$ diff deepseek-v4-pro-0813 inkling
DeepSeek V4-Pro-0813 vs Inkling
Values come from DeepSeek V4-Pro-0813 and Inkling, where each is cited to its source. This page states no benchmark result and ranks neither model — it puts two published specifications next to each other. Where a lab has not published a figure, the row says so rather than guessing.
DeepSeekDeepSeek V4-Pro-0813
- context
- 1.0M
- weights
- open
- $/M in
- $0.66
- $/M out
- $1.98
- context
- 1M
- weights
- open
- $/M in
- —
- $/M out
- —
What actually differs
- Context window
- DeepSeek V4-Pro-0813 takes 1.0M against 1M — modestly more room in a single request.
- Weights
- Both publish weights — DeepSeek V4-Pro-0813 under MIT (open-weight, as reported), Inkling under Apache 2.0 (open-weight). Check the licences rather than assuming they permit the same commercial use.
- Recency
- DeepSeek V4-Pro-0813 shipped 29 days after Inkling (2026-08-13 vs 2026-07-15).
Full spec
| Attribute | DeepSeek V4-Pro-0813 | Inkling |
|---|---|---|
| Developer | DeepSeek | Thinking Machines |
| Released | 2026-08-13 | 2026-07-15 |
| Context window | 1,048,576 (1M) — 384K max output | 1M |
| Pricing | $0.66/M input (cache miss) · $1.98/M output off-peak; $1.32 · $3.96 at peak — see Pricing | not recorded |
| License | MIT (open-weight, as reported) | Apache 2.0 (open-weight) |
| Availability | DeepSeek API (Responses format, Codex-adapted), Hugging Face (`deepseek-ai/DeepSeek-V4-Pro-0813`) | Hugging Face (BF16 and NVFP4), Tinker (fine-tuning), SGLang, vLLM, llama.cpp, Unsloth |