MoE open model with frontier-class quality at low cost. Built by DeepSeek.
Prices updated
Input price
$0.26
per 1M tokens · Standard
Output price
$1.03
per 1M tokens · Standard
Input limit
164K
tokens
Output limit
16K
tokens
Input formats
Output formats
DeepSeek V3 price history
16 price records since 4/1/2026 · 14 changes
DeepSeek V3 cost calculator
Overview
What is DeepSeek V3?
DeepSeek V3 is a text & reasoning and code & slms model from DeepSeek. MoE open model with frontier-class quality at low cost. Its 164K context window and $0.26 input price make it a candidate for cost-sensitive, high-throughput applications.
Benchmarks
DeepSeek V3 benchmarks & speed
How DeepSeek V3 scores on standardized evaluations, and where it lands among every model we track.
8.5
Intelligence Index
Reasoning
GPQA Diamond
55.7%
Graduate-level scientific reasoning · top 84%
HLE
2.9%
Humanity's Last Exam · top 97%
Coding
SciCode
35.8%
Python for scientific computing · top 89%
Independent scores from Artificial Analysis and DesignArena · updated 10/5/2026. Higher is better; ranks compare against every model we track with that score.
Rates
DeepSeek V3 pricing
Pricing is based on token usage. Provider-specific caching, batch, regional, and tool charges may affect the final cost.
Input · Standard
$0.26
Per 1M tokens
Cached input · Standard
Not available
No listed cached-input rate
Capabilities
DeepSeek V3 Tools
Tools available when using DeepSeek V3 through supported provider APIs.
Function calling
Supported
Structured outputs
Supported
JSON mode
Supported
Reasoning
Not supported
Built-in web search
Not supported
Log probabilities
Not supported
Deterministic seed
Supported
Parallel tool calls
Not supported
Prompt caching
Not supported
Where to run it
DeepSeek V3 API providers
2 providers serve DeepSeek V3. Prices are per 1M tokens; uptime is the last 24 hours.
| Provider | Input | Output | Cached | Context | Uptime |
|---|---|---|---|---|---|
| StreamLake | $0.26 | $1.03 | — | 128K | 99.28% |
| DeepInfrafp4 | $0.32 | $0.89 | — | 164K | 93.03% |
- Input
- $0.26
- Output
- $1.03
- Cached
- —
- Context
- 128K
- Uptime
- 99.28%
- Input
- $0.32
- Output
- $0.89
- Cached
- —
- Context
- 164K
- Uptime
- 93.03%
Strengths and limitations
Strengths
- Low input cost at $0.26 per million tokens suits high-volume workloads.
- A 164K context window covers most focused application workflows.
- Supports text & reasoning and code & slms workloads in one model.
Limitations
- Generated tokens cost 4× more than input tokens, which matters for verbose responses.
- The 164K context window is smaller than several long-context alternatives.
- Arena Elo and MMLU-Pro are directional; test accuracy, latency and reliability on your own workload before committing.
Arena Elo, MMLU-Pro and pricing figures are illustrative; validate current vendor terms before purchase.
Same provider
More models from DeepSeek
Peer set
