Claude Sonnet
Anthropic’s production default—speed and intelligence at workable cost.
Anthropic’s Claude Sonnet 5 tier — best combination of speed and intelligence for most production agents and coding, at lower cost than Opus.
Why Claude Sonnet matters
Sonnet is the Claude most teams actually ship: strong enough for agents and IDE coding, fast enough for interactive UX, and cheaper than Opus. When people say “use Claude in production,” they usually mean Sonnet.
Vision · Tool calling · Thinking · MCP · Coding
Last reviewed: 21 August 2026
When to choose Claude Sonnet
Decision guidance for architects—not a feature list.
Best for
- Production chat and support agents
- IDE coding assistants
- RAG answer generation
- Structured extraction pipelines
Avoid if
- You need peak Claude capability on the hardest tasks
- You require open weights or self-hosted inference only
Strengths
Qualitative snapshot for architects—not a public ranking.
- Quality / cost / latency★★★★★
- Tool use for agents★★★★★
- Coding assistants★★★★★
- Peak reasoning vs Opus★★★☆☆
- Open weights★☆☆☆☆
Ecosystem
Built by
- Anthropic
Sonnet is Anthropic’s production-default Claude tier.
Competes with
- GPT-5
Competes as the everyday production brain for agents and coding.
Alternative to
- Gemini 3.1 Pro
Alternative proprietary default when Google Cloud is not required.
Works with
Recommended for
- RAG
Strong answer generation quality at workable production cost.
Often paired with
- Claude Opus
Escalate to Opus when Sonnet is not enough on hardest tasks.
How Claude Sonnet evolved
Key moments in chronological order.
- API
Computer use GA + browser use on Sonnet 5
Sonnet 5 supports GA computer_toolset_20260801 and browser_toolset_20260801 on the Claude API for UI/browser automation agents.
- API
Sonnet 5 $2/$10 pricing made standard
Anthropic confirms Claude Sonnet 5 introductory API rates ($2 input / $10 output per 1M tokens) are now standard; the scheduled Sept 1, 2026 increase to $3/$15 will not occur.
- Model
Claude Sonnet 5
Sonnet 5 ships as the speed/intelligence balance for most production Claude traffic.
- API
Introductory pricing window
Aggressive intro rates push Sonnet as the default production Claude.
- Product
Long-context Sonnet
1M-token-class context lands on the production tier, not only Opus.
- Model
Claude 3.5 Sonnet era
Sonnet becomes the breakout Claude for coding and everyday agent work.
- Model
Claude 3 Sonnet launches
Defines the mid-tier Claude brand for balanced cost and capability.
Overview
Capabilities
- Vision: Yes
- Audio: No
- Tool calling: Yes
- Thinking: Yes
- MCP: Yes
- Coding: Yes
- Structured output: Yes
Technical specifications
- Provider
- Anthropic
- License
- Proprietary
- Context window
- 1M
- Parameters
- Undisclosed
- Release
- 2026-07
- Modalities
- Text, Image
- Vision
- Yes
- Audio
- No
- Tool calling
- Yes
- Thinking
- Yes
- MCP
- Yes
- Open weights
- No
- API
- Yes
- Pricing (input)
- ~$2 per 1M tokens
- Pricing (output)
- ~$10 per 1M tokens
Supported modalities
Text · Image
Context window
1M (1,000,000 tokens)
Pricing
Anthropic confirmed Sonnet 5 introductory pricing is now standard (no Sept 2026 increase). Verify live pricing page for future changes.
Availability
Claude API model ID: claude-sonnet-5. Supports GA computer_toolset_20260801 and browser_toolset_20260801 (2026-08-19).
Use cases
- Production chat and support agents
- IDE coding assistants
- RAG answer generation
- Structured extraction pipelines
- Computer/browser automation agents
Strengths
- Strong quality / cost / latency balance
- Reliable tool use for agents
- GA computer use + browser toolsets
- 1M-token context on current Sonnet 5
Limitations
- Not peak Claude capability (vs Opus 5 / Fable 5.1)
- Closed weights
Related guides
Related benchmarks
Related research
- Anthropic research & model cards
Evaluation
Related GitHub
Related tools
Related rankings
Related comparisons
Companies
Explore more models
- Claude FableAnthropicAnthropic’s Claude Fable 5.1 — the most capable widely released Claude for long-horizon agents, deep reasoning, and demanding coding workflows. Mythos 5.1 is the same underlying model with relaxed cyber/life-sciences safeguards for trusted-access programs.
- Claude OpusAnthropicAnthropic’s Claude Opus 5 tier for complex agentic coding, enterprise work, long-context analysis, and careful instruction following. Claude Fable 5.1 sits above Opus for peak widely released capability.
- Claude HaikuAnthropicAnthropic’s fast, cost-efficient Claude tier for high-volume chat, classification, extraction, and sub-agent steps where latency and price matter more than peak reasoning.
- Gemini 3.1 ProGoogleGoogle’s current Pro-class Gemini for hard reasoning and native multimodal work. Prefer API id gemini-3.1-pro-preview; Gemini 3.5 Pro remains partner-testing. Legacy gemini-2.5-pro is scheduled for shutdown Oct 16, 2026.
- GPT-5.6OpenAIOpenAI’s GPT-5.6 family (Sol flagship, Terra balanced, Luna cost-efficient) for complex reasoning, coding, multimodal understanding, and agentic tool use. The gpt-5.6 API alias routes to Sol.
- GPT-6 AstraOpenAIOpenAI’s GPT-6 Astra peak model (API id gpt-6-astra) for computer use, coding agents, professional artifacts, science, and cybersecurity-adjacent defender workflows. Staged launch 2026-09-03; GPT-5.6 Sol/Terra/Luna remain the volume and cost-routing family.