R1 Distill Llama 70B vs Hy4
Price, context window & benchmark comparison
VS
Compare different models
Verdict: Hy4 is 22% cheaper than R1 Distill Llama 70B on a typical 3:1 input/output mix. Hy4 has the larger context window (1M vs 8K).
| R1 Distill Llama 70B | Hy4 | |
|---|---|---|
| Input price / 1M | $0.80 | $0.42 |
| Output price / 1M | $0.80 | $1.25 |
| Blended price (3:1) | $0.80 | $0.63 |
| Cached input / 1M | — | $0.021 |
| Context window | 8K | 1M |
| Max output | 7K | 66K |
| Intelligence index | — | 34.6 |
| Coding index | — | — |
| Providers | — | 1 |
| Best provider uptime (30m) | — | 100.0% |
| Vision input | No | Yes |
| Reasoning | Yes | Yes |
| Tool calling | No | Yes |
| Released | 2025-01-23 | 2026-11-04 |
| Retirement | 2026-09-28 | — |
Cost calculator
FAQ
Which is cheaper, R1 Distill Llama 70B or Hy4?
Hy4 is 22% cheaper than R1 Distill Llama 70B on a typical 3:1 input/output mix.
R1 Distill Llama 70B vs Hy4: which has a bigger context window?
R1 Distill Llama 70B: 8,192 tokens. Hy4: 1,048,576 tokens.
How much would 1 million requests cost?
At 2,000 input + 500 output tokens per request: R1 Distill Llama 70B ≈ $2,000, Hy4 ≈ $1,459.
More comparisons
R1 Distill Llama 70B vs Gemini 4 CarbonR1 Distill Llama 70B vs Claude Fable 5.2R1 Distill Llama 70B vs Gemini Omni 1.2 FlashR1 Distill Llama 70B vs Gemini Omni 1.1 FlashR1 Distill Llama 70B vs GLM 5.3 FlashX LegalR1 Distill Llama 70B vs GPT-6.1 TerraR1 Distill Llama 70B vs GPT-6.1 Terra ProR1 Distill Llama 70B vs Kimi K3.1 ProR1 Distill Llama 70B vs MiniMax M3.1 FlashR1 Distill Llama 70B vs DeepSeek V4.1 Flash 1017R1 Distill Llama 70B vs Nemotron 3.5 Super VLR1 Distill Llama 70B vs Gemini 4 ArgonR1 Distill Llama 70B vs Claude Haiku 5.5R1 Distill Llama 70B vs Nano Banana 2.1R1 Distill Llama 70B vs Mistral Large 4R1 Distill Llama 70B vs GPT-6.1 Sol ProHy4 vs Gemini 4 CarbonHy4 vs Claude Fable 5.2Hy4 vs Gemini Omni 1.2 FlashHy4 vs Gemini Omni 1.1 FlashHy4 vs GLM 5.3 FlashX LegalHy4 vs GPT-6.1 TerraHy4 vs GPT-6.1 Terra ProHy4 vs Kimi K3.1 Pro