Models

31 / 31

Models

DeepSeek V4 Pro 202606 DeepSeek V4 Pro 202606deepseek-v4-pro-202606

DeepSeek V4 Pro snapshot with 1M context for hard reasoning.

Flagshipctx 200k

Use this model
DeepSeek V4 Flash DeepSeek V4 Flashdeepseek-v4-flash-202605

DeepSeek V4 Flash snapshot with 1M context for agents and code.

Litectx 200k

Use this model
DeepSeek V4.1 Flash DeepSeek V4.1 Flashdeepseek-v4.1-flash

Fast DeepSeek model for everyday tasks.

Litectx 200k

Use this model
DeepSeek V4 Flash Vision DeepSeek V4 Flash Visiondeepseek/deepseek-v4-flash-vision-exp

Experimental vision-enabled DeepSeek V4 Flash build.

Lite visionctx 200k

Use this model
GLM-5.2 GLM-5.2glm-5.2

Capable GLM model for everyday conversations and tasks.

Balancedctx 200k

Use this model
GLM-5.3 Flash GLM-5.3 Flashglm-5.3-flash

Fast GLM-5.3 variant with 1M context and vision.

Litectx 1M

Use this model
Kimi K2.6 Kimi K2.6kimi-k2.6

Versatile Kimi model for conversations and tasks.

Balancedctx 256k

Use this model
Kimi K2.7 Code Kimi K2.7 Codekimi-k2.7-code

Kimi coding model for software development tasks.

Codingctx 256k

Use this model
Kimi K2.7 Code Highspeed Kimi K2.7 Code Highspeedkimi-k2.7-code-highspeed

High-speed Kimi code model with 256K context.

Codingctx 256k

Use this model
Kimi K2.8 Preview Kimi K2.8 Previewkimi-k2.8-preview

Preview of the next Kimi generation; 256K context.

Balancedctx 256k

Use this model
MiMo V2.6 Flash MiMo V2.6 Flashmimo-v2.6-flash

Open source model served via Tencent TokenHub.

Litectx 256k

Use this model
MiMo V2.6 Pro MiMo V2.6 Promimo-v2.6-pro

Open source model served via Tencent TokenHub.

Balancedctx 256k

Use this model
GPT 6.1 Sol GPT 6.1 Solgpt-6.1-sol

Newest flagship with 1M context for agent workloads.

Flagship visionctx 1.05M

Use this model
GPT 6 Luna GPT 6 Lunagpt-6-luna

New-generation Luna with 1M context and multimodal agents.

Flagship visionctx 1.05M

Use this model
GPT 6 Astra GPT 6 Astragpt-6-astra

New-generation flagship model with high quality and balanced speed.

Flagship visionctx 1.05M

Use this model
GPT 6 Sol GPT 6 Solgpt-6-sol

New-generation Sol with 1M context and balanced power.

Flagship visionctx 1.05M

Use this model
GPT 5.6 Terra GPT 5.6 Terragpt-5.6-terra

Strong general-purpose model with 1M context.

Flagship visionctx 1.05M

Use this model
GPT 5.6 Luna GPT 5.6 Lunagpt-5.6-luna

Balanced model for reasoning, coding, and long-context work.

Flagship visionctx 1.05M

Use this model
GPT 5.6 Sol GPT 5.6 Solgpt-5.6-sol

Flagship model for maximum quality and demanding tasks.

Flagship visionctx 1.05M

Use this model
GPT 5.5 GPT 5.5gpt-5.5

Fast GPT-5.5 chat model for light tasks and everyday conversations.

Flagship visionctx 1.05M

Use this model
GPT 5.4 Pro GPT 5.4 Progpt-5.4-pro

Advanced reasoning model for hard agentic and coding tasks. Responses API only.

Flagship visionctx 1.05M

Use this model
GPT 5.4 GPT 5.4gpt-5.4

New-generation model with 1M context for general use.

Balanced visionctx 1.05M

Use this model
GPT 5.4 Mini GPT 5.4 Minigpt-5.4-mini

Fast and cost-effective with 400K context.

Balanced visionctx 400k

Use this model
GPT 5.4 Nano GPT 5.4 Nanogpt-5.4-nano

Fastest and cheapest with 400K context for simple jobs.

Lite visionctx 400k

Use this model
GPT 5.3 Codex GPT 5.3 Codexgpt-5.3-codex

Code-optimized model with 400K context.

Balanced visionctx 400k

Use this model
GPT 5.2 GPT 5.2gpt-5.2

Balanced general model with 400K context.

Balanced visionctx 400k

Use this model
GPT 5.1 Codex Mini GPT 5.1 Codex Minigpt-5.1-codex-mini

Light, fast code model with 400K context.

Balanced visionctx 400k

Use this model
GPT 5 GPT 5gpt-5

Strong general model with 400K context.

Balanced visionctx 400k

Use this model
GPT 5 Mini GPT 5 Minigpt-5-mini

Fast and economical with 400K context.

Balanced visionctx 400k

Use this model
GPT 5 Nano GPT 5 Nanogpt-5-nano

Lightest model with 400K context for high volume.

Lite visionctx 400k

Use this model
GPT 4o GPT 4ogpt-4o

Classic strong multimodal model with 128K context.

Balanced visionctx 128k

Use this model