Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
| 1 model | thinkingmachinesThinking Machines: InklingRemove × |
|---|---|
| What’s different | Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and… |
| Date | Jul 15, 2026Released |
API prices USD · provider configuration shown below | |
| Listed rate | $0.95 in / $4.05 out/ 1M tokensdeepinfra · via Hugging Face · all routes ↗ |
| Provider endpoints | 6 endpoints → |
Benchmarks Each result retains its evaluation configuration | |
| AA Intelligence ↗4.3.2 | 24.98 ↗Effort: xhigh · XhighIndependent result |
| AA-Briefcase ↗1.1 | 832.43 ↗Effort: xhigh · XhighIndependent result |
| GDPval-AA ↗2.1 | 1,076.19 ↗Effort: xhigh · XhighIndependent result |
| AutomationBench-AA ↗AA Index 4.3.2 collection | 4.98% ↗Effort: xhigh · XhighIndependent result |
| Terminal-Bench 4.0 · AA ↗ | 1.01% ↗Effort: xhigh · XhighHarness unreportedIndependent result |
| SciCode ↗AA Index 4.3.2 collection | 46.99% ↗AA · Under reviewEffort: xhigh · XhighIndependent result |
| Humanity’s Last Exam ↗AA Index 4.3.2 collection | 31.88% ↗Effort: xhigh · XhighIndependent result |
| GDP.pdf ↗AA Index 4.3.2 collection | 12.8% ↗Effort: xhigh · XhighIndependent result |
| CritPt ↗AA Index 4.3.2 collection | 5.43% ↗AA · Under reviewEffort: xhigh · XhighIndependent result |
| AA-Omniscience ↗AA Index 4.3.2 collection | 2 ↗Effort: xhigh · XhighIndependent result |
| AA-LCR ↗1.1 | 77.33% ↗Effort: xhigh · XhighIndependent result |
Specifications | |
| Context window | 1M |
| Max output | 471.9K |
| Parameters | — |
| Tool calling | Supported |
| Structured output | Supported |
| Image input | Supported |
| Audio input | Supported |
| Reasoning | Supported |
| Prompt caching | Supported |
| Open weights | Supported |