token.app › Compare › DeepSeek V3 0324 vs Inkling Small
DeepSeek V3 0324 vs Inkling Small
Inkling Small leads on 2 of 2 shared benchmarks. DeepSeek V3 0324 is 1.3× cheaper per token on a blended 3:1 basis. Inkling Small accepts the larger context window (524K).
Head to head
Blended price uses a 3:1 input:output mix
| DeepSeek V3 0324 | Inkling Small | |
|---|---|---|
| Provider | DeepSeek | Thinkingmachines |
| Input $/1M | $0.290 | $0.450 |
| Output $/1M | $1.14 | $1.20 |
| Blended $/1M | $0.502 | $0.637 |
| Context window | 164K | 524K |
| Max output | 115K | 262K |
| Released | Mar 2025 | Jul 2026 |
| Licence | Open weights | Open weights |
| GPQA Diamond | 67.6% | 88.5% |
| OTIS Mock AIME | 37.8% | 90.0% |
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 DeepSeek V3 0324 if…
- Costs less per token — $0.502 vs $0.637 blended
Choose Inkling Small if…
- Higher GPQA Diamond (88.5% vs 67.6%)
- Higher OTIS Mock AIME (90.0% vs 37.8%)
- Larger context window (524K)
- Newer model (released Jul 2026)
FAQ
Which is better, DeepSeek V3 0324 or Inkling Small?
Across the 2 benchmarks both models have independently-run scores for, DeepSeek V3 0324 leads on 0 and Inkling Small leads on 2. Benchmarks are one input — price and context window are on this page too.
Is DeepSeek V3 0324 cheaper than Inkling Small?
DeepSeek V3 0324 is cheaper: $0.502 versus $0.637 per million tokens blended at 3:1 input:output. Input alone: $0.290 vs $0.450. Output alone: $1.14 vs $1.20.
What context windows do DeepSeek V3 0324 and Inkling Small have?
DeepSeek V3 0324: 163,840 tokens. Inkling Small: 524,288 tokens.
Who makes DeepSeek V3 0324 and Inkling Small?
DeepSeek V3 0324 is made by DeepSeek. Inkling Small is made by Thinkingmachines.
Related comparisons