Kimi K3.1 Pro is based on Moonshot AI’s Kimi K3.1, offering code generation and interactive content development capabilities for coding assistance, code analysis, and visual prototyping.
Pricing
- Input Tokens: $2 /M tokens
- Output Tokens: $10 /M tokens
- Cache Read: $0.2 /M tokens
Input Modalities
- Text
- Vision
- Video
Output Modalities
- Text
Context length
- 1.05M tokens
Max output
- 1.05M tokens
Capabilities
- Thinking
- Streaming
- Tool calling
- Web search
- URL context
- Code interpreter
- Computer use
- File search
- Memory tool
- Structured outputs
- Structured decision
- Citations
- Prompt caching
- Background mode
- Server-side sessions
Providers
aiand aiand-kimi-k3.1-pro
10% off·Nov 9 09:00 – Nov 23 09:00 GMT+0Pricing$2$1.8$10$9
Cache$0.2$0.18
PrecisionⓘNot Disclosed
Latency3.2S
Throughput62.5TPS
Uptime
100.00% uptime 2 days ago
100.00% uptime yesterday
100.00% uptime today
Pareto pareto-kimi-k3.1-pro
10% off·Nov 17 12:00 – Nov 23 12:00 GMT+0Pricing$2$1.8$10$9
Cache$0.2$0.18
PrecisionⓘMXFP4
Latency0.9S
Throughput89.9TPS
Uptime
100.00% uptime 2 days ago
100.00% uptime yesterday
100.00% uptime today
Alibaba Cloud alicloud-kimi-k3.1-pro
Pricing$2$10.5
Cache$0.2
PrecisionⓘNot Disclosed
Latency2.0S
Throughput26.4TPS
Uptime
100.00% uptime 2 days ago
100.00% uptime yesterday
100.00% uptime today
Azure azure-kimi-k3.1-pro
Pricing$2.3$11.5
Cache$0.23
PrecisionⓘNot Disclosed
Latency-
Throughput-
Uptime
0.00% uptime 2 days ago
0.00% uptime yesterday
0.00% uptime today
Moonshot moonshot-kimi-k3.1-pro
Pricing$2$10.5
Cache$0.2
PrecisionⓘNot Disclosed
Latency-
Throughput-
Uptime
100.00% uptime 2 days ago
100.00% uptime yesterday
0.00% uptime today
Performance for kimi-k3.1-pro
Uptime is the percentage of requests that succeeded over the past 72 hours. AIHubMix continuously monitors every provider and automatically retries with the next-best provider when one returns an error or responds too slowly; Latency is total round-trip time (lower is better); Throughput is how fast the model writes (tokens per second, higher is better).
Uptime
Loading...
Latency
Loading...
Throughput
Loading...
Try this model
Python