Models Directory

Search supported models across GLM, DeepSeek, MiniMax, and Moonshot with 1M-token context windows and transparent credit pricing. Copy any model ID directly into your OpenAI SDK calls.

Showing 8 models (catalog source: live gateway cache)Pricing shown in Blazo credits per 1M tokens (2.0x compute multiplier, 150 credits = $1.00)
DeepSeekVision

DeepSeek V4.1 Flash Fast

deepseek/deepseek-v4.1-flash-fast

Ultra-economical high-speed inference tier with 1M context window.

Context
1M
Input / 1M
3 cr
Output / 1M
24 cr
MiniMaxVision

MiniMax M3.1 Flash

minimax/minimax-m3.1-flash

Fast multimodal assistant model built for structured tool workflows.

Context
1M
Input / 1M
6 cr
Output / 1M
24 cr
DeepSeekVision

DeepSeek V4.1 Flash

deepseek/deepseek-v4.1-flash

High-throughput multimodal DeepSeek model for coding, JSON, and analysis.

Context
1M
Input / 1M
36 cr
Output / 1M
135 cr
DeepSeekVision

DeepSeek V4.1 Flash Turbo

deepseek/deepseek-v4.1-flash-turbo

Accelerated DeepSeek Flash variant optimized for streaming latency.

Context
1M
Input / 1M
36 cr
Output / 1M
135 cr
GLMVision

GLM 5.3 Flash

glm/glm-5.3-flash

Low-latency multimodal GLM model tuned for interactive developer apps.

Context
1M
Input / 1M
36 cr
Output / 1M
150 cr
MoonshotVision

Kimi K3.1 Pro

moonshot/kimi-k3.1-pro

Long-context enterprise reasoning model with multimodal vision support.

Context
1M
Input / 1M
75 cr
Output / 1M
750 cr
GLM

GLM 5.3

glm/glm-5.3

Flagship general reasoning and code synthesis model with 1M token context.

Context
1M
Input / 1M
300 cr
Output / 1M
600 cr
MoonshotVision

Kimi K3.1 Pro Extended

moonshot/kimi-k3.1-pro-extended

Extended-capacity Kimi K3.1 Pro tier for complex multi-step reasoning.

Context
1M
Input / 1M
450 cr
Output / 1M
900 cr