Featured models from the catalog
A sample of commonly selected models. Full availability depends on tier.
Filter by capability
Meta (Llama)
Llama 3.2 90B Vision
- Vision + text
In / Out
$0.90 / $0.90
per 1M tokens
Value
~3,703
chats / $10
Mistral AI
Mistral Large
- European flagship
- Enterprise friendly
In / Out
$0.52 / $1.56
per 1M tokens
Value
~3,846
chats / $10
Alibaba (Qwen)
Qwen3 Coder Flash
- Fast coding
- Everyday dev
In / Out
$0.19 / $0.97
per 1M tokens
Value
~7,396
chats / $10
Alibaba (Qwen)
Qwen3.6 35B-A3B
- MoE efficiency
- Strong reasoning
In / Out
$0.15 / $0.99
per 1M tokens
Value
~7,763
chats / $10
Alibaba (Qwen)
Qwen3.5 35B-A3B
- MoE mid-size
- Good value
In / Out
$0.14 / $0.99
per 1M tokens
Value
~7,886
chats / $10
Moonshot (Kimi)
Kimi K2.6
- Latest Kimi flagship
- 1M context
In / Out
$0.88 / $3.52
per 1M tokens
Value
~1,893
chats / $10
Alibaba (Qwen)
Qwen3 Next 80B-A3B Instruct
- Next-gen instruct
- Versatile
In / Out
$0.09 / $1.09
per 1M tokens
Value
~7,885
chats / $10
Alibaba (Qwen)
Qwen3 14B
- Dense small
- Low latency
In / Out
$0.10 / $0.24
per 1M tokens
Value
~22,935
chats / $10
Alibaba (Qwen)
Qwen3 32B
- Dense capability
- Self-host friendly
In / Out
$0.08 / $0.28
per 1M tokens
Value
~22,967
chats / $10
Alibaba (Qwen)
Qwen3 VL Flash
- Fast vision
- Real-time
In / Out
$0.31 / $1.25
per 1M tokens
Value
~5,341
chats / $10
Alibaba (Qwen)
Qwen Coder Plus
- Solid coder
- Proven
In / Out
$0.31 / $1.25
per 1M tokens
Value
~5,341
chats / $10
Alibaba (Qwen)
Qwen3 Omni Flash
- Omni flash
- All-in-one
In / Out
$0.31 / $1.25
per 1M tokens
Value
~5,341
chats / $10
Zhipu (GLM)
GLM-5
- Next-gen Zhipu
- 200K context
In / Out
$0.53 / $1.69
per 1M tokens
Value
~3,636
chats / $10
Alibaba (Qwen)
Qwen3 8B
- Tiny & fast
- Edge deploy
In / Out
$0.05 / $0.40
per 1M tokens
Value
~20,202
chats / $10
Alibaba (Qwen)
Qwen3.5 397B-A17B
- Massive MoE
- Top performance
In / Out
$0.39 / $2.32
per 1M tokens
Value
~3,234
chats / $10
Alibaba (Qwen)
Qwen3.5 27B
- Dense mid-size
- Reliable
In / Out
$0.19 / $1.55
per 1M tokens
Value
~5,165
chats / $10
Alibaba (Qwen)
Qwen2.5 Coder
- Code specialist
In / Out
$0.40 / $1.60
per 1M tokens
Value
~4,166
chats / $10
Alibaba (Qwen)
Qwen3.5 Plus
- Solid all-rounder
- Agent capable
In / Out
$0.30 / $1.78
per 1M tokens
Value
~4,212
chats / $10
Alibaba (Qwen)
Qwen3 Coder
- Code specialist
In / Out
$0.22 / $1.78
per 1M tokens
Value
~4,512
chats / $10
Alibaba (Qwen)
Qwen3 235B-A22B
- Massive MoE
- Deep reasoning
In / Out
$0.45 / $1.80
per 1M tokens
Value
~3,700
chats / $10
Tencent (Hunyuan)
Hunyuan Pro
- CN enterprise
In / Out
$0.50 / $2.00
per 1M tokens
Value
~3,333
chats / $10
Alibaba (Qwen)
Qwen3.5 122B-A10B
- Large MoE
- Enterprise scale
In / Out
$0.26 / $2.06
per 1M tokens
Value
~3,881
chats / $10
Alibaba (Qwen)
Qwen VL Plus
- Vision plus
- Good value
In / Out
$0.52 / $2.08
per 1M tokens
Value
~3,205
chats / $10
Alibaba (Qwen)
Qwen VL Plus Latest
- Latest VL Plus
- Auto-updated
In / Out
$0.52 / $2.08
per 1M tokens
Value
~3,205
chats / $10