| Model | Context | Input / 1M | Output / 1M | Cache Read / 1M |
|---|---|---|---|---|
| DeepSeek: DeepSeek V4.1 Flash 1017 (batch) deepseek/deepseek-v4.1-flash-1017:batch |
1.0M | $0.035 | $0.149 | $0.0029 |
| DeepSeek: DeepSeek V4 Flash 0731 (batch) deepseek/deepseek-v4-flash-0731:batch |
1.0M | $0.048 | $0.144 | $0.012 |
| DeepSeek: DeepSeek V4.1 Flash (batch) deepseek/deepseek-v4.1-flash:batch |
1.0M | $0.050 | $0.150 | $0.0040 |
| DeepSeek: DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash |
1.0M | $0.050 | $0.199 | $0.0010 |
| DeepSeek: DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731 |
1.0M | $0.044 | $0.300 | $0.035 |
| DeepSeek: DeepSeek V4 Flash 0423 deepseek/deepseek-v4-flash |
1.0M | $0.090 | $0.180 | $0.018 |
| DeepSeek: DeepSeek V4.1 Flash 1017 deepseek/deepseek-v4.1-flash-1017 |
1.0M | $0.150 | $0.600 | $0.0030 |
| DeepSeek: DeepSeek V3.2 deepseek/deepseek-v3.2 |
164K | $0.260 | $0.380 | $0.130 |
| DeepSeek: DeepSeek V3.2 Exp deepseek/deepseek-v3.2-exp |
164K | $0.270 | $0.410 | — |
| DeepSeek: DeepSeek V4 Flash Vision Exp deepseek/deepseek-v4-flash-vision-exp |
1.0M | $0.216 | $0.647 | $0.0069 |
| DeepSeek: DeepSeek V3.1 deepseek/deepseek-chat-v3.1 |
164K | $0.250 | $0.950 | $0.130 |
| DeepSeek: DeepSeek V3 0324 deepseek/deepseek-chat-v3-0324 |
164K | $0.250 | $1.00 | — |
| DeepSeek: DeepSeek V3 deepseek/deepseek-chat |
164K | $0.257 | $1.03 | — |
| DeepSeek: DeepSeek V3.1 Terminus deepseek/deepseek-v3.1-terminus |
164K | $0.270 | $1.00 | — |
| DeepSeek: R1 0528 deepseek/deepseek-r1-0528 |
164K | $0.571 | $2.29 | — |
| DeepSeek: DeepSeek V4 Pro 0423 deepseek/deepseek-v4-pro |
1.0M | $0.900 | $1.50 | $0.200 |
| DeepSeek: DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813 |
1.0M | $1.32 | $3.96 | $0.044 |
Recommended AI & GPU Infrastructure
Best for H100 / A100 / 4090
Launch GPU on RunPod →
RunPod Cloud GPUs
Spin up on-demand H100, A100, and RTX 4090 pods or serverless vLLM endpoints in seconds.
Predictable Cloud Infra
Try DigitalOcean →
DigitalOcean GPU Droplets
Deploy AI inference APIs, vector databases, and GPU droplets with simple monthly billing.
Global Low-Latency Regions
Deploy on Vultr →
Vultr Cloud GPU
Run dedicated NVIDIA H100/A100/L40S instances across 32 global data center regions.
1 API Key · 470+ Models
Get Unified API Key →
OpenRouter Unified API
Switch between Gemini, Claude, GPT, DeepSeek, and Llama with one OpenAI-compatible key.