DeepSeek
The open-weight family everyone else gets benchmarked against.
DeepSeek publishes the weights for nearly everything it ships, which is why its models became the price anchor for the whole market — a Flash model here costs a fraction of a frontier model and gets close on reasoning and code. The V4 line is a sparse mixture-of-experts design with a million-token context. This row is the model family; DeepSeek's own free chat app has its own entry in Chats.
At a glance — R1
- Cost
- $0.70 in · $2.50 out per 1M tokensMid-range
- Memory
- 64K tokens — about 96 pages
- Reads
- Text
- Can do
- Use tools (agents)
- Structured output
- Thinking mode
- Good at
- Coding: better than 25% · Agentic work: better than 15% · Overall: better than 18%
- Reliability
- 99.97% uptime, last 24h
- Released
- Jan 20, 2025
Advanced details
- API model ID
deepseek/deepseek-r1- Max output
- 16K tokens
- Knowledge cutoff
- 2024-07-31
- Tokenizer
- DeepSeek
- Coding index
- 24.6
- Agentic work index
- 1.1
- Overall index
- 11.4
Providers
The same model, hosted by different companies. OpenRouter picks one per request and falls back to the next if it fails.
| Provider | Input /1M | Output /1M | Cached /1M | Max output | Uptime 24h |
|---|---|---|---|---|---|
| Novita · fp8 | $0.70 | $2.50 | — | 16K | 99.97% |
Supported parameters
- frequency_penalty
- include_reasoning
- max_tokens
- presence_penalty
- reasoning
- repetition_penalty
- response_format
- seed
- stop
- temperature
- tool_choice
- tools
- top_k
- top_p
Live from OpenRouter, refreshed hourly. Scores from Artificial Analysis.
Key info
- Pricing
- Open source
- Category
- Models
- Best for
- Intermediate
- Made by
- DeepSeek
- Weights
- Open
- Good for
- Reasoning and code at a fraction of frontier prices