Model catalog

One endpoint, every model. Compare context windows, capabilities and real per-token pricing side by side, then swap the model string in your request — nothing else changes.

351
Models: 35
Providers: 11
Free to try: $0.0001
Cheapest input / 1M

8 of 351 models

Kimi K3
moonshotai/kimi-k3
Language
Kimi’s flagship model for long-horizon coding and end-to-end knowledge work, with a 1M-token context window.
Context
1M
In / 1M
$3.00
Out / 1M
$15.00
- Reasoning
- Tool use
- Vision
- +3
Kimi K2.7 Code High Speed
moonshotai/kimi-k2.7-code-highspeed
Language
Kimi K2.7 Code HighSpeed is the high-speed version of Kimi K2.7 Code, the same model as Kimi K2.7 Code, but with an output speed of approximately 180 Tokens/s and up to 260 Tokens/s in short context scenarios, delivering a more extreme coding experience.
Context
262K
In / 1M
$1.90
Out / 1M
$8.00
- Reasoning
- Tool use
- Vision
- +3
Kimi K2.7 Code
moonshotai/kimi-k2.7-code
Language
Kimi-K2.7-Code is a coding model from Moonshot AI. It has improved coding & agent performance over K2.6, more reasoning efficiency with less overthinking, and improved instruction following for long-horizon coding.
Context
256K
In / 1M
$0.950
Out / 1M
$4.00
- Reasoning
- Tool use
- Vision
- +3
Kimi K3 Fast
moonshotai/kimi-k3-fast
Language
Fast version of Kimi’s flagship model for long-horizon coding and end-to-end knowledge work, with a 1M-token context window.
Context
1M
In / 1M
$4.50
Out / 1M
$22.50
- Reasoning
- Tool use
- Vision
- +2
Kimi K2.6
moonshotai/kimi-k2.6
Language
Kimi K2.6 demonstrates particularly strong performance in long-horizon coding tasks and produces professional-grade design with code and vision.
Context
262K
In / 1M
$0.950
Out / 1M
$4.00
- Reasoning
- Tool use
- Vision
- +2
Kimi K2.5
moonshotai/kimi-k2.5
Language
kimi-k2.5 is Kimi's most versatile model to date, featuring a native multimodal architecture that supports both visual and text input, thinking and non-thinking modes, and dialogue and agent tasks.
Context
262K
In / 1M
$0.600
Out / 1M
$3.00
- Reasoning
- Tool use
- Vision
- +2
Kimi K2 Thinking
moonshotai/kimi-k2-thinking
Language
Kimi K2 Thinking is an advanced open-source thinking model by Moonshot AI. It can execute up to 200 – 300 sequential tool calls without human interference, reasoning coherently across hundreds of steps to solve complex problems. Built as a thinking agent, it reasons step by step while using tools, achieving state-of-the-art performance on Humanity's Last Exam (HLE), BrowseComp, and other benchmarks, with major gains in reasoning, agentic search, coding, writing, and general capabilities.
Context
216K
In / 1M
$0.470
Out / 1M
$2.00
- Reasoning
- Tool use
- Implicit caching
Kimi K2 Instruct
moonshotai/kimi-k2
Language
Kimi K2 is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. Trained with the Muon optimizer, Kimi K2 achieves exceptional performance across frontier knowledge, reasoning, and coding tasks while being meticulously optimized for agentic capabilities.
Context
131K
In / 1M
$0.570
Out / 1M
$2.30
- Tool use