GLM-5.3 z-ai/glm-5.3
Served by 22 providers. Cheapest: Inference.net at $1.43 blended /1M tokens. The most expensive listing costs 1.9× as much for the same model.
| Provider | Type | Input /1M | Output /1M | Cached input | Blended | Context | Notes | Source |
|---|---|---|---|---|---|---|---|---|
| Inference.net glm-5.3 |
Inference hosts | $0.90 | $3 | $0.15 | $1.43 | 1M | https://inference.net/models shows the same figures |
✓ src 2026-09-18 |
| DigitalOcean glm-5.3 |
Inference hosts | $0.95 | $3.40 | $0.20 | $1.56 | 1.05M | DO models page: weights not yet published. |
✓ src src2 2026-09-18 |
| DeepInfra zai-org/GLM-5.3 |
Inference hosts | $1.20 | $4 | — | $1.90 | 1.05M | fp4 Price columns are DeepInfra's list price; its models API flags a 25% promotional discount on this model (no end date given), so billed price is lower. |
✓ src src2 2026-09-18 |
| AkashML zai-org/GLM-5.3 |
Inference hosts | $1.30 | $4.40 | $0.26 | $2.08 | — | Limited Trial. |
✓ src src2 2026-09-18 |
| Atlas Cloud zai-org/glm-5.3 |
Inference hosts | $1.40 | $4.40 | $0.26 | $2.15 | 1.05M | fp8 |
✓ src 2026-09-18 |
| Baseten | Inference hosts | $1.40 | $4.40 | $0.14 | $2.15 | — | Model API id not shown on pricing page. |
◐ src 2026-09-18 |
| Cloudflare Workers AI @cf/zai-org/glm-5.3 |
Inference hosts | $1.40 | $4.40 | $0.26 | $2.15 | — | Billed in neurons ($0.011/1k neurons); USD per-M-token equivalent as published by Cloudflare; requires Workers Paid or AI Gateway credits |
✓ src 2026-09-18 |
| Crusoe | Inference hosts | $1.40 | $4.40 | $0.26 | $2.15 | — |
✓ src 2026-09-18 |
|
| Featherless zai-org/GLM-5.3 |
Inference hosts | $1.40 | $4.40 | — | $2.15 | 262k | Developer-plan per-token rate; model_class glm-moe-dsa-753b3; effective price differs from class base rate (docs table class rate $1.0 in/$4.0 out) — niche-model multiplier; also usable flat-rate on $25/mo Chat plan (32K ctx, human chat only) |
✓ src src2 src3 2026-09-18 |
| Fireworks AI accounts/fireworks/models/glm-5p3 |
Inference hosts | $1.40 | $4.40 | $0.26 | $2.15 | — | batch −50% Priority $1.75/$0.325/$5.50; Fast $2.10/$0.39/$6.60 |
✓ src 2026-09-18 |
| FriendliAI zai-org/GLM-5.3 |
Inference hosts | $1.40 | $4.40 | $0.26 | $2.15 | 1.05M | promo "10% OFF" shown: $1.26 in / $0.234 cached / $3.96 out; context from pricing page embedded model data |
✓ src 2026-09-18 |
| GMI Cloud Inference Engine zai-org/GLM-5.3 |
Inference hosts | $1.40 | $4.40 | — | $2.15 | — | list price; currently discounted to $1.05 in / $3.3 out (25% off, effective 2026-08-14); from GMI console public pricing API (console is client-rendered; docs say prices live in console Model Hub) |
✓ src src2 2026-09-18 |
| Mistral AI zai-glm-5-3 |
Model labs | $1.40 | $4.40 | $0.14 | $2.15 | 1M | Third-party model served unmodified by Mistral. |
✓ src src2 2026-09-18 |
| Novita AI zai-org/glm-5.3 |
Inference hosts | $1.40 | $4.40 | $0.26 | $2.15 | 1.05M | Also glm-5.3-p variant at same price. |
✓ src src2 2026-09-18 |
| OpenRouter z-ai/glm-5.3 |
LLM routers | $1.40 | $4.40 | $0.26 | $2.15 | 1.05M | api modality text->text |
✓ src 2026-09-18 |
| Parasail | Inference hosts | $1.40 | $4.40 | $0.26 | $2.15 | — |
✓ src 2026-09-18 |
|
| Requesty zai/glm-5.3 |
LLM routers | $1.40 | $4.40 | $0.26 | $2.15 | 1M | upstream route zai; geo sg; 6 other upstream routes listed (input $1.2-$1.75/M); API list price; Requesty's 5% markup on model cost (pricing page) is not included |
✓ src 2026-09-18 |
| SiliconFlow | Inference hosts | $1.40 | $4.40 | $0.26 | $2.15 | — | context shown on pricing page as "1049K" |
✓ src 2026-09-18 |
| Together AI zai-org/GLM-5.3 |
Inference hosts | $1.40 | $4.40 | $0.26 | $2.15 | 1.05M | fp4 |
✓ src 2026-09-18 |
| Z.ai (Zhipu GLM API, international) glm-5.3 |
Model labs | $1.40 | $4.40 | $0.26 | $2.15 | — | Cached-input storage limited-time free. |
✓ src 2026-09-18 |
| Microsoft Foundry (Azure AI Foundry / Azure OpenAI) GLM-5.3 |
Hyperscaler AI platforms | $1.75 | $5.50 | $0.325 | $2.69 | — | Global Standard, Azure Retail Prices API meter 'FW GLM 5.3 Inp Tokens' (eastus); API meter is per 1K tokens, multiplied by 1000 (unit conversion only); sold under Azure Fireworks Models product; meter name has no Global/DZ label |
✓ src src2 2026-09-18 |
| Venice.ai API z-ai-glm-5-3 |
Inference hosts | $1.75 | $5.50 | $0.325 | $2.69 | 1M |
✓ src src2 2026-09-18 |
✓ from the provider's own pricing page · ◐ partly confirmed there · 2° third-party source. Router prices may exclude the router's own fees; see each router's page.