Buy tokens. Use any model.

Top up once, share team keys, and run models through one clean API.

DeepSeek V4 Pro 202606

DeepSeek V4 Flash 202605

3.5 Flash

DeepSeek V4 Pro

DeepSeek V4 Flash

GLM 5.1

Kimi K2.6

Kimi K2.5

MiniMax M3

MiniMax M2.7

MiniMax M2.5

GLM 5V Turbo

GLM 5 Turbo

GLM 5

DeepSeek V3.2

Nano Banana 2

Nano Banana Pro

Nano Banana

3.1 Flash TTS

Grok Voice TTS 1.0

MAI Voice 2

Orpheus 3B

CSM 1B

Kokoro 82M

Nova 3

Model access your team can read

Each alias shows model type, capability, and cost context before a developer copies it into a tool.

DeepSeek V4 Pro 202606

Vendor-direct DeepSeek V4 Pro for deeper reasoning and code work.

Input

$0.435/M

Output

$0.87/M

Context

DeepSeek V4 Flash 202605

Vendor-direct DeepSeek V4 Flash for quick, low-cost assistant work.

Input

$0.14/M

Output

$0.28/M

Context

Gemini 3.5 Flash

A quick general-purpose model for everyday coding assistant work.

Input

$1.50/M

Output

$9/M

Context

DeepSeek V4 Pro

Deep reasoning and structured output for heavier implementation work.

Input

$1.74/M

Output

$3.48/M

Context

DeepSeek V4 Flash

Low-cost fast responses for lightweight code edits and daily assistants.

Input

$0.14/M

Output

$0.28/M

Context

GLM 5.1

Long-form reasoning coverage for structured code and planning tasks.

Input

$1.40/M

Output

$4.40/M

Context

200K

Kimi K2.6

A strong coding model for code generation, repair, and review loops.

Input

$0.858/M

Output

$3.566/M

Context

256K

Kimi K2.5

Agentic coding and multimodal reasoning with a long working context.

Input

$0.60/M

Output

$3/M

Context

256K

MiniMax M3

Large-context multimodal reasoning for long documents and agent plans.

Input

$0.60/M

Output

$2.40/M

Context

MiniMax M2.7

Balanced MiniMax model for long context reasoning and function calling.

Input

$0.30/M

Output

$1.20/M

Context

200K

MiniMax M2.5

Compact MiniMax reasoning model for efficient agent and document work.

Input

$0.30/M

Output

$1.20/M

Context

200K

GLM 5V Turbo

Vision-capable GLM 5 Turbo for multimodal analysis and tool use.

Input

$1.20/M

Output

$4/M

Context

200K

GLM 5 Turbo

Faster GLM 5 variant for everyday reasoning and structured responses.

Input

$1.20/M

Output

$4/M

Context

200K

GLM 5

Flagship GLM reasoning model for long planning and tool-heavy work.

Input

$1/M

Output

$3.20/M

Context

200K

DeepSeek V3.2

Deep reasoning and structured output for complex coding and planning.

Input

$0.57/M

Output

$1.71/M

Context

128K

Buy tokens once. Give your team simple access to the models they need.

Team credits

Top up once and share access with your team.

Usage limits

Give each teammate or key a clear limit.

Model access

Use chat, image, speech, and audio models from one URL.

Keep team credits simple

Top up, issue keys, set limits, and track usage in one place.

Team token wallet

Buy credits for your team and keep spend predictable.

One API URL

Use one OpenAI-compatible URL across apps, editors, and SDKs.

Model catalog

Pick from text, image, audio, and speech models.

Spend tracking

Track token use before it becomes a billing surprise.