Home / Models
AI models on kryyt
One OpenAI-compatible API for Kryyt AI, GLM-5.3, Kimi K3, Qwen3.8, and MiniMax M3. Kryyt AI is live today; the rest are coming soon. Compare context windows, licenses, and pricing, then call any of them with a single key.
All models
| Model | API ID | Context | Pricing | License | Status |
|---|---|---|---|---|---|
| Kryyt AI | deepseek-v4.1-flash | 1M | See account pricing | MIT | Live |
| DeepSeek V4.1 Pro | deepseek-v4.1-pro | 1M | See account pricing | MIT | Soon |
| GLM-5.3 | glm-5.3 | 200K | See account pricing | MIT | Soon |
| GLM-5.3 Flash | glm-5.3-flash | 1M | See account pricing | MIT | Soon |
| GLM-5.2 | glm-5.2 | 1M | See account pricing | MIT | Soon |
| Kimi K3 | kimi-k3 | 1M | See account pricing | Open weights (custom) | Soon |
| Qwen3.8-Max | qwen3.8-max | 1M | See account pricing | Apache 2.0 / Qwen | Soon |
| Qwen3.8-27B | qwen3.8-27b | 262K | See account pricing | Apache 2.0 / Qwen | Soon |
| Qwen3.8-Flash | qwen3.8-flash | 256K | See account pricing | Apache 2.0 / Qwen | Soon |
| MiniMax M3 | minimax-m3 | 1M | See account pricing | MiniMax Community | Soon |
| MiniMax M2.5 | minimax-m2.5 | 204K | See account pricing | MiniMax Community | Soon |
deepseek-v4.1-flash
- Model
- Kryyt AI
- Context
- 1M
- Pricing
- See account pricing
- License
- MIT
- Status
- Live
deepseek-v4.1-pro
- Model
- DeepSeek V4.1 Pro
- Context
- 1M
- Pricing
- See account pricing
- License
- MIT
- Status
- Soon
glm-5.3
- Model
- GLM-5.3
- Context
- 200K
- Pricing
- See account pricing
- License
- MIT
- Status
- Soon
glm-5.3-flash
- Model
- GLM-5.3 Flash
- Context
- 1M
- Pricing
- See account pricing
- License
- MIT
- Status
- Soon
glm-5.2
- Model
- GLM-5.2
- Context
- 1M
- Pricing
- See account pricing
- License
- MIT
- Status
- Soon
kimi-k3
- Model
- Kimi K3
- Context
- 1M
- Pricing
- See account pricing
- License
- Open weights (custom)
- Status
- Soon
qwen3.8-max
- Model
- Qwen3.8-Max
- Context
- 1M
- Pricing
- See account pricing
- License
- Apache 2.0 / Qwen
- Status
- Soon
qwen3.8-27b
- Model
- Qwen3.8-27B
- Context
- 262K
- Pricing
- See account pricing
- License
- Apache 2.0 / Qwen
- Status
- Soon
qwen3.8-flash
- Model
- Qwen3.8-Flash
- Context
- 256K
- Pricing
- See account pricing
- License
- Apache 2.0 / Qwen
- Status
- Soon
minimax-m3
- Model
- MiniMax M3
- Context
- 1M
- Pricing
- See account pricing
- License
- MiniMax Community
- Status
- Soon
minimax-m2.5
- Model
- MiniMax M2.5
- Context
- 204K
- Pricing
- See account pricing
- License
- MiniMax Community
- Status
- Soon
Usage is charged at Kryyt's published rates for the selected model and features. Review current pricing and usage in your account.
Kryyt AI
Kryyt AI currently uses DeepSeek V4.1 Flash, a 552B-parameter mixture-of-experts model with native image understanding, a 1M-token context, up to 384K output tokens, and a controllable reasoning-effort setting. DeepSeek reports it outperforms the previous V4 Pro on its own tests. V4.1 Pro is the upcoming higher-capability tier.
Provider: DeepSeek · License: MIT · Context: 1M tokens · Released: September 2026
Best for:
- Long-context code generation
- Step-by-step reasoning
- High-volume, cost-sensitive workloads
| Model | API ID | Context | Pricing | License | Status |
|---|---|---|---|---|---|
| Kryyt AI | deepseek-v4.1-flash | 1M | See account pricing | MIT | Live |
| DeepSeek V4.1 Pro | deepseek-v4.1-pro | 1M | See account pricing | MIT | Soon |
deepseek-v4.1-flash
- Model
- Kryyt AI
- Context
- 1M
- Pricing
- See account pricing
- License
- MIT
- Status
- Live
deepseek-v4.1-pro
- Model
- DeepSeek V4.1 Pro
- Context
- 1M
- Pricing
- See account pricing
- License
- MIT
- Status
- Soon
GLM 5.3
The GLM-5 series from Z.ai is a 744B-parameter mixture-of-experts family tuned for agentic engineering. GLM-5.3 leads on coding and cyber-defense workloads; GLM-5.3-Flash is an MIT-licensed fast tier; GLM-5.2 adds native multimodality and a 1M-token context.
Provider: Z.ai (Zhipu) · License: MIT · Context: up to 1M tokens · Released: August 2026
Best for:
- Repo-scale coding & terminal agents
- Hybrid fast/deliberate reasoning
- Chinese + English tasks
| Model | API ID | Context | Pricing | License | Status |
|---|---|---|---|---|---|
| GLM-5.3 | glm-5.3 | 200K | See account pricing | MIT | Soon |
| GLM-5.3 Flash | glm-5.3-flash | 1M | See account pricing | MIT | Soon |
| GLM-5.2 | glm-5.2 | 1M | See account pricing | MIT | Soon |
glm-5.3
- Model
- GLM-5.3
- Context
- 200K
- Pricing
- See account pricing
- License
- MIT
- Status
- Soon
glm-5.3-flash
- Model
- GLM-5.3 Flash
- Context
- 1M
- Pricing
- See account pricing
- License
- MIT
- Status
- Soon
glm-5.2
- Model
- GLM-5.2
- Context
- 1M
- Pricing
- See account pricing
- License
- MIT
- Status
- Soon
Kimi K3
Kimi K3 from Moonshot AI is the largest open-weights model released to date, a mixture-of-experts model with native vision, a 1M-token context, and a Swarm system that orchestrates hundreds of specialized sub-agents across long autonomous runs.
Provider: Moonshot AI · License: Open weights (custom) · Context: 1M tokens · Released: July 2026
Best for:
- Long-horizon autonomous agents
- Multimodal image + video input
- Research and multi-step orchestration
| Model | API ID | Context | Pricing | License | Status |
|---|---|---|---|---|---|
| Kimi K3 | kimi-k3 | 1M | See account pricing | Open weights (custom) | Soon |
kimi-k3
- Model
- Kimi K3
- Context
- 1M
- Pricing
- See account pricing
- License
- Open weights (custom)
- Status
- Soon
Qwen3.8
Qwen3.8 is Alibaba's newest generation. Qwen3.8-Max is a 2.4-trillion-parameter mixture-of-experts flagship with a 1M-token context and native vision; Qwen3.8-27B is a compact, Apache-2.0 dense model with vision-language input, ideal for self-hosting and cost-efficient serving.
Provider: Alibaba Cloud · License: Apache 2.0 / Qwen · Context: up to 1M tokens · Released: August 2026
Best for:
- Multimodal understanding (text, image, video)
- Multilingual coverage
- Cost-efficient dense deployment
| Model | API ID | Context | Pricing | License | Status |
|---|---|---|---|---|---|
| Qwen3.8-Max | qwen3.8-max | 1M | See account pricing | Apache 2.0 / Qwen | Soon |
| Qwen3.8-27B | qwen3.8-27b | 262K | See account pricing | Apache 2.0 / Qwen | Soon |
| Qwen3.8-Flash | qwen3.8-flash | 256K | See account pricing | Apache 2.0 / Qwen | Soon |
qwen3.8-max
- Model
- Qwen3.8-Max
- Context
- 1M
- Pricing
- See account pricing
- License
- Apache 2.0 / Qwen
- Status
- Soon
qwen3.8-27b
- Model
- Qwen3.8-27B
- Context
- 262K
- Pricing
- See account pricing
- License
- Apache 2.0 / Qwen
- Status
- Soon
qwen3.8-flash
- Model
- Qwen3.8-Flash
- Context
- 256K
- Pricing
- See account pricing
- License
- Apache 2.0 / Qwen
- Status
- Soon
MiniMax M3
MiniMax M3 is a 428B-parameter mixture-of-experts model (~23B active) using MiniMax Sparse Attention to make a 1M-token context economical to serve. It takes text, image, and video natively and is strong on agentic coding — an efficient default for long agent loops.
Provider: MiniMax · License: MiniMax Community · Context: 1M tokens · Released: June 2026
Best for:
- Economical long-context agents
- Native image + video input
- Coding and tool use at scale
| Model | API ID | Context | Pricing | License | Status |
|---|---|---|---|---|---|
| MiniMax M3 | minimax-m3 | 1M | See account pricing | MiniMax Community | Soon |
| MiniMax M2.5 | minimax-m2.5 | 204K | See account pricing | MiniMax Community | Soon |
minimax-m3
- Model
- MiniMax M3
- Context
- 1M
- Pricing
- See account pricing
- License
- MiniMax Community
- Status
- Soon
minimax-m2.5
- Model
- MiniMax M2.5
- Context
- 204K
- Pricing
- See account pricing
- License
- MiniMax Community
- Status
- Soon
Model FAQ
Which kryyt model has the longest context window?
Several models support up to a 1M-token context, including DeepSeek V4.1, GLM-5.2, Kimi K3, Qwen3.8-Max, and MiniMax M3.
Which model is available now?
Kryyt AI is live today in browser chat, the VS Code extension, and the OpenAI-compatible API. The other families are coming soon.
How are models priced?
Usage is charged at Kryyt's published rates for the selected model and features. Review current pricing and usage in your account.
Can I switch models without changing code?
Yes — change the model string in your request body. The endpoint, key, and request format stay the same.
Ship with one endpoint
Get a key, change your base URL, and call every model on this page. No new SDKs.