Transparent pricing with no hidden fees. Pay as you go.
claude-sonnet-5claude-sonnet-5| Model | Spec | PoYo price | Official price | You save |
|---|---|---|---|---|
| claude-sonnet-5 | Input | $0.850/1M tokens 170 credits /1M tokens | $2.00/1M tokens Official | 57% |
Output | $4.28/1M tokens 855 credits /1M tokens | $10.00/1M tokens Official | 57% |
* Actual fees are based on the final output.
Complete guide to using Claude Sonnet 5 API
claude-sonnet-5. Anthropic describes Sonnet 5 as the best combination of speed and intelligence, with strong coding and agentic workflow performance.Official Anthropic materials position Sonnet 5 as a strict upgrade over Sonnet 4.6 for coding, agents, computer use, and cost-performance flexibility.
01
Anthropic says Claude Sonnet 5 is its most agentic Sonnet model yet. It is designed to plan, use tools, debug, drive browsers and terminals, and finish multi-step work where earlier Sonnet models could stop short.
02
The current Claude model overview lists Claude Sonnet 5 with a 1M token context window and up to 128K output tokens on the synchronous Messages API. Message Batches can support larger output with the documented beta header.
03
Claude Sonnet 5 uses adaptive thinking and the effort parameter instead of manual extended-thinking budgets. On the Claude API and Claude Code, Anthropic documents the default effort as high.
04
Anthropic highlights browser and computer-use performance as a key Sonnet 5 improvement. For production migration, note that Claude Sonnet 5 also uses a new tokenizer, so the same text may produce about 30% more tokens than Sonnet 4.6.
05
Claude Sonnet 5 is documented as the first Sonnet-tier model with real-time cybersecurity safeguards. Some prohibited or high-risk cybersecurity requests may return a successful response with stop_reason: "refusal".
Use Claude Sonnet 5 for planning, implementation, debugging, maintenance, multi-file refactors, code review, and repository-scale assistant workflows.
Build agents that select tools, recover from errors, check their own output, and keep working through complex multi-step tasks.
Automate browser-based research, procurement, customer onboarding, data entry, and operational workflows that need reliable action-taking.
Analyze financial data, synthesize internal and external sources, draft documents, edit spreadsheets, and support high-volume professional workflows.
Claude Sonnet 5 is a drop-in model ID upgrade from Sonnet 4.6, but Anthropic documents several behavior and migration notes around adaptive thinking, sampling parameters, and token counting.
| Feature | Claude Sonnet 5 | Claude Sonnet 4.6 |
|---|---|---|
| Model ID | claude-sonnet-5 | claude-sonnet-4-6 |
| Launch date | June 30, 2026 | Earlier Claude 4.6 generation |
| Positioning | Best combination of speed and intelligence, stronger agentic coding | Previous Sonnet model for coding and agent workflows |
| Context window | 1M tokens | 1M tokens |
| Max output | 128K tokens | 128K tokens |
| Thinking mode | Adaptive thinking with effort parameter | Adaptive thinking; manual extended thinking deprecated |
| PoYo pricing | Input 170 credits / 1M tokens (about $0.850), output 855 credits / 1M tokens (about $4.275) | Existing Claude 4.6 pricing varies by Sonnet and Opus tier |
Sources: Anthropic launch post and Claude Platform model documentation published June 30, 2026.
Create a PoYo API key
Get API Key
Set the model ID
Use claude-sonnet-5 as the model ID in your request.
Choose one of two endpoints
Use the OpenAI-compatible endpoint /v1/chat/completions, or use the Anthropic-native endpoint /v1/messages. Both follow the same Claude model ID.
Open API docs
View API docs
| Model | Input | Output |
|---|---|---|
| Claude Sonnet 5 | 170 credits / 1M tokens about $0.850 | 855 credits / 1M tokens about $4.275 |
High-tier top-ups include +10% bonus credits. Effective pricing is approximately 10% lower than the above rates.
claude-sonnet-5./v1/chat/completions for OpenAI-compatible chat requests or /v1/messages for Anthropic-native Messages API requests.