Models

Run the world’s leading models for less, with TPCoin.

Frontier models and niche models built by creators. Every model has its own TPA address, and you pay per call.

16 models shown

CLD-000

Claude Fable 5.2

Textby Anthropic

Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. In prerelease testing it completed otherwise-infeasible software migrations, designed working electronic devices from scratch, and made progress on open problems in physics and mathematics. It communicates more clearly than earlier Fable models and generates output up to 30% faster than Fable 5.1. Adaptive extended thinking is always on, with reasoning effort levels from low to max (default high) and preserved thinking across turns. Anthropic recommends Opus 5.5 as the daily driver for most coding and knowledge work, with Fable 5.2 for the most ambitious, open-ended problems.

about 0.10 TPC / messageTry it (opens in a new tab)
RCL-000

Claude Opus 5.5

Textby Anthropic

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code review and bug finding, financial and scientific analysis, and reading dense charts, diagrams, and screenshots, and it is more careful than its predecessor about only stating figures and citing sources it can back up.

about 0.05 TPC / messageTry it (opens in a new tab)
CAR-000

Gemini 4 Carbon

Textby Google

Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. It takes text, image, audio, video and file input, supports long decode of up to 1M output tokens through continuation, and controls thinking depth with low, medium and high reasoning effort.

about 0.04 TPC / messageTry it (opens in a new tab)
GEM-000

Gemini 4 Hydrogen

Textby Google

Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than Gemini 4 Carbon. It takes text, image, audio, video and file input, supports long decode of up to 1M output tokens through continuation, and controls thinking depth with low, medium, high and xhigh reasoning effort.

about 0.05 TPC / messageTry it (opens in a new tab)
GPP-999

GPT-5

Textby OpenAI

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like "think hard about this." Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.

about 0.03 TPC / messageTry it (opens in a new tab)
GPT-000

GPT-6 Astra

Textby OpenAI

GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon agentic tasks that involve computer and browser use.

about 0.05 TPC / messageTry it (opens in a new tab)
GPT-004

GPT-6 Luna

Textby OpenAI

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model. It shares the GPT-6 family's gains in factual reliability and its clearer, more concise communication style.

about 0.05 TPC / messageTry it (opens in a new tab)
DFE-111

DealMate

TextBuilt by creators

Customer support and sales booster.

LEG-000

GymGenie

TextBuilt by creators

Workout coach and fitness tracker.

APL-002

Tripster

TextBuilt by creators

Travel helper for planning trips and destinations.

ZEN-100

Carely

TextBuilt by creators

Friendly wellness assistant for health guidance.

AVA-998

Finly

TextBuilt by creators

Smart money advisor for budgeting and finance.

STG-123

StruMind

TextBuilt by creators

StruMind is an advanced AI assistant designed specifically for structural engineers, architects, and construction firms. It leverages the power of artificial intelligence to streamline the structural design process, reduce human error, and ensure optimal material use — all while complying with nati…

XRP-000

DevAI

TextBuilt by creators

Developer assistant for coding and debugging.

PWC-001

Lernix

TextBuilt by creators

Interactive AI learning companion.

MEX-605

Estatia

TextBuilt by creators

Real estate assistant for property insights.