 100% | 1.85 s | 48 tok/s | Normal | |
| Decart | fp4 | 1.05M | 944K | $0.84 | $2.69 | $0.19 | 100% | 792 ms | 99 tok/s | Normal | |
| Io Net | fp8 | 262K | 131K | $0.33 | $3.20 | $0.31 | 100% | 1.81 s | 77 tok/s | Normal | |
| InferenceNet | fp4 | 1.05M | 944K | $0.08 | $3.60 | $0.076 | 100% | 449 ms | 134 tok/s | Normal | |
| InferenceNet | fp4 | 1.05M | 944K | $0.08 | $3.60 | $0.076 | 100% | 459 ms | 131 tok/s | Normal | |
| DigitalOcean | — | 1.05M | 128K | $0.91 | $2.86 | $0.169 | 100% | 796 ms | 82 tok/s | Normal | |
| Inceptron | fp4 | 1.05M | 944K | $1.40 | $2.64 | $0.14 | 100% | 434 ms | 106 tok/s | Normal | |
| Fireworks | — | 1.05M | 944K | $0.98 | $3.08 | $0.182 | — | — | — | Code -5 | |
| PrimeIntellect | — | 1.05M | 131K | $0.98 | $3.08 | $0.182 | 100% | 488 ms | 101 tok/s | Normal | |
| Relace | — | 1.05M | 131K | $0.0703 | $4.38 | $0.0703 | 100% | 1.91 s | 81 tok/s | Normal | |
| AkashML | fp8 | 1.05M | 131K | $0.19 | $4.40 | $0.19 | 100% | 1.26 s | 77 tok/s | Normal | |
| Alibaba | — | 1M | 131K | $1.19 | $3.74 | $0.238 | — | 2.23 s | 45 tok/s | Normal | |
| CoreWeave | fp8 | 1.05M | 944K | $1.20 | $4.00 | $0.19 | 100% | 656 ms | 99 tok/s | Normal | |
| Friendli | — | 1.05M | 944K | $1.26 | $3.96 | $0.234 | 100% | 312 ms | 109 tok/s | Normal | |
| AtlasCloud | fp8 | 1.05M | 131K | $1.40 | $4.40 | $0.26 | — | 3.38 s | 50 tok/s | Normal | |
| BaseTen | fp4 | 1.05M | 262K | $1.40 | $4.40 | $0.14 | 100% | 2.42 s | 57 tok/s | Normal | |
| BaseTen | fp4 | 1.05M | 262K | $1.40 | $4.40 | $0.14 | — | 2.83 s | 24 tok/s | Normal | |
| Cloudflare | — | 1.05M | 944K | $1.40 | $4.40 | $0.26 | — | 4.09 s | 31 tok/s | Normal | |
| Crusoe | fp4 | 1.05M | 944K | $1.40 | $4.40 | $0.26 | 100% | 510 ms | 119 tok/s | Normal | |
| Fireworks | — | 1.05M | 944K | $1.40 | $4.40 | $0.26 | 100% | 788 ms | 83 tok/s | Normal | |
| Mistral | nvfp4 | 1.05M | 131K | $1.40 | $4.40 | $0.14 | 100% | 832 ms | 100 tok/s | Normal | |
| Mistral | nvfp4 | 1.05M | 131K | $1.40 | $4.40 | $0.14 | 100% | 579 ms | 101 tok/s | Normal | |
| Modal | — | 1.05M | 944K | $1.40 | $4.40 | $0.26 | 100% | 361 ms | 130 tok/s | Normal | |
| Nebius | fp4 | 1.05M | 944K | $1.40 | $4.40 | $0.26 | 0% | 1.07 s | 92 tok/s | Normal | |
| Parasail | fp8 | 1.05M | 944K | $1.40 | $4.40 | $0.26 | 100% | 558 ms | 130 tok/s | Normal | |
| Together | — | 1.05M | 944K | $1.40 | $4.40 | $0.26 | 100% | 557 ms | 103 tok/s | Normal | |
| Venice | — | 1M | 131K | $1.40 | $4.40 | $0.26 | — | 640 ms | 91 tok/s | Normal | |
| Z.AI | fp8 | 1.05M | 131K | $1.40 | $4.40 | $0.26 | 100% | 1.56 s | 53 tok/s | Normal | |
| Mistral | nvfp4 | 1.05M | 131K | $1.54 | $4.84 | $0.154 | 100% | 423 ms | 185 tok/s | Normal | |
| Amazon Bedrock | — | 1.05M | 131K | $1.68 | $5.28 | $0.312 | 100% | 1.84 s | 109 tok/s | Normal | |
| BaseTen | fp8 | 1.05M | 262K | $2.10 | $6.60 | $0.21 | 100% | 1.14 s | 140 tok/s | Normal | |
| BaseTen | fp8 | 1.05M | 262K | $2.10 | $6.60 | $0.21 | 100% | 703 ms | 145 tok/s | Normal | |
| Fireworks | — | 1.05M | 944K | $2.10 | $6.60 | $0.39 | 100% | 738 ms | 142 tok/s | Normal | |
| ModelRun | fp4 | 1.05M | 524K | $2.10 | $6.60 | $0.40 | 100% | 227 ms | 157 tok/s | Normal | |
| Alibaba | — | 1M | 131K | $2.80 | $8.80 | $0.56 | 100% | 1.03 s | 91 tok/s | Normal |
"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.
Usage
#10
by tokens, Oct 29, 2026
664B
tokens that day · 7 days −5%
Data as of 2026-10-30T18:12:03.879Z.All rankings
Related models
- Z.ai
GLM 5.3 Flash
- Input
- $0.018
- Output
- $0.14
- Context
- 1.05M
- Z.ai
GLM 5.2
- Input
- $0.006
- Output
- $7.00
- Context
- 1.05M
- Z.ai
GLM 5.3 Prime
- Input
- $2.80
- Output
- $8.80
- Context
- 1M
- Z.ai
GLM 5.3 FlashX
- Input
- $0.37
- Output
- $1.25
- Context
- 1.05M
- Z.ai
GLM 5.3 Flash (batch)
- Input
- $0.05
- Output
- $0.18
- Context
- 1.05M
- Z.ai
GLM 5.3 (batch)
- Input
- $0.45
- Output
- $2.00
- Context
- 1.05M