AI Rate CardClaude Haiku 4.5 (latest) vs DeepSeek R1 Distill Llama 70B: API price and specs
DeepSeek R1 Distill Llama 70B is 94% cheaper than Claude Haiku 4.5 (latest) on input price.
DeepSeek R1 Distill Llama 70B is 94% cheaper than Claude Haiku 4.5 (latest) on output price.
DeepSeek R1 Distill Llama 70B is 94% cheaper than Claude Haiku 4.5 (latest) on a 1M-in / 200k-out workload.
Claude Haiku 4.5 (latest) has a 52.6% larger context than DeepSeek R1 Distill Llama 70B.
| Field | Claude Haiku 4.5 (latest) | DeepSeek R1 Distill Llama 70B |
|---|---|---|
| Lowest input, per 1M | $0.50 +1566.7% | $0.03 |
| Median input, per 1M | $1.00 +42.9% | $0.70 |
| Lowest output, per 1M | $2.50 +1685.7% | $0.14 |
| Median output, per 1M | $5.00 +525% | $0.80 |
| Lowest unit price | $0.001 / request | — |
| Cost of 1M in + 200k out | $1.00 +1624.1% | $0.058 |
| Context | 200K | 131K +34.5% |
| Max output | 64K +51.2% | 131K |
| Providers | 34 | 6 +82.4% |
| Regions | APAC, AU, EU, GLOBAL, IN, JP, US | US |
| Accepts | application/pdf, file, image, image/gif, image/jpeg, image/png, image/webp, pdf, text | text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | openrouter | fastrouter |
Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.
Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.
Providers selling both
aihubmix, deepinfra, edenai, fastrouter, helicone, requesty
Frequently asked questions
Which is cheaper, Claude Haiku 4.5 (latest) or DeepSeek R1 Distill Llama 70B?
DeepSeek R1 Distill Llama 70B is 94% cheaper than Claude Haiku 4.5 (latest) on input price. DeepSeek R1 Distill Llama 70B is 94% cheaper than Claude Haiku 4.5 (latest) on output price. DeepSeek R1 Distill Llama 70B is 94% cheaper than Claude Haiku 4.5 (latest) on a 1M-in / 200k-out workload.
Which has the larger context, Claude Haiku 4.5 (latest) or DeepSeek R1 Distill Llama 70B?
Claude Haiku 4.5 (latest): 200K tokens; DeepSeek R1 Distill Llama 70B: 131K tokens.
Where can I use both Claude Haiku 4.5 (latest) and DeepSeek R1 Distill Llama 70B?
aihubmix, deepinfra, edenai, fastrouter, helicone, requesty