token.app › Compare › R1 0528 vs Inkling
R1 0528 vs Inkling
Inkling leads on 2 of 2 shared benchmarks. R1 0528 is 1.9× cheaper per token on a blended 3:1 basis. Inkling accepts the larger context window (524K).
Head to head
Blended price uses a 3:1 input:output mix
| R1 0528 | Inkling | |
|---|---|---|
| Provider | DeepSeek | Thinkingmachines |
| Input $/1M | $0.500 | $1.00 |
| Output $/1M | $2.15 | $4.05 |
| Blended $/1M | $0.912 | $1.76 |
| Context window | 164K | 524K |
| Max output | 33K | 472K |
| Released | May 2025 | Jul 2026 |
| Licence | Open weights | Open weights |
| GPQA Diamond | 76.3% | 88.3% |
| OTIS Mock AIME | 66.4% | 88.9% |
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose R1 0528 if…
- Costs less per token — $0.912 vs $1.76 blended
Choose Inkling if…
- Higher GPQA Diamond (88.3% vs 76.3%)
- Higher OTIS Mock AIME (88.9% vs 66.4%)
- Larger context window (524K)
- Newer model (released Jul 2026)
FAQ
Which is better, R1 0528 or Inkling?
Across the 2 benchmarks both models have independently-run scores for, R1 0528 leads on 0 and Inkling leads on 2. Benchmarks are one input — price and context window are on this page too.
Is R1 0528 cheaper than Inkling?
R1 0528 is cheaper: $0.912 versus $1.76 per million tokens blended at 3:1 input:output. Input alone: $0.500 vs $1.00. Output alone: $2.15 vs $4.05.
What context windows do R1 0528 and Inkling have?
R1 0528: 163,840 tokens. Inkling: 524,288 tokens.
Who makes R1 0528 and Inkling?
R1 0528 is made by DeepSeek. Inkling is made by Thinkingmachines.