Model library
Models (15)
DeepSeek
Try in playgroundDeepSeek V4 Flash
Best for: fast, low-cost general tasks
$/MTOK
- Context
- 1M
- Input
- $0.04
- Output
- $0.21
Xiaomi
Try in playgroundMiMo-V2.5
Best for: omnimodal understanding across text, image, audio and video
$/MTOK
- Context
- 1M
- Input
- $0.12
- Output
- $0.24
Qwen
Try in playgroundQwen3.6-35B-A3B
Best for: lightweight workloads at minimal cost
$/MTOK
- Context
- 262K
- Input
- $0.04
- Output
- $0.35
Z.ai
Try in playgroundGLM-5.3 Flash
Best for: low-cost long-context multimodal work at speed
$/MTOK
- Context
- 1M
- Input
- $0.12
- Output
- $0.40
Qwen
Try in playgroundQwen3.8 Flash
Best for: fast, low-cost general tasks
$/MTOK
- Context
- 1M
- Input
- $0.15
- Output
- $0.47
NVIDIA
Try in playgroundNemotron 3 Super
Best for: long-context reasoning and tool use
$/MTOK
- Context
- 262K
- Input
- $0.12
- Output
- $0.52
- New
DeepSeek
Try in playgroundDeepSeek V4.1 Flash
Best for: fast, low-cost agentic coding and visual analysis
$/MTOK
- Context
- 1M
- Input
- $0.20
- Output
- $1.00
MiniMax
Try in playgroundMiniMax M3
Best for: long-horizon agentic work over text, image and video
$/MTOK
- Context
- 1M
- Input
- $0.28
- Output
- $1.10
OpenAI
Try in playgroundGPT-5.6 Luna
Best for: high-volume GPT-5.6 chat, classification, and light agents
$/MTOK
- Context
- 262K
- Input
- $0.20
- Output
- $1.20
DeepSeek
Try in playgroundDeepSeek V4 Pro
Best for: frontier reasoning and agentic coding
$/MTOK
- Context
- 1M
- Input
- $1.04
- Output
- $2.08
Z.ai
Try in playgroundGLM-5.2
Best for: flagship general-purpose chat and reasoning
$/MTOK
- Context
- 262K
- Input
- $0.34
- Output
- $2.30
OpenAI
Try in playgroundGPT-5.6 Sol
Best for: GPT-5.6 flagship for CLI-heavy coding and long-horizon problem solving
$/MTOK
- Context
- 262K
- Input
- $2.00
- Output
- $10.00
Moonshot AI
Try in playgroundKimi K3
Best for: agentic coding, tool use, and long-horizon reasoning
$/MTOK
- Context
- 1M
- Input
- $2.30
- Output
- $11.40
Anthropic
Try in playgroundClaude Opus 5
Best for: anthropic Opus 5 for demanding coding, review, and long-horizon agents
$/MTOK
- Context
- 262K
- Input
- $5.00
- Output
- $25.00
Anthropic
Try in playgroundClaude Fable 5.1
Best for: claude Fable 5.1 for agentic coding, front-end generation, and knowledge work
$/MTOK
- Context
- 262K
- Input
- $10.00
- Output
- $50.00
