LLMIteraCompute API pricing
15 IteraCompute models. Source: https://iteracompute.com/models/glm-5-3-flash/
- Provider type
- Inference host
- Server location (where inference runs)
- unknown
- Regions
- unknown
- Company HQ (secondary)
- China (outside EU) · Operated by IteraCompute Artificial Intelligence Technology (Chongqing) Co., Ltd., a company registered in Chongqing, China (Terms of Service, last updated 2026-10-22; Privacy Policy, last updated 2026-10-15). Checked 2026-10-30. · legal source
- EU data residency
- unknown
- Residency notes
- IteraCompute serves models through its own infrastructure and through third-party inference APIs; it does not publish serving regions. Privacy Policy: retention by the inference providers involved is disclosed per service; using a provider's official API does not by itself give a zero-data-retention guarantee. Terms §9: website prices are for general information; binding prices are those in the Console.
- Listing note
- Open-weight models only. IteraCompute's Claude, GPT and Gemini rows are not listed: they are supplied through third-party resellers rather than the model vendor's own or an authorised channel (see /get-listed). Qwen3.8-27B is free during a promotion with no published standard price, so it is not listed either.
- Residency source
- https://iteracompute.com/privacy.html
Primary location is where inference servers run (server region, from the cited source; otherwise 'unknown'). Company HQ is secondary public company information. OpenRouter prices are volatile: refreshed twice daily and excluded from cheapest-price answers.
15 of 15 models.
| Provider | Model | Input | Output | Cached in | Blended 3:1* ▲ | Context | EU residency |
|---|---|---|---|---|---|---|---|
| IteraCompute Inference host | GLM-5.3 Flash | $0.08 | $0.28 | $0.023 | $0.13 | 1.05M | unknown |
| IteraCompute Inference host | Qwen3.8 Flash | $0.11 | $0.38 | $0.016 | $0.177 | 1.05M | unknown |
| IteraCompute Inference host | DeepSeek V4.1 Flash | $0.14 | $0.55 | $0.006 | $0.243 | 1.05M | unknown |
| IteraCompute Inference host | DeepSeek V4.1 Flash 1017 | $0.14 | $0.55 | $0.006 | $0.243 | 1.05M | unknown |
| IteraCompute Inference host | MiniMax M2.5 | $0.27 | $1.03 | $0.03 | $0.46 | 205K | unknown |
| IteraCompute Inference host | MiniMax M3 | $0.30 | $1.19 | $0.05 | $0.522 | 1.05M | unknown |
| IteraCompute Inference host | MiniMax M2.7 | $0.38 | $1.48 | $0.03 | $0.655 | 205K | unknown |
| IteraCompute Inference host | GLM-5.2 | $0.53 | $1.72 | $0.12 | $0.828 | 1.05M | unknown |
| IteraCompute Inference host | DeepSeek V4 Pro 0813 | $0.60 | $1.79 | $0.044 | $0.897 | 1.05M | unknown |
| IteraCompute Inference host | Kimi K2.5 | $0.54 | $2.78 | $0.06 | $1.10 | 262K | unknown |
| IteraCompute Inference host | GLM-5.3 | $0.82 | $2.88 | $0.20 | $1.33 | 1.05M | unknown |
| IteraCompute Inference host | Kimi K2.7 Code | $0.69 | $3.29 | $0.15 | $1.34 | 262K | unknown |
| IteraCompute Inference host | Kimi K2.6 | $0.87 | $3.51 | $0.07 | $1.53 | 262K | unknown |
| IteraCompute Inference host | Qwen3.8 Max | $1.95 | $5.70 | $0.25 | $2.89 | 1.05M | unknown |
| IteraCompute Inference host | Kimi K3 | $2.35 | $11.76 | $0.23 | $4.70 | 1.05M | unknown |
Per 1M tokens, standard (non-promo) list prices; short-context / peak tier where tiered. USD unless shown with €, CHF or ₹: those are as published and not converted. ₹ rows also show ≈ USD at the RBI reference rate of ₹93.8579 per USD (2026-11-09); sorting still uses the published ₹ amount. Rows marked “Calculated from credits” have no official per-token price; see how they are calculated. Click a header to sort.
* 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.