DeepSeek V3.1
deepseek/deepseek-v3.1A chat model with a 164K-token context window, at $0.2625 per million input tokens and $0.9975 per million output tokens.
Details
- Maker
- deepseek
- Kind
- Chat
- Context window
- 163,840 tokens
- Max output
- 128,000 tokens
- Input
- $0.2625 per million tokens
- Cached input
- $0.1365 per million tokens, 48% off
- Cache write
- Same as input
- Output
- $0.9975 per million tokens
- Capabilities
- Reasoning, tool use
- Takes
- Text
- Returns
- Text
- Zero data retention
- Not on every provider
- No training on requests
- Not on every provider
- Released
- 2025-08-21
- Newer model
- deepseek/deepseek-v4.1-flash-1017Released later by the same maker, costs no more, and lists the same capabilities. Compare the two
Description
DeepSeek-V3.1 is post-trained on the top of DeepSeek-V3.1-Base, which is built upon the original V3 base checkpoint through a two-phase long context extension approach, following the methodology outlined in the original DeepSeek-V3 report. We have expanded our dataset by collecting additional long documents and substantially extending both training phases. The 32K extension phase has been increased 10-fold to 630B tokens, while the 128K extension phase has been extended by 3.3x to 209B tokens. Additionally, DeepSeek-V3.1 is trained using the UE8M0 FP8 scale data format to ensure compatibility with microscaling data formats.
Call it
curl https://phantom.codes/v1/chat/completions \
-H "Authorization: Bearer $PHANTOM_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v3.1",
"messages": [
{"role": "user", "content": "Hello"}
]
}'Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.