DeepSeek Llama3.3 70B
DeepSeek Llama3.3 70B is DeepSeek's language model with a 131K context window, starting at $0.2 / 1M input and $0.6 / 1M output. A 70B LLM fine-tuned by DeepSeek on the Llama 3.3 base architecture, combining DeepSeek's training methodology with Meta's Llama 3.3 foundation.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities3/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
| $0.2 | $0.6 | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host DeepSeek Llama3.3 70B, ranked by cheapest on-demand price. The model needs about 168 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| Standard_NP40s |  Azure | 4× AMD Alveo U250 FPGA (64GB) | 256 GB | $6.60/hr | ||
| g2-standard-96 |  GCP | 8× nvidia-l4 | 192 GB | $7.98/hr | ||
| g7e.12xlarge |  AWS | 2× RTX PRO Server 6000 | 192 GB | $8.29/hr | ||
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| DeepSeek 4 Flash | — | — | $0.440 | $1.32 | Available |
| DeepSeek 4 Pro | — | — | $1.74 | $3.48 | Available |
| Aion 3 Mini | 1.0M | $0.700 | $1.40 | Available | |
| DeepSeek Janus Pro | — | — | — | — | Available |
| DeepSeek Llama3.3 70B | — | 131K | $0.200 | $0.600 | Current |
| DeepSeek | — | — | $0.580 | $1.68 | Available |
| DeepSeek LLM 67B Chat (V1) | — | — | — | — | Available |
| DeepSeek Janus Pro 1B | — | — | — | — | Available |
| DeepSeek Janus Pro 7B | — | — | — | — | Available |