Coming to CheapestInference — models under review
New models don’t land in a pool by surprise. Every candidate goes through the same review — Reviewing → Confirmed → Capacity secured → Live — and this page is its live status board. Check back or watch the changelog for the moment a model goes live.
Current pipeline
Section titled “Current pipeline”| Model | State | Pool candidate | Notes | Updated |
|---|---|---|---|---|
Qwen3.8 Max (qwen3.8-max) | Reviewing | Flagship | Alibaba’s 2.4T-parameter flagship — 53 on the Artificial Analysis Intelligence Index, 1M-token context. Runs cleanly on our API stack (OpenAI + Anthropic endpoints, tool calling verified). The open question is licensing: Alibaba has announced open weights but not yet released them — the review is waiting on that release. Read the full analysis: Qwen3.8 Max: specs, benchmarks & API options. | 2026-08-04 |
Recently shipped
Section titled “Recently shipped”Models that completed this pipeline and went live:
- 2026-07-31 — DeepSeek V4 Flash (0731 build) — upgraded in the Core Pool
- 2026-07-28 — Kimi K3 — launched the Flagship Pool
- Full history in the changelog
Want a model reviewed?
Section titled “Want a model reviewed?”Tell us what you’d pay a flat monthly fee for: support@cheapestinference.com. Real demand moves models up this list.