GLM
Z.ai's open-weight family, behind the cheap coding subscriptions.
GLM is the model family from Z.ai, and the reason its coding plan turns up in every "cheaper than Claude Code" thread — the weights are published, plenty of providers serve them, and the Flash models are some of the cheapest usable coding models anywhere. The 5.3 line runs to a million tokens of context, with Flash variants that also read images and video. Z.ai's own chat app is listed separately under Chats.
At a glance — GLM 5.3 Flash
- Cost
- $0.045 in · $0.14 out per 1M tokensBudget
- Memory
- 1.3M tokens — about 1,950 pages
- Reads
- Text · Images · Video
- Can do
- Use tools (agents)
- Structured output
- Thinking mode
- Good at
- Coding: better than 80% · Agentic work: better than 91% · Overall: better than 79%
- Reliability
- 99.90% uptime, last 24h
- Released
- Aug 26, 2026
Advanced details
- API model ID
z-ai/glm-5.3-flash- Max output
- 128K tokens
- Cached input
- $0.01 per 1M
- Tokenizer
- Other
- Coding index
- 71.5
- Agentic work index
- 50.9
- Overall index
- 41.8
Providers
The same model, hosted by different companies. OpenRouter picks one per request and falls back to the next if it fails.
| Provider | Input /1M | Output /1M | Cached /1M | Max output | Uptime 24h |
|---|---|---|---|---|---|
| InferenceNet · fp4 | $0.045 | $0.14 | $0.01 | 128K | 99.41% |
| Sail Research · us | $0.045 | $0.60 | $0.029 | 131K | 99.64% |
| Sail Research · fp8 | $0.045 | $0.60 | $0.029 | 131K | 99.85% |
| OpenInference · fp4 | $0.05 | $0.50 | $0.015 | 944K | 99.90% |
| Relace | $0.07 | $0.28 | $0.02 | 131K | 99.85% |
| DeepInfra · fp4 | $0.075 | $0.25 | $0.015 | 131K | 99.77% |
| Wafer | $0.089 | $0.35 | $0.03 | 944K | 99.77% |
| GMICloud · fp8 | $0.09 | $0.30 | $0.018 | 944K | 99.38% |
| Morph | $0.098 | $0.343 | $0.02 | 944K | 96.73% |
| Inceptron · fp8 | $0.11 | $0.45 | $0.07 | 944K | 99.28% |
| Decart · fp4 | $0.128 | $0.425 | $0.026 | 944K | 98.60% |
| Phala · fp8Degraded | $0.128 | $0.425 | $0.026 | 131K | 98.31% |
| Novita · fp8 | $0.132 | $0.44 | $0.026 | 131K | 99.73% |
| StreamLake · fp8 | $0.141 | $0.47 | $0.028 | 128K | 99.46% |
| Modal · nvfp4 | $0.15 | $0.50 | $0.03 | 944K | 99.74% |
| BaseTen · fp8 | $0.15 | $0.50 | $0.03 | 131K | 99.16% |
| Near AI · fp8 | $0.15 | $0.50 | $0.035 | 131K | 99.52% |
| Crusoe · fp4 | $0.15 | $0.50 | $0.03 | 944K | 99.42% |
| CoreWeave · nvfp4 | $0.15 | $0.50 | $0.05 | 944K | 98.51% |
| AtlasCloud · fp8 | $0.15 | $0.50 | $0.03 | 131K | 99.56% |
| Fireworks | $0.15 | $0.50 | $0.03 | 944K | 99.53% |
| Friendli | $0.15 | $0.50 | $0.03 | 944K | 99.55% |
| SiliconFlow · fp8 | $0.15 | $0.50 | $0.03 | 262K | 99.75% |
| DigitalOcean | $0.15 | $0.50 | $0.03 | 944K | 99.14% |
| Together | $0.15 | $0.50 | $0.03 | 944K | 99.87% |
| Reka | $0.15 | $0.50 | $0.03 | 236K | 99.49% |
| Parasail · fp8 | $0.15 | $0.50 | $0.03 | 944K | 99.30% |
| BaseTen · fp8 | $0.15 | $0.50 | $0.03 | 131K | 99.24% |
| Venice | $0.15 | $0.50 | $0.03 | 131K | 99.29% |
| Io Net · fp8 | $0.15 | $0.50 | $0.03 | 66K | 99.06% |
| Z.AI · fp8 | $0.15 | $0.50 | $0.03 | 131K | 99.07% |
| NextBit · fp8 | $0.165 | $0.55 | $0.033 | 128K | 99.83% |
| Cloudflare | $0.30 | $1.00 | $0.03 | 1.2M | 99.86% |
Supported parameters
- frequency_penalty
- include_reasoning
- logit_bias
- logprobs
- max_tokens
- min_p
- parallel_tool_calls
- presence_penalty
- reasoning
- reasoning_effort
- repetition_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_k
- top_logprobs
- top_p
Live from OpenRouter, refreshed hourly. Scores from Artificial Analysis.
Key info
- Pricing
- Open source
- Category
- Models
- Best for
- Intermediate
- Made by
- Z.ai
- Weights
- Open
- Good for
- Coding on a budget