AI Model Profile
Claude Sonnet 5
Claude Sonnet 5 is Anthropic's speed-and-intelligence balance in the Claude 5 line, with a 1M-token context window and 128K maximum output.
- Family
- Claude
- Release date
- Unknown
- Status
- Deprecated
- Context window
- 1M tokens
- Output limit
- 128K tokens
- API
- yes
- Open weights
- no
- Local/self-hosted
- no
- Pricing
- Pricing reviewed September 21, 2026. Claude API Standard: US$2 per million input tokens and US$10 per million output tokens. Anthropic made these rates permanent on August 10; the previously announced September 1 increase to US$3/US$15 was cancelled. These are API usage rates, separate from Claude subscription pricing.
- Evidence state
- Source-verified
Benchmark Caveat
Benchmarks and provider capability notes are directional, not universal rankings. Results can shift with prompts, tool use, latency targets, pricing tier, safety filters, context length, and the workload mix a real team runs.
See the linked official model, docs, model-card, or pricing source for provider-published capability notes.
Best for
Existing Claude Sonnet 5 integrations that are not ready to migrate yet. New work should start on Claude Sonnet 5.5, which has the same $2/$10 price.
Skip if
Skip for new work: Claude Sonnet 5.5 (September 28, 2026) has the same price and scores higher on every benchmark Anthropic published. Consider Haiku 4.5 if it meets the task at lower cost.
Strengths
Anthropic lists Sonnet 5 with a 1M-token context window, 128K max output, adaptive thinking, and fast comparative latency. On the Message Batches API it supports up to 300K output tokens using the output-300k-2026-03-24 beta header.
Weaknesses
Superseded by Claude Sonnet 5.5 on September 28, 2026; Anthropic now lists Sonnet 5 under legacy models. Reliable knowledge cutoff is January 2026. Extended thinking is not supported.
Agent suitability
Useful for agent workflows when the provider supports tool use, long context, structured outputs, or workflow-specific APIs.
Kingy AI take
Use this as a source-backed shortlist candidate, not a universal ranking. Re-check official provider docs and run a task-specific trial before production adoption.
Verification & Sources
- Evidence state
- Source-verified
- Source links
- 4
- Freshness
- Checked September 28, 2026
- Last verified
- September 28, 2026
- Last updated
- July 25, 2026
What this evidence state means
- Definition
- The stated claim was checked against a named primary or authoritative source. This does not mean Kingy tested the product.
- Required provenance
- At least one public, named primary or authoritative source that directly supports the claim.
- Owner
- Kingy editorial reviewer
- Freshness rule
- Recheck within 30 days and after a material product, price, access, or source change.
- Disputes and corrections
- Use “Suggest a correction” on the record. Kingy editorial reviews the cited evidence, records material corrections, and changes or removes the state when it is not supported.
Key source checks
Suggest a correction
Coding notes
Use official docs and live evals before selecting this model for production coding workflows.
Reasoning notes
Provider capability notes are useful but should be validated on representative prompts and tools.
Creative notes
Use a small creative test set before standardizing outputs for brand, media, or customer-facing work.
Research notes
Track release notes and model lifecycle notices because availability and aliases can change.
API pricing notes
Claude API pricing checked September 21, 2026; all amounts USD per million tokens. Batch: $1 input/$5 output. Standard prompt caching: $2.50 for 5-minute writes, $4 for 1-hour writes and $0.20 for cache hits/refreshes. Standard rates apply throughout the 1M-token context window. US-only inference adds 10% to all token categories; global routing uses base rates. Tool charges can add to token costs, and partner-operated cloud prices require a separate check. Priority Tier is unavailable for Sonnet 5. Anthropic says its newer tokenizer produces approximately 30% more tokens for the same text than Sonnet 4.6, depending on content; recount workloads before estimating savings. Source review only; Kingy did not run paid requests or verify an invoice.
License notes
Commercial/API terms apply unless the linked official source states otherwise.
Hardware requirements
Cloud/API model; local hardware requirements are not published as a self-hosted path.
Official Model Links
Model Intelligence Research Map
Use these internal paths to move from this model profile into provider pages, static comparison pages, related Kingy records, and the broader AI launch graph. These are research paths, not rankings.