# Coolhand Inference API Catalog

A curated list of LLM models available via the Coolhand inference API catalog, with pricing per million tokens.

| Provider | Model | Input ($/1M tokens) | Output ($/1M tokens) | Status |
|---|---|---|---|---|
| anthropic | Claude 3.5 Haiku | $0.8000 | $4.0000 | Deprecated |
| anthropic | Claude 3.5 Sonnet | $3.0000 | $15.0000 | Active |
| anthropic | Claude 3.7 Sonnet (Latest) | $3.0000 | $15.0000 | Active |
| anthropic | Claude 3 Haiku (2024-03-07) | $0.2500 | $1.2500 | Deprecated |
| anthropic | Claude 3 Opus | $15.0000 | $75.0000 | Deprecated |
| anthropic | Claude 3 Sonnet | $3.0000 | $15.0000 | Deprecated |
| anthropic | Claude Haiku 4.5 | $1.0000 | $5.0000 | Active |
| anthropic | Claude Haiku 4.5 | $1.0000 | $5.0000 | Active |
| anthropic | Claude Opus 4.1 | $15.0000 | $75.0000 | Deprecated |
| anthropic | Claude Opus 4 | $15.0000 | $75.0000 | Deprecated |
| anthropic | Claude Opus 4.5 | $5.0000 | $25.0000 | Active |
| anthropic | Claude Opus 4.6 | $5.0000 | $25.0000 | Active |
| anthropic | Claude Opus 4.7 | $5.0000 | $25.0000 | Active |
| anthropic | Claude Opus 4.8 | $5.0000 | $25.0000 | Active |
| anthropic | Claude Sonnet 4 | $3.0000 | $15.0000 | Deprecated |
| anthropic | Claude Sonnet 4.5 | $3.0000 | $15.0000 | Active |
| anthropic | Claude Sonnet 4.6 | $3.0000 | $15.0000 | Active |
| azure | GPT-4 | $30.0000 | $60.0000 | Active |
| azure | GPT-4.1 | $2.0000 | $8.0000 | Active |
| azure | GPT-4.1 Mini | $0.4000 | $1.6000 | Active |
| azure | GPT-4.1 Nano | $0.1000 | $0.4000 | Active |
| azure | GPT-4o | $2.5000 | $10.0000 | Active |
| azure | GPT-4o (2024-05-13) | $5.0000 | $15.0000 | Active |
| azure | GPT-4o (2024-08-06) | $2.5000 | $10.0000 | Active |
| azure | GPT-4o (2024-11-20) | $2.5000 | $10.0000 | Active |
| azure | GPT-4o Mini | $0.1500 | $0.6000 | Active |
| azure | GPT-4o Mini (2024-07-18) | $0.1500 | $0.6000 | Active |
| azure | GPT-4 Turbo | $11.0000 | $33.0000 | Active |
| azure | o1 | $15.0000 | $60.0000 | Active |
| azure | o1 Mini | $1.1000 | $4.4000 | Active |
| azure | o3 | $2.0000 | $8.0000 | Active |
| azure | o3 Mini | $1.1000 | $4.4000 | Active |
| azure | o4 Mini | $1.1000 | $4.4000 | Active |
| copilot | Claude Haiku 4.5 (via Copilot) | $1.0000 | $5.0000 | Active |
| gemini | Gemini 2.0 Flash (Standard) | $0.1000 | $0.4000 | Deprecated |
| gemini | Gemini 2.0 Flash-Lite (Standard) | $0.0750 | $0.3000 | Deprecated |
| gemini | Gemini 2.5 Flash | $0.3000 | $2.5000 | Active |
| gemini | Gemini 2.5 Flash-Lite (Batch) | $0.0500 | $0.2000 | Active |
| gemini | Gemini 2.5 Pro (&gt;200k context, Standard) | $2.5000 | $15.0000 | Active |
| gemini | Gemini 3.1 Pro Preview (Custom Tools) | $2.0000 | $12.0000 | Active |
| ollama | GPT-4 Turbo Preview (Ollama) | $0.1800 | $0.1800 | Active |
| ollama | Llama 3.1 (8b) | $0.1800 | $0.1800 | Active |
| openai | ChatGPT 4o (Latest) | $5.0000 | $15.0000 | Active |
| openai | GPT-3.5 Turbo | $0.5000 | $1.5000 | Active |
| openai | GPT-4.1 | $2.0000 | $8.0000 | Active |
| openai | GPT-4.1 (2025-04-14) | $2.0000 | $8.0000 | Active |
| openai | GPT-4.1 Mini | $0.4000 | $1.6000 | Active |
| openai | GPT-4.1 Mini (2025-04-14) | $0.8000 | $3.2000 | Active |
| openai | GPT-4.1 Nano | $0.1000 | $0.4000 | Active |
| openai | GPT-4o | $2.5000 | $10.0000 | Active |
| openai | GPT-4o Mini | $0.1500 | $0.6000 | Active |
| openai | GPT-4o Mini (2024-07-18) | $0.1500 | $0.6000 | Active |
| openai | GPT-4 Turbo | $10.0000 | $30.0000 | Active |
| openai | GPT-4 Turbo Preview | $10.0000 | $30.0000 | Active |
| openai | GPT-5 | $1.2500 | $10.0000 | Active |
| openai | GPT-5.2 (Chat Latest) | $1.7500 | $14.0000 | Active |
| openai | GPT-5 Mini | $0.2500 | $2.0000 | Active |
| openai | GPT-5 Nano | $0.0500 | $0.4000 | Active |
| openai | o4-mini | $1.1000 | $4.4000 | Active |
| openai | Text Embedding 3 Large | $0.1300 | $0.0000 | Active |
| openai | Text Embedding 3 Small | $0.0200 | $0.0000 | Active |
| openai | Text Embedding Ada 002 | $0.1000 | $0.0000 | Active |
| openai | Text Embedding Ada 002 (v2) | $0.1000 | $0.0000 | Active |
| openai_api | GPT-5.4 | $2.5000 | $15.0000 | Active |
| openai_api | GPT-5.4 mini | $0.7500 | $4.5000 | Active |
| openai_api | GPT-5.5 | $5.0000 | $30.0000 | Active |
| openai_api | GPT-Image-2 (Image) | $8.0000 | $30.0000 | Active |
| openai_api | GPT-Image-2 (Text) | $5.0000 | $0.0000 | Active |
| openai_api | GPT-Realtime-2 (Audio) | $32.0000 | $64.0000 | Active |
| openai_api | GPT-Realtime-2 (Image) | $5.0000 | $0.0000 | Active |
| openai_api | GPT-Realtime-2 (Text) | $4.0000 | $24.0000 | Active |
| vertex | Gemini 2.0 Flash | $0.1000 | $0.4000 | Active |
| vertex | Gemini 2.0 Flash | $0.1000 | $0.4000 | Active |
| vertex | Gemini 2.5 Flash | $0.3000 | $2.5000 | Active |
| vertex | Gemini 2.5 Pro | $1.2500 | $10.0000 | Active |
| vertex | Llama 3.1 405B Instruct | $5.0000 | $16.0000 | Active |
| vertex | Llama 4 Maverick 17B Instruct | $0.3500 | $1.1500 | Active |

---

Source: [coolhandlabs.com/inference-apis](https://coolhandlabs.com/inference-apis)
