LLMFly AI

MODEL DIRECTORY

LLM API Models: Compare GPT, Claude, Gemini and Grok

Use the provider pages to understand each model, then open Model Plaza to confirm the model ID, price, and availability for your API key.

01 · Providers

Browse by model provider

Start with model families, lifecycle notes, and protocol differences.

Provider

OpenAI

GPT-5.6 Sol, Terra and Luna

Provider

Anthropic

Current Claude model IDs and lifecycle

Provider

Google

Gemini 3.7 Flash and Gemini 3 models

Provider

xAI

Grok 4.6

02 · Model guides

Open a concrete model guide

Review pricing, context, tools, migration risks, and workload-specific guidance.

Choose by workload
Explore production LLM use cases

Start from real code generation, review, support, RAG, agent, document analysis, and extraction workflows.

01
OpenAI model family

GPT API

Compare GPT routes for general work, coding, tools, and structured output.

Family selection guide
02
Anthropic model family

Claude API

Compare Claude routes for coding, agents, analysis, and long-form work.

Family selection guide
03
Google model family

Gemini API

Compare Gemini routes for multimodal, long-context, and production applications.

Family selection guide
04
OpenAI model

GPT-5.6 Sol

OpenAI's flagship GPT-5.6 model for complex professional work, advanced coding, reasoning, and long-running agents.

1.05M context · $4 input / $20 output
05
OpenAI model

GPT-5.6 Terra

The balanced GPT-5.6 tier for production workloads that need strong reasoning and tools at a lower price than Sol.

1.05M context · $2 input / $12 output
06
OpenAI model

GPT-5.6 Luna

The cost-sensitive GPT-5.6 tier for high-volume workloads, fast routing, extraction, and lightweight reasoning.

1.05M context · $0.20 input / $1.20 output
07
Anthropic model

Claude Sonnet 5

Anthropic's fast, high-capability production model for coding, agents, document work, and tool-driven applications.

1M context · $2 input / $10 output
08
Google model

Gemini 3.7 Flash

Google's production-ready Flash model for coding, multimodal reasoning, agent workflows, and high-volume applications.

1,048,576 context · $0.75 input / $3.75 output through Dec 31, 2026
09
xAI model

Grok 4.6

xAI's flagship model for coding, AI agent workflows, knowledge work, long-running tool use, and visual interaction.

500K context · $2 input / $6 output

How to use this section

Use the model ID shown in Model Plaza

A provider's public model ID may differ from the ID available through LLMFly AI. Copy the ID exactly as shown for your API key; model IDs are case-sensitive, and unavailable IDs return a 404 error.

Browse provider hubs, then open a concrete model

Provider pages explain a model family; concrete model pages answer narrower searches about API pricing, context windows, inputs, tools, migration constraints, and use cases. Start with the exact model you plan to evaluate.

  • OpenAI: GPT-5.6 Sol, Terra, and Luna.
  • Anthropic: Claude Sonnet 5.
  • Google: Gemini 3.7 Flash.
  • xAI: Grok 4.6.

Choose an LLM API model by task

The best model depends on the work, not a universal leaderboard. Build a shortlist from the capabilities the application actually needs, then test representative tasks before production use.

  • Coding: measure accepted patches, tool reliability, repository understanding, and iteration latency.
  • Multimodal work: verify every input type, file limit, preprocessing step, and output format.
  • AI agents: test tool selection, schema adherence, recovery after tool errors, and cost across the complete loop.
  • Large-scale processing: compare throughput, retry rate, and cost per accepted result instead of price per token alone.

Compare API pricing without mixing different numbers

Provider list price, LLMFly AI price, API key billing multiplier, and the amount recorded for a real request are different values. Use provider prices to understand model tiers, Model Plaza for current platform pricing, and usage records to validate a budget.

  • Include both input and output tokens.
  • Include cache writes, cache reads, and applicable long-context tiers.
  • Include reasoning tokens, tools, retries, and conversation history.
  • Recalculate when a model, prompt, or price changes.

What to check before production use

  • Input modalities and output type.
  • Context window and maximum output.
  • Tools, structured output, and streaming behavior.
  • LLMFly AI price, billing multiplier, and current availability.
  • A tested fallback model for the same task.

Frequently asked questions

Why are provider prices shown separately?

Provider prices are useful reference points, but they are not a promise of the amount charged by LLMFly AI. Model Plaza and the usage record determine the platform charge.

Can I use the provider's model name without checking it?

No. Fetch the model list or copy the model ID from Model Plaza, and confirm that it is available to your API key.

Where is the current model list?

Open Model Plaza in the current console. It shows the models available to your API key.

Choose a model available to your API key

Open Model Plaza, copy the model ID exactly, and use it in your first request.

Open Model Plaza