DeepSeek chat model for instruction following, coding, and analysis
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
Context
164K
163,840 tokens
Max output
33K
32,768 tokens
Input
$0.25
per 1M tokens
Output
$0.95
per 1M tokens
Providers
1
1 listings
Intelligence
13.7
Intelligence Index
Pricing
USD per 1M tokens · listed by Kilo Gateway
| Token type | Standard |
|---|---|
| Input | $0.25 |
| Output | $0.95 |
| Cache read | $0.13 |
Lowest input price across providers: $0.25.
Capabilities
ReasoningYes
Effort: none, high
Tool callYes
Structured outputYes
TemperatureYes
AttachmentsNo
Interleaved reasoningNo
Open weightsYes
ModeratedNo
Input
Text
Output
Text
Benchmarks
Published scores and Design Arena Elo
- Intelligence13.7#127 of 208
- CodingNot scored—
- AgenticNot scored—
- Arena1,076#99 of 128
Rankings
Position on each OneAtlas leaderboard
Providers · 1
1 listings
| Provider | Model ID | Context | Input limit | Output | Input $ | Output $ | Reasoning $ | Cache read | Cache write | Audio in | Audio out | Reasoning | Tools | Structured | Temp. | Updated |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
 Kilo Gateway | deepseek/deepseek-chat-v3.1 | 164K | — | 33K | $0.25 | $0.95 | — | $0.13 | — | — | — | Yes | Yes | Yes | Yes | Aug 21, 2025 |