Claude Sonnet
Anthropic’s production default—Sonnet 5.5 (claude-sonnet-5-5, 2026-09-28) at the same $2/$10 list price as Sonnet 5.
Anthropic’s Claude Sonnet 5.5 (API id claude-sonnet-5-5, released 2026-09-28) for well-scoped everyday coding, agents, and documents. List price matches Sonnet 5 at $2/$10 per 1M tokens. Opus 5.5 remains the high-stakes tier; Haiku 5.5 (2026-10-07) is the low-cost subagent and high-volume tier.
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: 29 September 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
DataAIHub qualitative scores from 1 to 5, for architects. Not official benchmark results or 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.
- Model
Anthropic releases claude-sonnet-5-5 as the current Sonnet. List price matches Sonnet 5 at $2 input / $10 output per 1M tokens (cache read $0.20, 5-minute cache write $2.50, 1-hour cache write $4). 1M context and 128K max output. Adaptive thinking is on by default; between_tools turns off up-front thinking. Forced tool use returns an error. Haiku 5.5 is not released yet.
- 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 input: No
- Tool calling: Yes
- Thinking: Yes
- MCP: Yes
- Coding: Yes
- Structured output: Yes
Technical specifications
- Provider
- Anthropic
- License
- Proprietary
- Context window
- 1M
- Parameters
- Undisclosed
- Architecture
- Transformer (proprietary)
- Release
- 2026-09
- Modalities
- Text, Image
- Vision
- Yes
- Audio input
- No
- Tool calling
- Yes
- Thinking
- Yes
- MCP
- Yes
- Open weights
- No
- API
- Yes
- Pricing (input)
- ~$2 per 1M tokens (claude-sonnet-5-5)
- Pricing (output)
- ~$10 per 1M tokens
Supported modalities
Text · Image
Context window
1M (1,000,000 tokens)
Pricing
Same list price as Sonnet 5. Cache read $0.10 (halved from $0.20 on 2026-10-07; Anthropic estimates ~20% lower cost on most agentic work) / 5-minute cache write $2.50 / 1-hour cache write $4 per 1M tokens. Anthropic says most tasks use fewer tokens than Sonnet 5. Verify platform.claude.com.
Availability
Claude API id claude-sonnet-5-5 (2026-09-28); also Amazon Bedrock (anthropic.claude-sonnet-5-5), Google Cloud, Microsoft Foundry, and Claude Platform on AWS. 1M context and 128K max output. Adaptive thinking is on by default; between_tools turns off up-front thinking. Forced tool use returns an error. On the Claude API and Google Cloud, computer_20251124 is not accepted (use computer_toolset_20260801). Default effort is high on the API and medium in Claude Code. Generally available in GitHub Copilot (Pro, Pro+, Max, Business, and Enterprise; gradual rollout, 2026-09-28). From Claude Code v2.1.284 the sonnet alias resolves to Sonnet 5.5 on the Claude API. Messages API version 2026-10-21, the default in new Anthropic SDK majors and ant CLI 2.0.0, returns 400 if a request sends temperature, top_p, or top_k. Keep anthropic-version 2023-06-01 when a call still needs those parameters. On Amazon Bedrock, 2026-10-21 is only for Claude 4.7 and later. Those new SDK and CLI releases are Apache-2.0; earlier releases stay MIT.
Use cases
- Production chat and support agents
- IDE coding assistants
- RAG answer generation
- Structured extraction pipelines
- Computer/browser automation agents
Strengths
- Current Sonnet API id (claude-sonnet-5-5) at the same $2/$10 list price as Sonnet 5
- 1M-token context and 128K max output
- Positioned for well-scoped everyday work that uses fewer tokens per task than Sonnet 5
Limitations
- Closed weights
- Not the Opus 5.5 / Fable 5.1 tier for open-ended judgment
- Forced tool use returns an error; turning up-front thinking off requires between_tools
Related guides
Related benchmarks
Related research
- Introducing Claude Sonnet 5.5
Original Paper
- Claude Sonnet 5.5 model overview
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 5.5 (API id claude-opus-5-5, released 2026-09-22) for complex agentic coding, enterprise work, long-context analysis, and careful instruction following. Anthropic says it matches Fable 5.1 on most work at a lower price. Fable 5.1 remains a separate higher list-price SKU. Sonnet 5.5 (claude-sonnet-5-5, 2026-09-28) is the current Sonnet at the same $2/$10 list price as Sonnet 5. Haiku 5.5 (claude-haiku-5-5, 2026-10-07) is the current Haiku.
- 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. Claude Haiku 5.5 (API id claude-haiku-5-5, released 2026-10-07) is the current Haiku: Anthropic’s fastest model at standard speed, the first Haiku with an adjustable effort setting, and around 75% cheaper to run than Haiku 4.5 on average. Sonnet 5.5 and Opus 5.5 remain better for complex agentic coding.
- Gemini 3.1 ProGoogleGoogle’s 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. This slug is not Gemini 4 Argon (gemini-4-argon, public 2026-10-13). On the Gemini API, gemini-2.5-pro has no announced shutdown date and is not deprecated; access is limited to projects that have already used it.
- Gemini 4 ArgonGoogleStable Gemini API id gemini-4-argon, released 13 October 2026. Google’s model page describes it as the flagship for complex software engineering, deep mathematical and scientific problems, autonomous multi-step agents, and long decode. Thinking can be set to low, medium, or high. The long-decode guide names medium as the default for most coding and agentic work. It documents function calling, structured outputs, code execution, search grounding, URL context, and file search. Computer use is in preview. The model page does not document native MCP support. Image generation, audio generation, and the Live API are not supported.
- 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-6.1 Sol (gpt-6.1-sol, 2026-09-29) is the current lower-cost Sol; GPT-6 Sol and Luna (2026-09-22) are earlier cost tiers. This entry remains GPT-5.6, which is still available.