In force now
26 Oct 2026 · First recorded terms
Input 0.34 USD / 1M tokensOutput 4.48 USD / 1M tokens
Loading…
Your privacy choices
Necessary storage keeps the site working. Analytics and advertising stay off unless you allow them. Cookie notice
Only published terms. A tier or mode the provider does not publish is written out, never interpolated from another one.
Standard · Any prompt size
| Component | PriceUSD / 1M tokens |
|---|---|
| Input (uncached) | 0.34 |
| Output | 4.48 |
Each route is a separate deployment of this offer with its own published prices. Only published prices are shown.
| Route | Input | Output | Last checked |
|---|---|---|---|
| GLM-5.3 | 0.34 | 4.48 |
Every published revision of this offer, newest last in the chart. Earlier terms are kept; a correction adds a revision; a change of model version is marked as a break.
Only one set of terms is recorded, so there is no chart yet. The revision is listed below.
Input 0.34 USD / 1M tokensOutput 4.48 USD / 1M tokens
Other providers, tiers and subscriptions for the same model version. Prices differ by provider, region and conditions.
| Provider | Input | Output | Cached input | Cache write |
|---|---|---|---|---|
| OpenRouter45 routes · from 0.0699 | ||||
| GLM-5.3, OpenRouter, Upstream provider: Wafer, Quantization: FP4, Region: USUpstream provider — the company actually serving this routeQuantization — numeric precision of the served weightsRegion — where this route is served | 0.0699 | 1.40 | 0.0689 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Morph, Quantization: FP8Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 0.07 | 1.40 | 0.069 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: RelaceUpstream provider — the company actually serving this route | 0.0703 | 4.38 | 0.0703 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Relace, Quantization: FP4Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 0.0703 | 4.38 | 0.0703 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: InferenceNet, Quantization: FP4, Region: USUpstream provider — the company actually serving this routeQuantization — numeric precision of the served weightsRegion — where this route is served | 0.08 | 3.60 | 0.076 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: InferenceNet, Quantization: FP4Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 0.08 | 3.60 | 0.076 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Wafer, Quantization: FP4Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 0.179 | 1.40 | 0.178 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Makora, Quantization: FP4Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 0.18 | 3.00 | 0.125 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: DekaLLMUpstream provider — the company actually serving this route | 0.18 | 2.95 | 0.15 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: AkashML, Quantization: FP8Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 0.19 | 4.40 | 0.19 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: AkashML, Quantization: FP4Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 0.19 | 4.40 | 0.19 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Io Net, Quantization: FP8Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 0.33 | 3.20 | 0.31 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: PrimeIntellectUpstream provider — the company actually serving this route | 0.40 | 2.46 | 0.0744 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Sail Research, Quantization: FP8Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 0.50 | 2.00 | 0.08 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Decart, Quantization: FP4Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 0.56 | 1.78 | 0.10 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Tenstorrent, Quantization: FP8Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 0.60 | 2.50 | 0.10 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: CloudflareUpstream provider — the company actually serving this route | 0.70 | 2.20 | 0.13 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Sail Research, Quantization: FP8, Region: USUpstream provider — the company actually serving this routeQuantization — numeric precision of the served weightsRegion — where this route is served | 0.75 | 3.00 | 0.12 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: CoreWeave, Quantization: NVFP4Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 0.75 | 3.00 | 0.19 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: DigitalOceanUpstream provider — the company actually serving this route | 0.91 | 2.86 | 0.169 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Inceptron, Quantization: FP4Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 1.00 | 3.08 | 0.14 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: AlibabaUpstream provider — the company actually serving this routeRoute ID: alibaba | 1.19 | 3.74 | 0.238 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: CoreWeave, Quantization: FP8Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 1.20 | 4.00 | 0.19 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: AtlasCloud, Quantization: FP8Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 1.40 | 4.40 | 0.26 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Mistral, Quantization: NVFP4Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weightsRoute ID: mistral/zdr | 1.40 | 4.40 | 0.14 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Nebius, Quantization: FP4Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 1.40 | 4.40 | 0.26 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Fireworks AIUpstream provider — the company actually serving this routeRoute ID: fireworks | 1.40 | 4.40 | 0.26 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Mistral, Quantization: NVFP4Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weightsRoute ID: mistral/nvfp4 | 1.40 | 4.40 | 0.14 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Parasail, Quantization: FP8Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weightsRoute ID: parasail/fp8 | 1.40 | 4.40 | 0.26 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Baseten, Quantization: FP4, Region: USUpstream provider — the company actually serving this routeQuantization — numeric precision of the served weightsRegion — where this route is served | 1.40 | 4.40 | 0.14 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Z.AI, Quantization: FP8Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 1.40 | 4.40 | 0.26 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: ModalUpstream provider — the company actually serving this route | 1.40 | 4.40 | 0.26 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Baseten, Quantization: FP4Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 1.40 | 4.40 | 0.14 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Together AIUpstream provider — the company actually serving this route | 1.40 | 4.40 | 0.26 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Crusoe, Quantization: FP4Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 1.40 | 4.40 | 0.26 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Baidu, Quantization: FP8Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 1.40 | 4.40 | 0.26 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Mistral, Quantization: NVFP4, Region: EUUpstream provider — the company actually serving this routeQuantization — numeric precision of the served weightsRegion — where this route is served | 1.54 | 4.84 | 0.154 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Amazon Bedrock, Region: us-east-1Upstream provider — the company actually serving this routeRegion — where this route is served | 1.68 | 5.28 | 0.312 | 2.10 |
| GLM-5.3, OpenRouter, Upstream provider: Baseten, Quantization: FP8Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 2.10 | 6.60 | 0.21 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Fireworks AIUpstream provider — the company actually serving this routeRoute ID: fireworks/fast | 2.10 | 6.60 | 0.39 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Baseten, Quantization: FP8, Region: USUpstream provider — the company actually serving this routeQuantization — numeric precision of the served weightsRegion — where this route is served | 2.10 | 6.60 | 0.21 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: ModelRun, Quantization: FP4Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weights | 2.10 | 6.60 | 0.40 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: Parasail, Quantization: FP8Upstream provider — the company actually serving this routeQuantization — numeric precision of the served weightsRoute ID: parasail/fast | 2.10 | 6.60 | 0.26 | Not published |
| GLM-5.3, OpenRouter, Upstream provider: AlibabaUpstream provider — the company actually serving this routeRoute ID: alibaba/prime | 2.80 | 8.80 | 0.56 | Not published |
| OpenRouter | Not published | Not published | Not published | Not published |
| SCX.ai | 0.98 | 3.08 | 0.18 | Not published |
| ai& | 1.00 | 4.00 | 0.30 | Not published |
| Alibaba (China) | 1.10 | 3.85 | 0.275 | Free |
| Boundless | 1.12 | 3.52 | 0.14 | Not published |
| Kyma | 1.18 | 3.70 | Not published | Not published |
| CoreWeave | 1.20 | 4.00 | 0.19 | Not published |
| AI/ML API | 1.40 | 4.40 | 0.26 | Not published |
| Arcee | 1.40 | 4.40 | 0.26 | Not published |
| ClinePass | 1.40 | 4.40 | 0.26 | Not published |
| Cloudflare Workers AI | 1.40 | 4.40 | 0.26 | Not published |
| Bothub | 1.42 | 4.48 | Not published | Not published |
| Amazon Bedrock | 1.85 | 5.81 | 0.3432 | 2.31 |
| AIHubMix | Free | Free | Not published | Not published |
| Alibaba Token Plan | Free | Free | Free | Free |
| Bigmodel | Not published | 4.00 | Not published | Not published |