Claude Sonnet 5 pricing, context window, and cost calculator
An Anthropic model with tracked introductory pricing and a future effective pricing record.
Verified fields
Quick facts
claude-sonnet-5Supported capabilities
- Streaming
- Function calling
- Structured outputs
- Prompt caching
- Batch API
- Reasoning
Only capabilities explicitly tracked from provider documentation are shown.
Source-tracked rates
Verified pricing profiles
Amounts are USD per 1M tokens unless the column states an hourly storage unit.
| Profile | Input / 1M | Cached input / 1M | Cache write / 1M | Output / 1M | Notes |
|---|---|---|---|---|---|
| standardDefault | $2.00 USD | $0.20 USD | $2.50 USD (5m) / $4.00 USD (1h) | $10.00 USD | Used for default estimates. |
Temporary pricing: Current tracked pricing is effective through 2026-08-31.
Future pricing: A separate verified record becomes effective 2026-09-01.
Workload estimate
Claude Sonnet 5 cost calculator
Change the workload assumptions. The calculator uses the same shared pricing resolver as StackLens Compare.
Estimated monthly total$70.00
- Monthly input cost
- $20.00
- Monthly output cost
- $50.00
- Per 1,000 requests
- $7.00
- Active profile
- standard
Estimate excludes untracked provider-specific charges.
Explicit assumptions
Common workload examples
1M input tokens
$2.00 under the standard profile, excluding output and other charges.
1M output tokens
$10.00 under the standard profile, excluding input and other charges.
10,000 monthly requests
At 1,000 input and 500 output tokens per request: $70.00 under standard.
50% cached input
The same default workload with 50% cached input is estimated at $61.00. Cache savings apply only to the tracked cached-input rate.
Research layer
Experience and rollout notes
Official facts are separated from user reports. Community reports are useful signals, not controlled benchmarks.
Official rollout details
Anthropic documents a 1M-token context window and 128K maximum output for Sonnet 5. Introductory API pricing is scheduled through August 31, 2026, with separately published rates after that date.
What this does not prove: Verify the effective pricing date before using the introductory rate in a budget.
Speed and coding fit
Fast responses are a recurring early theme, and some developers report useful results on larger codebases. Views are mixed on whether the improvement over Sonnet 4.6 is substantial.
What this does not prove: The reports cover different interfaces, tasks, and prompt setups, so they do not establish a comparative performance result.
Instruction following and pushback
Several users report more pushback or refusals than expected in some writing and coding sessions, while others describe normal instruction following.
What this does not prove: This is a conflicting early signal. Test representative prompts before changing a production workflow.
No controlled StackLens benchmark yet
StackLens has not run a controlled Sonnet 5 benchmark. The notes above separate official documentation from independent user reports.
Research reviewed 2026-07-13. Reports may change as Claude Sonnet 5 reaches more workflows.
Tracked relationships
Related models
StackLens relationship map based on model families and published decision comparisons. Find a workload match → Open relationship map → Open price map →
Featured comparisons
- Claude Sonnet 5 vs GPT-5.6 Terra cost
- Claude Sonnet 5 vs GPT-5.6 Sol cost
- Claude Sonnet 5 vs Gemini 3.6 Flash cost
- Claude Sonnet 5 vs Gemini 3.1 Pro Preview cost
- Claude Sonnet 5 vs DeepSeek V4 Flash non-thinking cost
- Claude Sonnet 5 vs Claude Sonnet 4.6 cost
Continue your research
Verification
Sources and methodology
Pricing and limits are source-tracked and may change. Verify current values with the provider before making production purchasing decisions.
Calculator profile rule: standard is the verified default. Display as temporary introductory pricing through August 31, 2026.