Z.ai: GLM 5.3
by Z.aiZ.ai: GLM 5.3 is a large language model from Z.ai. It costs $0.070 per million input tokens and $1.40 per million output tokens. Its context window is 1.0M tokens.
- Input / 1M tokens
- $0.070
- Output / 1M tokens
- $1.40
- Cached input / 1M
- $0.069
- Context window
- 1.0M
On repeated prefixes
tokens
Who serves it cheapest
38 hosts serve GLM 5.3. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| WaferCheapestfp4 | $0.070 | $1.40 | 1.0M | - | 100.0% |
| Baidufp8 | $0.280 | $0.880 | 1.0M | - | 100.0% |
| Morphfp8 | $0.176 | $1.54 | 1.0M | - | 99.1% |
| Reka | $0.140 | $2.10 | 1.0M | - | 99.7% |
| Makorafp4 | $0.140 | $3.00 | 1.0M | - | 99.3% |
| Sail Researchfp8 | $0.500 | $2.00 | 1.0M | - | 100.0% |
| DekaLLM | $0.250 | $2.95 | 1.0M | - | 99.9% |
| InferenceNetfp4 | $0.080 | $3.60 | 1.0M | - | 100.0% |
| Novitafp8 | $0.630 | $1.98 | 1.0M | - | 99.7% |
| DeepInfrafp4 | $0.563 | $2.50 | 1.0M | - | 98.2% |
| Io Netfp8 | $0.330 | $3.20 | 262K | - | 99.9% |
| Tenstorrentfp8 | $0.600 | $2.50 | 1.0M | - | 99.8% |
| SiliconFlowfp8 | $0.700 | $2.20 | 1.0M | - | 99.9% |
| GMICloudfp8 | $0.700 | $2.20 | 1.0M | - | 100.0% |
| Relace | $0.070 | $4.38 | 1.0M | - | 100.0% |
| AkashMLfp8 | $0.190 | $4.40 | 1.0M | - | 100.0% |
| Phala | $0.840 | $2.64 | 1.0M | - | 100.0% |
| Decartfp4 | $0.840 | $2.69 | 1.0M | - | 100.0% |
| DigitalOcean | $0.910 | $2.86 | 1.0M | - | 99.5% |
| Inceptronfp4 | $1.20 | $2.20 | 1.0M | - | 99.9% |
| Fireworks | $0.980 | $3.08 | 1.0M | - | 76.7% |
| PrimeIntellect | $0.980 | $3.08 | 1.0M | - | 99.5% |
| Alibaba | $1.19 | $3.74 | 1M | - | 100.0% |
| CoreWeavefp8 | $1.20 | $4.00 | 1.0M | - | 98.9% |
| Friendli | $1.26 | $3.96 | 1.0M | - | 100.0% |
| Mistralnvfp4 | $1.40 | $4.40 | 1.0M | - | 99.9% |
| BaseTenfp4 | $1.40 | $4.40 | 1.0M | - | 100.0% |
| Nebiusfp4 | $1.40 | $4.40 | 1.0M | - | 94.0% |
| Crusoefp4 | $1.40 | $4.40 | 1.0M | - | 100.0% |
| Venice | $1.40 | $4.40 | 1M | - | 99.6% |
| Together | $1.40 | $4.40 | 1.0M | - | 100.0% |
| Parasailfp8 | $1.40 | $4.40 | 1.0M | - | 100.0% |
| Modal | $1.40 | $4.40 | 1.0M | - | 100.0% |
| Cloudflare | $1.40 | $4.40 | 1.0M | - | 100.0% |
| AtlasCloudfp8 | $1.40 | $4.40 | 1.0M | - | 100.0% |
| Z.AIfp8 | $1.40 | $4.40 | 1.0M | - | 100.0% |
| Amazon Bedrock | $1.68 | $5.28 | 1.0M | - | 74.1% |
| ModelRunfp4 | $2.10 | $6.60 | 1.0M | - | 100.0% |
The spread between Wafer and ModelRun is 8.0× for identical weights. Quantization and context limits differ, so check both columns before switching.
Benchmarks
Independent scores published alongside the catalogue.
- Intelligence index
- 31.7
- Coding index
- 74.8
- Agentic index
- 53.1
About 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...
Specifications
| Model ID | z-ai/glm-5.3 |
|---|---|
| Provider | Z.ai |
| Context window | 1.0M tokens |
| Max output | 944K tokens |
| Input modalities | text |
| Output modalities | text |
| Knowledge cutoff | - |
| Open weights | Yes - zai-org/GLM-5.3 |
| Released | August 18, 2026 |
Cheaper alternatives
Models that cost less than GLM 5.3 while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does Z.ai: GLM 5.3 cost?
$0.070 per million input tokens and $1.40 per million output tokens. Cached input reads cost $0.069 per million tokens.
What is the context window of Z.ai: GLM 5.3?
1.0M tokens, with up to 944K tokens of output per request.
Which provider serves Z.ai: GLM 5.3 cheapest?
Wafer at $0.070 per million input tokens - 8.0× cheaper than ModelRun, the most expensive of the 38 hosts serving it.
Confirm against the source: Z.ai official pricing.