DeepSeek-R1 (US)
Classic open reasoning model for transparent math, coding, and deliberate problem solving
Cheapest input
$1.35
$/MTok · models.dev
Cheapest output
$5.40
$/MTok
Context
128K
tokens
Offers
4
2 sources
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestus.deepseek.r1-v1:0 | Amazon Bedrock | $1.35 | $5.40 | $0 | 128K |
| models.devcheapestdeepseek.r1-v1:0 | Amazon Bedrock | $1.35 | $5.40 | $0 | 128K |
| LiteLLMus.deepseek.r1-v1:0 | — | $1.35 | $5.40 | $0.135 | — |
| LiteLLMdeepseek.r1-v1:0 | — | $1.35 | $5.40 | $0.135 | — |
Capabilities
- Reasoning
- Tool calling
- Open weights
- In: text
- Out: text
Knowledge cutoff: 2024-07Released: 2025-01-20Family: deepseek-thinking
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence18.5
- AA coding24.6
- AA agentic3.1
Sources: Arena AI, Artificial Analysis. See /benchmarks.