Choose Auto, TokenLab Verified, or Official for each request, with prices shown up front. See what's new

Models

Compare models by price, context, and capability. The Official price is the model maker's published price.

Catalog updated 2026-11-13 · 368 models · pay-as-you-go · one-time $0.25 free trial credit: up to 10 calls in 7 days · $5 minimum top-up · first $10 top-up credits $15 · one OpenAI-compatible endpoint (/v1/chat/completions)

ModelContextMax outputOfficial priceVerified priceDiscount
gpt-6.1-solCodePrompt CacheReasoningTool useCached input 95% less
Available
1.05M128KOfficial price
Input$2.00/1MOutput$10.00/1M
Verified price-70% Discount
Input$0.60/1MOutput$3.00/1M
-70%
gpt-5.6-lunaCodeJSON modePrompt CacheReasoningTool useVisionCached input 90% less
Available
1.05M128KOfficial price
Input$0.20/1MOutput$1.20/1M
Verified price-70% Discount
Input$0.06/1MOutput$0.36/1M
-70%
gpt-5.6-solCodeJSON modePrompt CacheReasoningTool useVisionCached input 90% less
Available
1.05M128KOfficial price
Input$4.00/1MOutput$20.00/1M
Verified price-70% Discount
Input$1.20/1MOutput$6.00/1M
-70%
gpt-5.6-terraCodeJSON modePrompt CacheReasoningTool useVisionCached input 90% less
Available
1.05M128KOfficial price
Input$2.00/1MOutput$12.00/1M
Verified price-70% Discount
Input$0.60/1MOutput$3.60/1M
-70%
gpt-6-lunaCodeJSON modePrompt CacheReasoningTool useVisionCached input 90% less
Available
1.05M128KOfficial price
Input$0.10/1MOutput$0.50/1M
Verified price-70% Discount
Input$0.03/1MOutput$0.15/1M
-70%
gpt-6-solCodeJSON modePrompt CacheReasoningTool useVisionCached input 90% less
Available
1.05M128KOfficial price
Input$2.00/1MOutput$10.00/1M
Verified price-70% Discount
Input$0.60/1MOutput$3.00/1M
-70%
gpt-5.5CodeJSON modePrompt CacheReasoningTool useVisionCached input 90% less
Available
1.05M128KOfficial price
Input$5.00/1MOutput$30.00/1M
Verified price-30% Discount
Input$3.50/1MOutput$21.00/1M
-30%
gpt-6-astraCodeJSON modePrompt CacheReasoningTool useVisionCached input 90% less
Available
1.05M128KOfficial price
Input$10.00/1MOutput$50.00/1M
Verified price-70% Discount
Input$3.00/1MOutput$15.00/1M
-70%
glm-5.3CodeJSON modePrompt CacheReasoningTool useSupports prompt caching
Available
1M128KOfficial price
Input$1.40/1MOutput$4.40/1M
Verified price— Discount
—
—
grok-build-0.1CodeJSON modePrompt CacheReasoningTool useVisionSupports prompt caching
Available
256K128KOfficial price
Input$1.00/1MOutput$2.00/1M
Verified price— Discount
—
—
doubao-seed-2.0-codeCodeJSON modePrompt CacheReasoningTool useSupports prompt caching
Available
229K128KOfficial price
Input$0.4706/1MOutput$2.35/1M
Verified price— Discount
—
—
gpt-5.5-proCodeJSON modeReasoningTool useVision
Available
1.05M128KOfficial price
Input$30.00/1MOutput$180.00/1M
Verified price— Discount
—
—
ember-1CodePrompt CacheReasoningTool useSupports prompt caching
PreviewAvailable
1M—Official price
Input$3.00/1MOutput$15.00/1M
Verified price— Discount
—
—
nova-2-liteCodeReasoningTool useSupports prompt caching
Available
1M—Official price
Input$0.30/1MOutput$2.50/1M
Verified price— Discount
—
—
qwen3-coder-flashCodePrompt CacheSupports prompt caching
Available
998K64KOfficial price
Input$0.30/1MOutput$1.50/1M
Verified price— Discount
—
—
claude-fable-5-2JSON modePrompt CacheReasoningTool useVisionCached input 98% less
Available
1M128KOfficial price
Input$8.00/1MOutput$40.00/1M
Verified price-65% Discount
Input$2.80/1MOutput$14.00/1M
-65%
hy4Prompt CacheReasoningTool useVisionSupports prompt caching
Available
960K64KOfficial price
Input$0.417/1MOutput$1.25/1M
Verified price— Discount
—
—
gpt-6.1-terraPrompt CacheReasoningTool useVisionCached input 95% less
Available
1.05M128KOfficial price
Input$1.00/1MOutput$5.00/1M
Verified price-70% Discount
Input$0.30/1MOutput$1.50/1M
-70%
gemini-4-argonJSON modePrompt CacheReasoningTool useVisionCached input 95% less
Available
1M64KOfficial price
Input$2.00/1MOutput$10.00/1M
Verified price-50% Discount
Input$1.00/1MOutput$5.00/1M
-50%
claude-haiku-5-5JSON modePrompt CacheReasoningTool useVisionCached input 90% less
Available
1M128KOfficial price
Input$0.10/1MOutput$0.50/1M
Verified price-65% Discount
Input$0.035/1MOutput$0.175/1M
-65%
claude-opus-4-8JSON modePrompt CacheReasoningTool useVisionCached input 90% less
Available
1M128KOfficial price
Input$5.00/1MOutput$25.00/1M
Verified price-65% Discount
Input$1.75/1MOutput$8.75/1M
-65%
gemini-3.8-flashJSON modePrompt CacheTool useVisionCached input 90% less
Available
1M64KOfficial price
Input$0.75/1MOutput$3.75/1M
Verified price-50% Discount
Input$0.375/1MOutput$1.88/1M
-50%
claude-opus-4-7JSON modePrompt CacheReasoningTool useVisionCached input 90% less
Available
1M128KOfficial price
Input$5.00/1MOutput$25.00/1M
Verified price-65% Discount
Input$1.75/1MOutput$8.75/1M
-65%
gemini-3.5-flash-liteJSON modePrompt CacheTool useVisionCached input 90% less
Available
1M64KOfficial price
Input$0.30/1MOutput$2.50/1M
Verified price-50% Discount
Input$0.15/1MOutput$1.25/1M
-50%
1 / 16

All models

368

All model series

6 series

About the TokenLab model catalog

This page is the public catalog of AI models you can call through one TokenLab API. Each entry shows the maker, the model series, the supported tasks, the context window, and the input and output price, so you can compare options before you write any code.

Models are grouped into series, such as a vendor family with several sizes or releases. Open a series to see every available version, its capabilities, and a request example you can copy.

Model categories you can browse

  • Chat and reasoning. Text generation, question answering, long-context analysis, tool calling, and step-by-step reasoning.
  • Coding. Models tuned for code completion, review, refactoring, and agent workflows inside editors and terminals.
  • Image. Image generation and editing, plus vision models that read screenshots, charts, and photos.
  • Video. Text-to-video and image-to-video generation, priced per second or per clip.
  • Audio and speech. Text-to-speech, speech-to-text transcription, and music generation.
  • Embedding and rerank. Vector embeddings for search and retrieval, and rerankers that sort results by relevance.

How to choose a model

Start with the task. Filter the catalog by category, then narrow it by maker if your team already prefers one. Use search when you know part of a model name.

Next, compare price and limits. Text models are priced per token with separate input and output rates, image and video models are usually priced per image or per second, and the table shows which unit applies. Check the context window and the maximum output length against your longest prompt.

Finally, test with a small request. Because every model is reached through the same API, switching later means changing the model name in your request, not rewriting your integration.

Pricing and how to get started

TokenLab is prepaid and pay as you go. There is no subscription and no seat fee. You add funds to your balance and each call is deducted at the per-model rate shown in this catalog. Your balance does not expire.

Free trial credit is not always on. When it is offered to new accounts, the console shows the amount and its expiry once you sign up, so you can try a model before you add funds. Otherwise, a small first top-up is enough to start testing.

To begin, create an account, create an API key in the console, and send your first request to the model you picked. If you work in a coding agent such as Claude, Codex, or Cursor, you can connect over MCP and search models and prices from inside the tool.

Related pages