DeepSeek V4 Pro 0813 pricing
DeepSeek V4 Pro 0813 from Together AI costs $1.32 per 1M input tokens and $3.96 per 1M output tokens. Cached input is $0.130 per 1M.
API id deepseek-v4-pro-0813 · Together AI · source · updated 2026-09-25 · general-purpose
$1.32
Input / 1M tokens
$3.96
Output / 1M tokens
$0.130
Cached input / 1M
—
Context window
DeepSeek V4 Pro 0813 specifications
- Provider
- Together AI
- API id
deepseek-v4-pro-0813- Model type
- general-purpose
- Context window
- — tokens
- Max output
- not published
- Currency
- USD
- Price source
- First-party
- Last checked
- 2026-09-25
Tags
- flagship
DeepSeek V4 Pro 0813 across providers
The same model, priced by every seller we track. Ranked by the cost of 1M input + 1M output tokens, standard tier; savings measured against buying from the vendor directly.
| Provider | Input /1M | Cached /1M | Output /1M | 1M in + 1M out | vs vendor |
|---|---|---|---|---|---|
| $0.462 | $0.015 | $1.39 | $1.85 | — | |
OpenRouterHost | $0.462 | $0.015 | $1.39 | $1.85 | — |
| $1.32 | $0.130 | $3.96 | $5.28 | +186% |
What DeepSeek V4 Pro 0813 costs in practice
| Workload | Input tokens | Output tokens | Estimated cost |
|---|---|---|---|
| Short chat turn | 1,000 | 500 | $0.0033 |
| Document summary | 50,000 | 2,000 | $0.07 |
| 1M tokens in, 200K out | 1,000,000 | 200,000 | $2.11 |
Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.
DeepSeek V4 Pro 0813 price history
| Recorded | Input /1M | Output /1M |
|---|---|---|
| 2026-09-24 | $0.462 | $1.39 |
| 2026-09-21 | $1.32 | $3.96 |
| 2026-09-20 | $0.660 | $1.98 |
| 2026-09-19 | $0.578 | $1.73 |
| 2026-09-17 | $1.32 | $3.96 |
| 2026-09-14 | $0.983 | $2.95 |
| 2026-09-12 | $0.578 | $1.73 |
| 2026-09-10 | $1.05 | $3.15 |
| 2026-09-09 | $0.579 | $1.74 |
| 2026-09-08 | $1.05 | $3.15 |
| 2026-09-07 | $1.12 | $3.35 |
| 2026-09-05 | $1.12 | $3.36 |
Common questions
- How much does DeepSeek V4 Pro 0813 cost per 1M tokens?
- DeepSeek V4 Pro 0813 costs $1.32 per 1M input tokens and $3.96 per 1M output tokens on the standard tier. Cached input is $0.130 per 1M.
- What is DeepSeek V4 Pro 0813's context window?
- Together AI does not publish a context window for DeepSeek V4 Pro 0813 on its pricing page.
- Is there a cheaper Together AI model than DeepSeek V4 Pro 0813?
- Yes. Qwen3 235B A22B Instruct 2507 FP8 Throughput is $0.200 per 1M input tokens versus $1.32 for DeepSeek V4 Pro 0813.
- Where does this DeepSeek V4 Pro 0813 price come from?
- Directly from Together AI's published pricing page, re-read every day and normalized to USD per 1,000,000 tokens.
Head-to-head comparisons
Other Together AI models
- MiniMax M3 $0.300
- Kimi K3 $3.00
- Qwen3.8-2.4T-A95B $2.00
- Muse Glimmer 30B $0.350
- GLM-5.3 $1.40
- GLM-5.3-Flash $0.150
- DeepSeek V4.1 Flash $0.300
- Gemma 4 31B $0.390
- Qwen3.7-Plus $0.320
- GLM-5.2 $1.40
- Ternary Bonsai 27B Free
- Inkling $1.00
- DeepSeek V4 Flash 0731 $0.140
- Qwen3.8 Flash $0.090
- Qwen3.7-Max $1.50
- gpt-oss-120B $0.150