Claude Sonnet 4.6
Anthropic's balanced mid-tier model from February 2026. Best price/performance for production workloads: 5x cheaper than Opus, near-flagship quality.
Claude Sonnet 4.6 is multimodal AI model from Anthropic, priced at €0.003 per 1M input tokens with a 200K tokens context window.
About this model
0.7
Pricing
API Integration
Use our OpenAI-compatible API to integrate Claude Sonnet 4.6 into your application.
npm install railwailimport railwail from "railwail";
const rw = railwail("YOUR_API_KEY");
// Simple — just pass a string
const reply = await rw.run("claude-sonnet-4-6", "Hello! What can you do?");
console.log(reply);
// With message history
const reply2 = await rw.run("claude-sonnet-4-6", [
{ role: "system", content: "You are a helpful assistant." },
{ role: "user", content: "Explain quantum computing simply." },
]);
console.log(reply2);
// Full response with usage info
const res = await rw.chat("claude-sonnet-4-6", [
{ role: "user", content: "Hello!" },
], { temperature: 0.7, max_tokens: 500 });
console.log(res.choices[0].message.content);
console.log(res.usage);Deep dive — Anthropic's Claude Sonnet 4.6
Anthropic was founded in 2021 by Dario and Daniela Amodei together with senior researchers from OpenAI. The company is a Public Benefit Corporation focused on AI safety. Key research milestones include Constitutional AI (2022), Sparse Autoencoders for interpretability, and the Claude model family launched in March 2023. Claude Sonnet has been Anthropic's flagship 'balanced' tier since the Claude 3 family, with major releases including Sonnet 3.5 (June 2024), Sonnet 3.7 with extended thinking (February 2025), Sonnet 4 (May 2025), Sonnet 4.5 (late 2025) and Sonnet 4.6 (February 17, 2026). Investors include Google, Amazon, Spark Capital and Lightspeed; total funding exceeds $20 billion with a 2026 valuation above $150 billion.
Visit Anthropic →Claude Sonnet 4.6 was released February 17, 2026 as the mid-tier workhorse of the Claude 4.x family. It is a decoder-only Transformer engineered to deliver near-Opus quality at one-fifth the cost. Pretraining used the same multi-trillion-token mixture as Opus 4.7 with a knowledge cutoff in early 2026. Post-training combined RLHF, Constitutional AI, RLAIF, and reinforcement learning against verifiable rewards on coding, math and tool-use trajectories. Sonnet 4.6 supports the full Opus feature set: extended thinking mode, native vision, computer use, parallel tool calling, and 200K context. The training emphasis was on efficiency: Sonnet 4.6 outperforms Opus 4 on most coding and writing benchmarks while running ~2x faster and at one-fifth the cost. Anthropic positions Sonnet 4.6 as the recommended default for production workloads.
- Parameters
- Undisclosed (estimated dense model in the 100B-range)
- Context
- 200K tokens
- Near-Opus quality on most coding, writing and analysis tasks at 5x lower cost
- Extended thinking mode with adjustable thinking budget
- 200K token context window with strong needle-in-haystack recall
- Multimodal input: text, images, PDFs, charts and diagrams
- Native computer use: screenshots, mouse and keyboard control
- Parallel tool calling and stable multi-turn agent loops
- Strong instruction following including XML tags, schemas and strict JSON
- Constitutional-AI alignment with low refusal rate on benign questions
- Multilingual fluency across 20+ languages
- ~2x faster latency than Opus 4.7 on equivalent tasks
- Best for: production agents, developer copilots, customer support, most enterprise API scenarios.
Pretrained on a curated multi-trillion-token mixture identical to the Opus 4.7 corpus, with heavy quality filtering, deduplication and copyright screening. Knowledge cutoff in early 2026. Post-training uses RLHF, Constitutional AI, RLAIF and RL against verifiable rewards.
License: Proprietary commercial license via Anthropic API, Amazon Bedrock and Google Vertex AI. Commercial use permitted under Anthropic's Usage Policy.
Known limitations
- Below Opus 4.7 on the hardest agentic and reasoning benchmarks
- No native audio or video input
- Knowledge cutoff in early 2026; needs tool use for fresh information
- Will refuse some legitimate red-team and security research prompts
- No fine-tuning available to external customers
Frequently asked questions
Related Models
View all MultimodalBLIP
Salesforce BLIP. Vision-language model for image captioning and visual question answering. Given an image it writes a short natural-language caption, or answers a question about the image when one is supplied. A widely used baseline for automatic captioning.
CLIP Interrogator
pharmapsychotic's CLIP Interrogator. Takes an image and produces a Stable-Diffusion-style text prompt by combining BLIP captioning with CLIP to rank likely subjects, artists, mediums and styles. Commonly used to reverse-engineer a prompt from an existing picture.
Claude 3.5 Sonnet (vision)
Anthropic Claude 3.5 Sonnet with image input. 200k context, strong on dense documents, tables, charts and handwriting. Reliable structured extraction from screenshots and scans.
Claude Opus 4.7
Anthropic's April 2026 flagship. 87.6% on SWE-bench Verified, 3x higher image resolution, output self-verification, vision + reasoning.
Start using Claude Sonnet 4.6 today
Get started with free credits. No credit card required. Access Claude Sonnet 4.6 and 100+ other models through a single API.