APIs & SDKs

Claude 3.5 Sonnet

✓

Mid-tier Claude model with 200K context for coding and agentic workflows

Claude 3.5 Sonnet (launched Aug 28, 2025) is Anthropic's flagship mid-tier model with a 200K context window, strong coding and vision performance, and pay-per-use pricing at $3 per 1M input tokens and $15 per 1M output tokens. It is available via Claude.ai, the Claude iOS app, the Anthropic API, Amazon Bedrock, and Google Vertex AI, supports tool use/function calling, and powers agentic workflows, RAG, and coding assistants.

Claude 4.5 Haiku

✓

Fast Claude 4.5 model with 200K context at $1/$5 per MTok

Claude 4.5 Haiku (released Oct 15, 2025) is Anthropic's fastest Claude 4.5 model with near-Sonnet 4 performance at one-third the cost. It supports a 200K token context window, extended thinking, context awareness, and full tool use (code execution, computer use, bash, text editor, web search). It is available on Claude.ai (web, iOS, Android), the Claude Developer Platform/API, Claude Code, Amazon Bedrock, Google Cloud Vertex AI, and Microsoft Foundry with $1/$5 per million input/output token pricing.

Anthropic Claude API

✓

Build with Claude Opus 4.5, Sonnet 4.5, and Haiku 4.5 via the Anthropic API

The Anthropic Claude API provides pay-per-use access to Claude’s latest models: Opus 4.5 ($5/$25 MTok), Sonnet 4.5 ($3/$15 MTok for ≤200K prompts; $6/$22.5 MTok for >200K prompts), and Haiku 4.5 ($1/$5 MTok). The API supports 200K-token contexts, tool use/function calling, prompt caching (write/read discounts), and batch processing (50% savings). Available through the Claude Developer Platform with official SDKs, plus partner access on Amazon Bedrock, Google Cloud Vertex AI, and Microsoft Foundry.

Claude Opus 4.5

✓

Hybrid reasoning model for coding, agents, and computer use with a 200K context window

Claude Opus 4.5 (released Nov 24, 2025) is Anthropic's frontier model for complex coding, agentic workflows, and computer-use tasks. It offers a 200K token context window, supports tool use/function calling, and is available in Claude Pro/Max/Team/Enterprise as well as the Claude API, Amazon Bedrock, Google Cloud Vertex AI, and Microsoft Foundry. Pricing starts at $5 per 1M input tokens and $25 per 1M output tokens, with prompt caching and batch options for additional savings.

DeepSeek Coder

✓

Open-source MoE coding model (V2) with 128K context

DeepSeek Coder V2 is an open Mixture-of-Experts coding model (16B Lite and 236B) with a 128K context window and support for 338 programming languages. Weights are published on Hugging Face for self-hosting; code is MIT-licensed and the model weights use the DeepSeek Model License. Hosted inference is available through the DeepSeek API using OpenAI-compatible endpoints.

Google Gemini API

✓

Access Gemini 3 Pro preview and 2.5 family via pay-as-you-go with tools, caching, and Live API

The Gemini API exposes multimodal Gemini 3 Pro preview, Gemini 2.5 Pro, 2.5 Flash, and 2.5 Flash-Lite with text, image, audio, and video support. Developers get OpenAI-compatible endpoints, tool use (Search, Maps, code execution, URL, File Search, computer-use), context caching, Batch API, and a Live streaming API. Free tier offers limited usage; paid tier is per-token with higher limits and content not used to improve models.

Gemini 3 Pro

✓

Google's multimodal reasoning model (preview)

Gemini 3 Pro is Google's preview multimodal reasoning model for the Gemini API. It supports 1M token inputs with up to 64K output tokens, handles text, images, PDFs, and video, and adds thinking levels, thought signatures, and grounded tool use for agentic coding and planning workflows.

OpenAI API

✓

API access to GPT-5.1, GPT-5, GPT-4o, images, audio, and tools

OpenAI’s API gives developers pay-per-use access to the latest GPT models (GPT-5.1, GPT-5, GPT-4o, GPT-4.1, GPT-4.1 mini/nano, o-series), plus images (GPT-Image-1), speech (gpt-audio, Whisper), embeddings, and moderation. It supports tool calling, structured outputs, Assistants/Responses/Chat Completions, Batch, Realtime, prompt caching, fine-tuning, and file/image/audio endpoints. Pricing is metered per model; for example, GPT-5.1 Standard is $1.25 per 1M input ($0.125 cached) and $10 per 1M output, or $0.625 / $5 via Batch (see pricing page for all models).

GPT-4o

✓

OpenAI flagship GPT with text + image inputs and 128K context

GPT-4o (“o” for omni) is OpenAI’s fast, high-intelligence GPT model for general tasks. It accepts text and image inputs and returns text outputs (including structured outputs) via the Chat Completions API. It supports cached prompts, batch processing, fine-tuning, and snapshots, with a 128K context window and up to 16,384 output tokens. Knowledge cutoff: Oct 1, 2023.

GPT-5

✓

OpenAI reasoning model with 400K context and text+image inputs

GPT-5 is OpenAI’s previous-generation reasoning model for coding and agentic tasks. It supports text and image inputs with up to 128K output tokens inside a 400K context window, runs across the Chat Completions, Responses, Realtime, and Assistants APIs, and supports tools like web search, file search, image generation, and code interpreter (no computer-use). OpenAI recommends GPT-5.1 for the newest capabilities, but GPT-5 remains available for production workloads.

Vercel AI SDK

✓

Open-source TypeScript toolkit for streaming LLM apps with providers, tools, and generative UI

Vercel AI SDK (v6 beta) is a free, open-source toolkit for building streaming AI apps across Next.js, React, Vue/Nuxt, SvelteKit, and Node/Edge runtimes. It provides a unified provider API, tool calling, structured outputs (`generateObject`), server actions/RSC hooks, and generative UI helpers like `streamUI`, with adapters for OpenAI, Anthropic, Google, Mistral, Ollama, and more.