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 — DeepSeek V4 Pro 0423
- Cost
- $0.459 in · $0.919 out per 1M tokensBudget
- Memory
- 1M tokens — about 1,550 pages
- Reads
- Text
- Can do
- Use tools (agents)
- Structured output
- Thinking mode
- Good at
- Coding: better than 67% · Agentic work: better than 63% · Overall: better than 59%
- Reliability
- 99.96% uptime, last 24h
- Released
- Apr 24, 2026
Advanced details
- API model ID
deepseek/deepseek-v4-pro- Max output
- 384K tokens
- Max input
- 1M tokens
- Cached input
- $0.038 per 1M
- Tokenizer
- DeepSeek
- Coding index
- 59.4
- Agentic work index
- 26.3
- Overall index
- 30.4
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 |
|---|---|---|---|---|---|
| Baidu · fp8 | $0.448 | $0.896 | $0.037 | 393K | 99.93% |
| StreamLake · fp8 | $0.449 | $0.899 | $0.037 | 384K | 99.48% |
| GMICloud · fp8 | $0.957 | $1.914 | $0.08 | 944K | 98.38% |
| DigitalOcean | $1.044 | $2.088 | $0.209 | 384K | 99.91% |
| Cloudflare | $1.15 | $2.55 | $0.20 | 944K | 99.07% |
| DeepInfra · fp8 | $1.30 | $2.60 | $0.10 | 16K | 99.87% |
| Alibaba · fp8Degraded | $1.416 | $2.832 | $0.118 | 393K | 91.45% |
| SiliconFlow · fp8 | $1.502 | $3.135 | $0.135 | 393K | 99.75% |
| Novita · fp8 | $1.60 | $3.20 | $0.135 | 393K | 99.96% |
| Venice | $1.65 | $3.301 | $0.33 | 33K | 99.35% |
| AtlasCloud · fp4 | $1.68 | $3.38 | $0.13 | 393K | 99.25% |
| NextBit · fp8 | $1.74 | $3.48 | $0.145 | 944K | 98.01% |
| Parasail · fp8 | $1.74 | $3.48 | $0.10 | 944K | 99.65% |
| Azure · us | $1.91 | $3.83 | $0.16 | 384K | 98.80% |
Supported parameters
- frequency_penalty
- include_reasoning
- logit_bias
- logprobs
- max_completion_tokens
- max_tokens
- min_p
- presence_penalty
- reasoning
- reasoning_effort
- repetition_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_k
- top_logprobs
- 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