Featured models from the catalog
A sample of commonly selected models. Full availability depends on tier.
Launch flagship
8 models we feature at launch — covering coding, GPT flagship, Chinese, long-context, and RAG. The rest are grouped below.
Anthropic
Claude Opus 4.7
Featured- Highest quality
- 1M context
In / Out
$5.20 / $26.00
per 1M tokens
Value
~274
chats / $10
OpenAI
GPT-5.5 Pro
Featured- Latest GPT flagship
- Deep reasoning
In / Out
$31.20 / $187.20
per 1M tokens
Value
~40
chats / $10
Anthropic
Claude Sonnet 4.6
Featured- 200K context
- Best for code
In / Out
$3.12 / $15.60
per 1M tokens
Value
~457
chats / $10
DeepSeek
DeepSeek V4 Flash
Featured- 1M context
- Competitive pricing
In / Out
$0.15 / $0.29
per 1M tokens
Value
~17,152
chats / $10
Anthropic
Claude Haiku 4.5
Featured- Fast, cheap
- Good tool use
In / Out
$1.04 / $5.20
per 1M tokens
Value
~1,373
chats / $10
Alibaba (Qwen)
Qwen3 Max
Featured- Leading Chinese model
- Strong at SEA languages
In / Out
$0.81 / $4.06
per 1M tokens
Value
~1,761
chats / $10
Moonshot (Kimi)
Kimi K2
Featured- 1M context
- Long-context specialist
In / Out
$0.57 / $2.29
per 1M tokens
Value
~2,913
chats / $10
OpenAI
OpenAI Embedding 3 Large
Featured- Industry standard
- 3072-dim
In / Out
$0.14 / $0.00
per 1M tokens
Value
~37,037
chats / $10
Chat & customer support
15 modelsGoogle DeepMind (Gemini)
Gemini 3 Flash
- Fast multimodal
- 1M context
In / Out
$0.78 / $4.68
per 1M tokens
Value
~1,602
chats / $10
Google DeepMind (Gemini)
Gemini 3.1 Flash-Lite
- Lowest-cost Gemini
- 1M context
In / Out
$0.26 / $1.56
per 1M tokens
Value
~4,807
chats / $10
Google DeepMind (Gemini)
Gemini 3.1 Pro
- Google flagship
- 1M context
In / Out
$2.08 / $12.48
per 1M tokens
Value
~600
chats / $10
OpenAI
GPT-4o
- Multimodal
- Strong tool use
In / Out
$2.60 / $10.40
per 1M tokens
Value
~641
chats / $10
ByteDance (Doubao)
Doubao 1.5 Pro 32k
- Strong on Chinese tasks
- Competitive pricing
In / Out
$0.12 / $0.29
per 1M tokens
Value
~19,267
chats / $10
Zhipu (GLM)
GLM-4.6
- 200K context
- Strong tool use
In / Out
$0.14 / $0.43
per 1M tokens
Value
~13,812
chats / $10
Mistral AI
Mistral Small
- Balanced cost
- Fast
In / Out
$0.10 / $0.31
per 1M tokens
Value
~19,230
chats / $10
OpenAI
GPT-4o mini
- Very cheap
- Fast
In / Out
$0.16 / $0.62
per 1M tokens
Value
~10,683
chats / $10
Alibaba (Qwen)
Qwen3 Plus
- Balanced
- Long context
In / Out
$0.27 / $0.81
per 1M tokens
Value
~7,401
chats / $10
Meta (Llama)
Llama 3.3 70B Instruct
- Open ecosystem
- Hosted via Together
In / Out
$0.92 / $0.92
per 1M tokens
Value
~3,623
chats / $10
ByteDance (Doubao)
Doubao 1.5 Lite 32k
- Very cheap
- Fast
In / Out
$0.04 / $0.09
per 1M tokens
Value
~57,142
chats / $10
ByteDance (Doubao)
Doubao 2.0 Mini
- Ultra-low latency
- Real-time voice/chat
In / Out
$0.04 / $0.09
per 1M tokens
Value
~57,142
chats / $10
Alibaba (Qwen)
Qwen3 Turbo
- Cheapest tier
- Fast
In / Out
$0.05 / $0.20
per 1M tokens
Value
~33,333
chats / $10
Mistral AI
Mistral Large
- European flagship
- Enterprise friendly
In / Out
$2.08 / $6.24
per 1M tokens
Value
~961
chats / $10
Zhipu (GLM)
GLM-4 Flash
- Free-tier friendly
- Fast
In / Out
$0.00 / $0.00
per 1M tokens
Value
—
chats / $10
Code assistant
8 modelsGoogle DeepMind (Gemini)
Gemini 3.1 Pro
- Google flagship
- 1M context
In / Out
$2.08 / $12.48
per 1M tokens
Value
~600
chats / $10
DeepSeek
DeepSeek V4 Pro
- 1M context
- Frontier reasoning
In / Out
$1.81 / $3.62
per 1M tokens
Value
~1,381
chats / $10
OpenAI
GPT-4o
- Multimodal
- Strong tool use
In / Out
$2.60 / $10.40
per 1M tokens
Value
~641
chats / $10
ByteDance (Doubao)
Doubao 1.5 Pro 32k
- Strong on Chinese tasks
- Competitive pricing
In / Out
$0.12 / $0.29
per 1M tokens
Value
~19,267
chats / $10
Alibaba (Qwen)
Qwen3 Plus
- Balanced
- Long context
In / Out
$0.27 / $0.81
per 1M tokens
Value
~7,401
chats / $10
Meta (Llama)
Llama 3.3 70B Instruct
- Open ecosystem
- Hosted via Together
In / Out
$0.92 / $0.92
per 1M tokens
Value
~3,623
chats / $10
OpenAI
o3-mini
- Reasoning model
- Strong on math/code
In / Out
$1.14 / $4.58
per 1M tokens
Value
~1,456
chats / $10
Mistral AI
Mistral Large
- European flagship
- Enterprise friendly
In / Out
$2.08 / $6.24
per 1M tokens
Value
~961
chats / $10
Long documents
3 modelsGoogle DeepMind (Gemini)
Gemini 3.1 Pro
- Google flagship
- 1M context
In / Out
$2.08 / $12.48
per 1M tokens
Value
~600
chats / $10
DeepSeek
DeepSeek V4 Pro
- 1M context
- Frontier reasoning
In / Out
$1.81 / $3.62
per 1M tokens
Value
~1,381
chats / $10
Zhipu (GLM)
GLM-4.6
- 200K context
- Strong tool use
In / Out
$0.14 / $0.43
per 1M tokens
Value
~13,812
chats / $10
Image generation
3 modelsStability AI
Stable Diffusion 3.5
- Open weights
- Customizable
In / Out
$30.00 / $30.00
per 1M tokens
Value
~111
chats / $10
OpenAI
DALL-E 3
- Prompt adherence
- Safe by default
In / Out
$40.00 / $40.00
per 1M tokens
Value
~83
chats / $10
Black Forest Labs (Flux)
FLUX 1.1 Pro
- Photorealistic
- Fast inference
In / Out
$40.00 / $40.00
per 1M tokens
Value
~83
chats / $10
Video generation
2 modelsKuaishou (Kling)
Kling 1.6
- Cinematic quality
- Long duration
In / Out
$120.00 / $120.00
per 1M tokens
Value
~27
chats / $10
Runway
Runway Gen-4
- High fidelity
- Motion control
In / Out
$150.00 / $150.00
per 1M tokens
Value
~22
chats / $10
Vision & OCR
4 modelsGoogle DeepMind (Gemini)
Gemini 3 Flash
- Fast multimodal
- 1M context
In / Out
$0.78 / $4.68
per 1M tokens
Value
~1,602
chats / $10
Google DeepMind (Gemini)
Gemini 3.1 Flash-Lite
- Lowest-cost Gemini
- 1M context
In / Out
$0.26 / $1.56
per 1M tokens
Value
~4,807
chats / $10
Google DeepMind (Gemini)
Gemini 3.1 Pro
- Google flagship
- 1M context
In / Out
$2.08 / $12.48
per 1M tokens
Value
~600
chats / $10
OpenAI
GPT-4o
- Multimodal
- Strong tool use
In / Out
$2.60 / $10.40
per 1M tokens
Value
~641
chats / $10
Automation & agents
12 modelsGoogle DeepMind (Gemini)
Gemini 3 Flash
- Fast multimodal
- 1M context
In / Out
$0.78 / $4.68
per 1M tokens
Value
~1,602
chats / $10
Google DeepMind (Gemini)
Gemini 3.1 Pro
- Google flagship
- 1M context
In / Out
$2.08 / $12.48
per 1M tokens
Value
~600
chats / $10
DeepSeek
DeepSeek V4 Pro
- 1M context
- Frontier reasoning
In / Out
$1.81 / $3.62
per 1M tokens
Value
~1,381
chats / $10
OpenAI
GPT-4o
- Multimodal
- Strong tool use
In / Out
$2.60 / $10.40
per 1M tokens
Value
~641
chats / $10
ByteDance (Doubao)
Doubao 1.5 Pro 32k
- Strong on Chinese tasks
- Competitive pricing
In / Out
$0.12 / $0.29
per 1M tokens
Value
~19,267
chats / $10
Zhipu (GLM)
GLM-4.6
- 200K context
- Strong tool use
In / Out
$0.14 / $0.43
per 1M tokens
Value
~13,812
chats / $10
OpenAI
GPT-4o mini
- Very cheap
- Fast
In / Out
$0.16 / $0.62
per 1M tokens
Value
~10,683
chats / $10
Alibaba (Qwen)
Qwen3 Plus
- Balanced
- Long context
In / Out
$0.27 / $0.81
per 1M tokens
Value
~7,401
chats / $10
ByteDance (Doubao)
Doubao 2.0 Mini
- Ultra-low latency
- Real-time voice/chat
In / Out
$0.04 / $0.09
per 1M tokens
Value
~57,142
chats / $10
OpenAI
o3-mini
- Reasoning model
- Strong on math/code
In / Out
$1.14 / $4.58
per 1M tokens
Value
~1,456
chats / $10
Mistral AI
Mistral Large
- European flagship
- Enterprise friendly
In / Out
$2.08 / $6.24
per 1M tokens
Value
~961
chats / $10
Zhipu (GLM)
GLM-4 Flash
- Free-tier friendly
- Fast
In / Out
$0.00 / $0.00
per 1M tokens
Value
—
chats / $10
Multilingual
7 modelsMistral AI
Mistral Small
- Balanced cost
- Fast
In / Out
$0.10 / $0.31
per 1M tokens
Value
~19,230
chats / $10
OpenAI
GPT-4o mini
- Very cheap
- Fast
In / Out
$0.16 / $0.62
per 1M tokens
Value
~10,683
chats / $10
Meta (Llama)
Llama 3.3 70B Instruct
- Open ecosystem
- Hosted via Together
In / Out
$0.92 / $0.92
per 1M tokens
Value
~3,623
chats / $10
Alibaba (Qwen)
Qwen3 Turbo
- Cheapest tier
- Fast
In / Out
$0.05 / $0.20
per 1M tokens
Value
~33,333
chats / $10
Mistral AI
Mistral Large
- European flagship
- Enterprise friendly
In / Out
$2.08 / $6.24
per 1M tokens
Value
~961
chats / $10
OpenAI
Whisper large-v3
- 99 languages
- Robust to noise
In / Out
$6.00 / $6.00
per 1M tokens
Value
~555
chats / $10
ElevenLabs
ElevenLabs Multilingual v2
- 29 languages
- Voice cloning
In / Out
$30.00 / $30.00
per 1M tokens
Value
~111
chats / $10
Search & rerank
2 modelsText to speech
2 modelsOpenAI
OpenAI TTS-1 HD
- Natural prosody
- 6 voices
In / Out
$15.00 / $15.00
per 1M tokens
Value
~222
chats / $10
ElevenLabs
ElevenLabs Multilingual v2
- 29 languages
- Voice cloning
In / Out
$30.00 / $30.00
per 1M tokens
Value
~111
chats / $10