Sitemap
272 public pagesModels, comparisons, guides and everything TokenRex.
Main pages
14- Home/
- Models & Pricing/models
- Compare models/models/compare
- Cost calculator/cost-calculator
- Features/features
- Integrations/integrations
- Docs/docs
- FAQ/faq
- Blog/blog
- Status/status
- OpenRouter alternative/openrouter-alternative
- India payments (UPI)/india-payments
- Send a suggestion/suggestion
- Contact & Grievances/contact
Model pages A to Z
151C
- ChatGPT Latestchat-latest
- Claude Fable 5.1claude-fable-5-1
- Claude Fable 5.1 Highclaude-fable-5-1-high
- Claude Fable 5.1 Lowclaude-fable-5-1-low
- Claude Fable 5.1 Maxclaude-fable-5-1-xhigh
- Claude Haiku 4.5claude-haiku-4-5
- Claude Haiku 4.5 Highclaude-haiku-4-5-high
- Claude Haiku 4.5 Lowclaude-haiku-4-5-low
- Claude Haiku 4.5 Maxclaude-haiku-4-5-xhigh
- Claude Opus 5claude-opus-5
- Claude Opus 5 Fastclaude-opus-5-fast
- Claude Opus 5 Fast Highclaude-opus-5-fast-high
- Claude Opus 5 Fast Lowclaude-opus-5-fast-low
- Claude Opus 5 Fast Maxclaude-opus-5-fast-xhigh
- Claude Opus 5 Highclaude-opus-5-high
- Claude Opus 5 Lowclaude-opus-5-low
- Claude Opus 5 Maxclaude-opus-5-xhigh
- Claude Opus 5.5claude-opus-5-5
- Claude Opus 5.5 Fastclaude-opus-5-5-fast
- Claude Opus 5.5 Fast Highclaude-opus-5-5-fast-high
- Claude Opus 5.5 Fast Lowclaude-opus-5-5-fast-low
- Claude Opus 5.5 Fast Maxclaude-opus-5-5-fast-xhigh
- Claude Opus 5.5 Highclaude-opus-5-5-high
- Claude Opus 5.5 Lowclaude-opus-5-5-low
- Claude Opus 5.5 Maxclaude-opus-5-5-xhigh
- Claude Sonnet 5claude-sonnet-5
- Claude Sonnet 5 Highclaude-sonnet-5-high
- Claude Sonnet 5 Lowclaude-sonnet-5-low
- Claude Sonnet 5 Maxclaude-sonnet-5-xhigh
G
- Gemini 2.5 Flashgemini-2.5-flash
- Gemini 2.5 Flash Imagegemini-2.5-flash-image
- Gemini 2.5 Flash Litegemini-2.5-flash-lite
- Gemini 2.5 Flash Lite TTSgemini-2.5-flash-lite-preview-tts
- Gemini 2.5 Flash TTSgemini-2.5-flash-tts
- Gemini 2.5 Progemini-2.5-pro
- Gemini 2.5 Pro TTSgemini-2.5-pro-tts
- Gemini 3 Flashgemini-3-flash-preview
- Gemini 3 Pro Imagegemini-3-pro-image
- Gemini 3 Pro Image 2Kgemini-3-pro-image-2k
- Gemini 3 Pro Image 4Kgemini-3-pro-image-4k
- Gemini 3.1 Flash Imagegemini-3.1-flash-image
- Gemini 3.1 Flash Image 2Kgemini-3.1-flash-image-2k
- Gemini 3.1 Flash Image 4Kgemini-3.1-flash-image-4k
- Gemini 3.1 Flash Litegemini-3.1-flash-lite
- Gemini 3.1 Flash Lite Imagegemini-3.1-flash-lite-image
- Gemini 3.1 Flash TTSgemini-3.1-flash-tts-preview
- Gemini 3.1 Progemini-3.1-pro-preview
- Gemini 3.5 Flashgemini-3.5-flash
- Gemini 3.5 Transcribegemini-3.5-transcribe
- Gemini 3.6 Flashgemini-3.6-flash
- Gemini 3.7 Flashgemini-3.7-flash
- Gemini 3.8 Flashgemini-3.8-flash
- Gemini 4 Argongemini-4-argon
- Gemini Embedding 001gemini-embedding-001
- Gemini Embedding 2gemini-embedding-2
- Gemini Omni 1.1 Flashgemini-omni-1.1-flash
- GPT Image 1 Minigpt-image-1-mini
- GPT Image 2gpt-image-2
- GPT Image 2.5 Flaregpt-image-2.5-flare
- GPT Image 2.5 Sunburstgpt-image-2.5-sunburst
- GPT Live 1gpt-live-1
- GPT Transcribegpt-transcribe
- GPT-4o Mini Transcribegpt-4o-mini-transcribe
- GPT-4o Mini TTSgpt-4o-mini-tts
- GPT-4o Transcribegpt-4o-transcribe
- GPT-5gpt-5
- GPT-5 Deepgpt-5-high
- GPT-5 Fastgpt-5-low
- GPT-5 Maxgpt-5-xhigh
- GPT-5 Minigpt-5-mini
- GPT-5 Mini Deepgpt-5-mini-high
- GPT-5 Mini Fastgpt-5-mini-low
- GPT-5 Mini Maxgpt-5-mini-xhigh
- GPT-5 Nanogpt-5-nano
- GPT-5 Nano Deepgpt-5-nano-high
- GPT-5 Nano Fastgpt-5-nano-low
- GPT-5 Nano Maxgpt-5-nano-xhigh
- GPT-5.2gpt-5.2
- GPT-5.2 Deepgpt-5.2-high
- GPT-5.2 Fastgpt-5.2-low
- GPT-5.2 Maxgpt-5.2-xhigh
- GPT-5.4gpt-5.4
- GPT-5.4 Deepgpt-5.4-high
- GPT-5.4 Fastgpt-5.4-low
- GPT-5.4 Maxgpt-5.4-xhigh
- GPT-5.4 Minigpt-5.4-mini
- GPT-5.4 Mini Deepgpt-5.4-mini-high
- GPT-5.4 Mini Fastgpt-5.4-mini-low
- GPT-5.4 Mini Maxgpt-5.4-mini-xhigh
- GPT-5.4 Nanogpt-5.4-nano
- GPT-5.4 Nano Deepgpt-5.4-nano-high
- GPT-5.4 Nano Fastgpt-5.4-nano-low
- GPT-5.4 Nano Maxgpt-5.4-nano-xhigh
- GPT-5.4 Progpt-5.4-pro
- GPT-5.4 Pro Deepgpt-5.4-pro-high
- GPT-5.4 Pro Maxgpt-5.4-pro-xhigh
- GPT-5.5gpt-5.5
- GPT-5.5 Deepgpt-5.5-high
- GPT-5.5 Fastgpt-5.5-low
- GPT-5.5 Maxgpt-5.5-xhigh
- GPT-5.5 Progpt-5.5-pro
- GPT-5.5 Pro Deepgpt-5.5-pro-high
- GPT-5.5 Pro Maxgpt-5.5-pro-xhigh
- GPT-5.6 Lunagpt-5.6-luna
- GPT-5.6 Luna Deepgpt-5.6-luna-high
- GPT-5.6 Luna Fastgpt-5.6-luna-low
- GPT-5.6 Luna Maxgpt-5.6-luna-xhigh
- GPT-5.6 Solgpt-5.6-sol
- GPT-5.6 Sol Deepgpt-5.6-sol-high
- GPT-5.6 Sol Fastgpt-5.6-sol-low
- GPT-5.6 Sol Maxgpt-5.6-sol-xhigh
- GPT-5.6 Terragpt-5.6-terra
- GPT-5.6 Terra Deepgpt-5.6-terra-high
- GPT-5.6 Terra Fastgpt-5.6-terra-low
- GPT-5.6 Terra Maxgpt-5.6-terra-xhigh
- GPT-6 Astragpt-6-astra
- GPT-6 Astra Deepgpt-6-astra-high
- GPT-6 Astra Fastgpt-6-astra-fast
- GPT-6 Astra Fast Highgpt-6-astra-fast-high
- GPT-6 Astra Fast Lowgpt-6-astra-fast-low
- GPT-6 Astra Fast Maxgpt-6-astra-fast-xhigh
- GPT-6 Astra Lowgpt-6-astra-low
- GPT-6 Astra Maxgpt-6-astra-xhigh
- GPT-6 Lunagpt-6-luna
- GPT-6 Luna Deepgpt-6-luna-high
- GPT-6 Luna Fastgpt-6-luna-low
- GPT-6 Luna Maxgpt-6-luna-xhigh
- GPT-6 Solgpt-6-sol
- GPT-6 Sol Deepgpt-6-sol-high
- GPT-6 Sol Fastgpt-6-sol-fast
- GPT-6 Sol Fast Highgpt-6-sol-fast-high
- GPT-6 Sol Fast Lowgpt-6-sol-fast-low
- GPT-6 Sol Fast Maxgpt-6-sol-fast-xhigh
- GPT-6 Sol Lowgpt-6-sol-low
- GPT-6 Sol Maxgpt-6-sol-xhigh
- GPT-6.1 Solgpt-6.1-sol
- GPT-6.1 Sol Deepgpt-6.1-sol-high
- GPT-6.1 Sol Fastgpt-6.1-sol-fast
- GPT-6.1 Sol Fast Highgpt-6.1-sol-fast-high
- GPT-6.1 Sol Fast Lowgpt-6.1-sol-fast-low
- GPT-6.1 Sol Fast Maxgpt-6.1-sol-fast-xhigh
- GPT-6.1 Sol Lowgpt-6.1-sol-low
- GPT-6.1 Sol Maxgpt-6.1-sol-xhigh
Model comparisons
16- Claude Haiku 4.5 vs Gemini 3.8 Flash/models/vs/claude-haiku-4-5-vs-gemini-3.8-flash
- Claude Opus 5.5 vs Claude Sonnet 5/models/vs/claude-opus-5-5-vs-claude-sonnet-5
- Claude Opus 5.5 vs Gemini 4 Argon/models/vs/claude-opus-5-5-vs-gemini-4-argon
- Claude Sonnet 5 vs Gemini 3.1 Pro/models/vs/claude-sonnet-5-vs-gemini-3.1-pro-preview
- GPT-5 Mini vs Gemini 2.5 Flash/models/vs/gpt-5-mini-vs-gemini-2.5-flash
- GPT-5 Nano vs Gemini 2.5 Flash Lite/models/vs/gpt-5-nano-vs-gemini-2.5-flash-lite
- GPT-5 vs Gemini 2.5 Pro/models/vs/gpt-5-vs-gemini-2.5-pro
- GPT-5.4 Mini vs Claude Haiku 4.5/models/vs/gpt-5.4-mini-vs-claude-haiku-4-5
- GPT-5.5 vs Claude Sonnet 5/models/vs/gpt-5.5-vs-claude-sonnet-5
- GPT-5.5 vs Gemini 2.5 Pro/models/vs/gpt-5.5-vs-gemini-2.5-pro
- GPT-6 Astra vs Claude Sonnet 5/models/vs/gpt-6-astra-vs-claude-sonnet-5
- GPT-6 Astra vs Gemini 3.1 Pro/models/vs/gpt-6-astra-vs-gemini-3.1-pro-preview
- GPT-6 Luna vs Gemini 3.8 Flash/models/vs/gpt-6-luna-vs-gemini-3.8-flash
- GPT-6 Sol vs Claude Opus 5.5/models/vs/gpt-6-sol-vs-claude-opus-5-5
- GPT-6 Sol vs Gemini 4 Argon/models/vs/gpt-6-sol-vs-gemini-4-argon
- GPT-6.1 Sol vs GPT-6 Sol/models/vs/gpt-6.1-sol-vs-gpt-6-sol
Integration guides
38- Agent Zero/integrations/agent-zero
- Aider/integrations/aider
- API Integration/integrations/api-integration
- Apple Xcode/integrations/xcode
- Chatbox/integrations/chatbox
- Claude Code/integrations/claude-code
- Claude Desktop app/integrations/claude-desktop
- Cline/integrations/cline
- Continue/integrations/continue
- Cursor/integrations/cursor
- DeepSeek Harness/integrations/deepseek-harness
- Dify/integrations/dify
- Droid (Factory)/integrations/droid
- Flowise/integrations/flowise
- GitHub Copilot CLI/integrations/copilot-cli
- Goose/integrations/goose
- Hermes Agent/integrations/hermes-agent
- Hermes Desktop/integrations/hermes-desktop
- JetBrains AI Assistant/integrations/jetbrains-ai-assistant
- Kilo Code/integrations/kilo-code
- LangChain/integrations/langchain
- Langflow/integrations/langflow
- LibreChat/integrations/librechat
- LobeChat/integrations/lobechat
- n8n/integrations/n8n
- nanobot/integrations/nanobot
- Oh My Pi/integrations/oh-my-pi
- Open WebUI/integrations/open-webui
- OpenAI Codex CLI/integrations/codex
- OpenClaw/integrations/openclaw
- OpenCode/integrations/opencode
- Pi coding agent/integrations/pi
- Poolside Agent CLI/integrations/poolside
- Qwen Code/integrations/qwen-code
- Roo Code/integrations/roo-code
- TypingMind/integrations/typingmind
- VS Code/integrations/vs-code
- Zed/integrations/zed
Blog articles
46- 12 tactics to cut your LLM bill in half/blog/cost-optimization-tactics
- Batch inference at scale/blog/batch-inference
- Build a chatbot in FastAPI/blog/chatbot-fastapi
- Build a chatbot in Go/blog/chatbot-go
- Build a chatbot in Next.js — streaming, memory, and UI/blog/chatbot-nextjs
- Build a chatbot in Rails — Hotwire streaming/blog/chatbot-rails
- Build a WhatsApp bot with TokenRex in 20 lines/blog/whatsapp-bot-in-20-lines
- Building a coding copilot with GPT-5 Codex/blog/coding-copilot-gpt5-codex
- Building a multi-tenant SaaS on top of TokenRex/blog/multi-tenant-saas
- Building a production RAG pipeline/blog/rag-pipeline
- Building an agent with tool loops — end to end/blog/building-an-agent
- Building an image generation SaaS/blog/image-gen-saas
- Changelog — July 2026/blog/changelog-july-2026
- Choosing an image model: Nano Banana vs GPT Image/blog/image-models-nano-banana-vs-gpt-image
- Chunking strategies for RAG/blog/chunking-strategies-rag
- Claude tier via TokenRex — long-form writing that doesn't feel like AI/blog/claude-tier-tokenbaazar
- Cursor with a custom base URL/blog/cursor-custom-base-url
- Embeddings and semantic search — a builder's guide/blog/embeddings-semantic-search
- Error handling patterns for LLM APIs/blog/error-handling-patterns
- Function calling in 2026 — patterns that actually work/blog/function-calling-2026
- Gemini 3 Pro — a deep dive/blog/gemini-3-pro-deep-dive
- GPT-5.4 Mini vs Gemini 3 Flash — real cost-per-1K in rupees/blog/gpt-5-vs-gemini-3-flash
- How OpenAI-compatible endpoints actually work/blog/openai-compatible-endpoints
- Introducing TokenRex — frontier AI, at market price, forever/blog/introducing-tokenbaazar
- JSON mode and structured outputs — a field guide/blog/json-mode-structured-outputs
- Key rotation and per-key spend caps/blog/key-rotation
- LangChain + TokenRex — setup in 3 lines/blog/langchain-setup
- LlamaIndex + TokenRex — setup/blog/llamaindex-setup
- Long context — when to use 1M tokens (and when not to)/blog/long-context-1m
- Migrate from OpenAI to TokenRex in 5 minutes/blog/migrate-from-openai
- Multi-turn memory patterns for chatbots/blog/multi-turn-memory
- Observability for LLM apps — what to log, what to alert on/blog/observability-llm-apps
- Prompt caching — save 50% on repeated context/blog/prompt-caching
- Rate limits and how to handle them/blog/rate-limits-handling
- Reranking for better RAG — cheaper than a bigger LLM/blog/reranking-rag
- Security best practices for API keys/blog/api-key-security
- Speech-to-text with Whisper-class models/blog/speech-to-text-whisper
- Streaming JSON with partial parsing/blog/streaming-json-partial
- Streaming responses with SSE — a practical guide/blog/streaming-sse-guide
- Testing prompts with golden datasets/blog/testing-prompts-golden
- Text-to-speech — choosing a voice model in 2026/blog/text-to-speech-voices
- The complete image generation guide/blog/image-generation-guide
- Vercel AI SDK + TokenRex/blog/vercel-ai-sdk
- Vision inputs — sending images to GPT-5 and Gemini 3/blog/vision-inputs-gpt5
- Voice assistants — the modern architecture/blog/voice-assistant-architecture
- Wallet, billing & per-request cost — the exact formula/blog/how-billing-is-calculated