$ diff inkling minimax-m3
Inkling vs MiniMax M3
Values come from Inkling and MiniMax M3, where each is cited to its source. This page states no benchmark result and ranks neither model — it puts two published specifications next to each other. Where a lab has not published a figure, the row says so rather than guessing.
Thinking MachinesInkling
- context
- 1M
- weights
- open
- $/M in
- —
- $/M out
- —
- context
- 1M
- weights
- open
- $/M in
- $0.3
- $/M out
- $1.2
What actually differs
- Context window
- Identical — both accept 1M tokens, so context length is not a reason to pick either.
- Weights
- Both publish weights — Inkling under Apache 2.0 (open-weight), MiniMax M3 under Open-weight (HuggingFace). Check the licences rather than assuming they permit the same commercial use.
- Recency
- Inkling shipped 44 days after MiniMax M3 (2026-07-15 vs 2026-06-01).
Full spec
| Attribute | Inkling | MiniMax M3 |
|---|---|---|
| Developer | Thinking Machines | MiniMax |
| Released | 2026-07-15 | 2026-06-01 |
| Context window | 1M | 1,000,000 tokens (1M); min. 512K guaranteed |
| Pricing | not recorded | $0.30/M input · $1.20/M output ($0.06/M cached input) — OpenRouter catalogue, read 2026-07-28 |
| License | Apache 2.0 (open-weight) | Open-weight (HuggingFace) |
| Availability | Hugging Face (BF16 and NVFP4), Tinker (fine-tuning), SGLang, vLLM, llama.cpp, Unsloth | API (global, including English) + open-weight on HuggingFace |