GLM 5.3 Flash
by Z.ai · z-ai/glm-5.3-flash
GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...
- Input / 1M tokens
- $0.018
- Output / 1M tokens
- $0.14
- Context
- 1.05M
Specs
| Input price | $0.018 / 1M tokens |
|---|---|
| Output price | $0.14 / 1M tokens |
| Cached input | $0.018 / 1M tokens |
| Context window | 1.05M tokens |
| Max output | 131K tokens |
| Reads | text, image, video |
| Writes | text |
| Tool calling | Yes |
| Reasoning | Yes |
| Listed | Aug 26, 2026 |
List prices in USD, updated Oct 30, 2026. Providers may charge differently.
Providers
40 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| OpenInference | fp4 | 1.05M | 944K | $0.0189 | $0.0569 | $0.0172 | 100% | 461 ms | 108 tok/s | Normal | |
| Relace | — | 1.05M | 131K | $0.018 | $0.14 | $0.018 | 100% | 816 ms | 57 tok/s | Normal | |
| Darkbloom | fp4 | 262K | 65.5K | $0.065 | $0.18 | $0.012 | — | 15.24 s | 4 tok/s | Normal | |
| Wafer | nvfp4 | 1.05M | 131K | $0.048 | $0.20 | $0.047 | 100% | 446 ms | 125 tok/s | Normal | |
| Wafer | nvfp4 | 1.05M | 131K | $0.054 | $0.20 | $0.053 | 100% | 452 ms | 117 tok/s | Normal | |
| GMICloud | fp8 | 1.05M | 944K | $0.075 | $0.25 | $0.015 | 100% | 1.76 s | 94 tok/s | Normal | |
| Morph | fp8 | 1.05M | 944K | $0.042 | $0.30 | $0.018 | 100% | 898 ms | 43 tok/s | Normal | |
| Novita | fp8 | 1.05M | 131K | $0.084 | $0.28 | $0.0168 | 100% | 3.14 s | 45 tok/s | Normal | |
| StreamLake | fp8 | 1.02M | 128K | $0.0885 | $0.295 | $0.0177 | 100% | 2.02 s | 37 tok/s | Normal | |
| Reka | — | 1.05M | 944K | $0.12 | $0.30 | $0.03 | 100% | 896 ms | 81 tok/s | Normal | |
| InferenceNet | fp4 | 1.05M | 262K | $0.108 | $0.35 | $0.032 | 100% | 291 ms | 89 tok/s | Normal | |
| InferenceNet | fp4 | 1.05M | 262K | $0.108 | $0.35 | $0.032 | 100% | 473 ms | 98 tok/s | Normal | |
| DigitalOcean | — | 1.05M | 131K | $0.113 | $0.375 | $0.03 | 100% | 837 ms | 95 tok/s | Normal | |
| CoreWeave | nvfp4 | 1.05M | 944K | $0.12 | $0.38 | $0.02 | 100% | 704 ms | 117 tok/s | Normal | |
| NextBit | fp4 | 1.05M | 128K | $0.11 | $0.44 | $0.03 | 100% | 2.67 s | 33 tok/s | Normal | |
| Phala | nvfp4 | 1.05M | 131K | $0.128 | $0.425 | $0.0255 | 100% | 3.41 s | 42 tok/s | Normal | |
| Near AI | fp8 | 1.05M | 944K | $0.08 | $0.50 | $0.012 | 100% | 1.09 s | 22 tok/s | Normal | |
| Makora | — | 1.05M | 131K | $0.14 | $0.47 | $0.024 | 100% | 931 ms | 77 tok/s | Normal | |
| AtlasCloud | fp8 | 1.05M | 131K | $0.15 | $0.50 | $0.03 | — | 3.79 s | 26 tok/s | Normal | |
| BaseTen | fp8 | 1.05M | 131K | $0.15 | $0.50 | $0.03 | — | 653 ms | 78 tok/s | Normal | |
| BaseTen | fp8 | 1.05M | 131K | $0.15 | $0.50 | $0.03 | 100% | 866 ms | 71 tok/s | Normal | |
| Cohere | — | 1.05M | 131K | $0.15 | $0.50 | $0.03 | 100% | 766 ms | 85 tok/s | Normal | |
| Crusoe | fp4 | 1.05M | 944K | $0.15 | $0.50 | $0.03 | 100% | 892 ms | 115 tok/s | Normal | |
| DeepInfra | fp4 | 1.05M | 944K | $0.15 | $0.50 | $0.03 | 100% | 1.29 s | 59 tok/s | Normal | |
| Fireworks | — | 1.05M | 944K | $0.15 | $0.50 | $0.03 | 100% | 761 ms | 117 tok/s | Normal | |
| Friendli | — | 1.05M | 944K | $0.15 | $0.50 | $0.03 | 100% | 905 ms | 75 tok/s | Normal | |
| Mistral | — | 1.05M | 131K | $0.15 | $0.50 | $0.03 | 100% | 835 ms | 116 tok/s | Normal | |
| Modal | fp4 | 1.05M | 944K | $0.15 | $0.50 | $0.03 | 100% | 423 ms | 82 tok/s | Normal | |
| Nebius | fp4 | 1.05M | 944K | $0.15 | $0.50 | $0.03 | 100% | 958 ms | 107 tok/s | Normal | |
| Parasail | fp4 | 1.05M | 944K | $0.15 | $0.50 | $0.03 | 100% | 2.37 s | 41 tok/s | Normal | |
| Particle AI | nvfp4 | 1.05M | 131K | $0.15 | $0.50 | $0.03 | 100% | 681 ms | 108 tok/s | Normal | |
| PrimeIntellect | — | 1.05M | 131K | $0.15 | $0.50 | $0.03 | 100% | 844 ms | 45 tok/s | Normal | |
| Sail Research | fp4 | 1.05M | 131K | $0.15 | $0.50 | $0.03 | — | — | — | Normal | |
| Sail Research | fp4 | 1.05M | 131K | $0.15 | $0.50 | $0.03 | — | — | — | Normal | |
| SiliconFlow | fp8 | 1.05M | 262K | $0.15 | $0.50 | $0.03 | 100% | 1.89 s | 36 tok/s | Normal | |
| Together | — | 1.05M | 944K | $0.15 | $0.50 | $0.03 | 100% | 956 ms | 75 tok/s | Normal | |
| Venice | — | 1.05M | 131K | $0.15 | $0.50 | $0.03 | 100% | 1.03 s | 116 tok/s | Normal | |
| Z.AI | fp8 | 1.05M | 131K | $0.15 | $0.50 | $0.03 | 100% | 2.08 s | 37 tok/s | Normal | |
| Inceptron | fp8 | 1.05M | 944K | $0.19 | $0.60 | $0.06 | 100% | 623 ms | 93 tok/s | Normal | |
| Fireworks | — | 1.05M | 944K | $0.225 | $0.75 | $0.045 | 100% | 1.09 s | 73 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
#3
by tokens, Oct 29, 2026
2.52T
tokens that day · 7 days +37%
Data as of 2026-10-30T18:12:03.879Z.All rankings
Related models
- Z.ai
GLM 5.3
- Input
- $0.08
- Output
- $3.60
- 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