Inworld API pricing
10 Inworld models. Source: https://inworld.ai/models
- Provider type
- Inference host
- Headquarters
- US (outside EU)
- Regions
- unknown
- EU data residency
- unknown
- Residency notes
- Inworld Inference (launched Oct 2026) hosts 'Inworld-optimized' open models on its own GPUs and also routes to third-party providers (those routed models are not listed here). Regions not stated; pricing page mentions GDPR and SOC 2 Type II on every plan. HQ Mountain View, CA (Theai, Inc. dba Inworld AI).
- Residency source
- https://inworld.ai/pricing
HQ country is from public company information; regions and EU residency are only filled from the cited source page, otherwise 'unknown'.
Blend input:output
| Provider | Model | Input | Output | Cached in | Blended 3:1* ▲ | Context | EU residency |
|---|---|---|---|---|---|---|---|
| Inworld Inference host | DeepSeek V4 Flash 0731 | $0.10 | $0.20 | $0.02 | $0.125 | 131K | unknown |
| Inworld Inference host | Gemma 4 26B A4B it | $0.07 | $0.34 | $0.035 | $0.138 | 262K | unknown |
| Inworld Inference host | Gemma 4 31B it | $0.13 | $0.38 | $0.065 | $0.193 | 262K | unknown |
| Inworld Inference host | GLM 5.3 Flash | $0.15 | $0.50 | $0.03 | $0.237 | 131K | unknown |
| Inworld Inference host | Qwen3.8 Flash | $0.16 | $0.47 | $0.016 | $0.237 | — | unknown |
| Inworld Inference host | DeepSeek V4.1 Flash | $0.30 | $1.20 | $0.006 | $0.525 | 131K | unknown |
| Inworld Inference host | Qwen3.8 27B | $0.40 | $3.00 | $0.04 | $1.05 | 262K | unknown |
| Inworld Inference host | GLM 5.2 | $1.20 | $4.10 | $0.20 | $1.92 | — | unknown |
| Inworld Inference host | DeepSeek V4 Pro 0813 | $1.32 | $3.96 | $0.044 | $1.98 | — | unknown |
| Inworld Inference host | GLM 5.3 | $1.40 | $4.40 | $0.26 | $2.15 | — | unknown |
Per 1M tokens, standard (non-promo) list prices; short-context / peak tier where tiered. USD unless shown with € or CHF: those are as published and not converted. Click a header to sort. 10 models.
* Blended assumes 3 input tokens for every output token: (3×input + output) / 4. Your real mix will differ, so use the cost calculator with your own token counts for a real estimate.