Claude Sonnet 5 API
LLMClaude Sonnet 5 is the balanced Claude coding route for daily agent work, with 1M context, vision, and structured tool use below the Opus 5 rate.
- Input · USD / 1M tokens$0.56 USDOfficial price
$2 USD - Output · USD / 1M tokens$2.8 USDOfficial price
$10 USD - Savings72%
- Context1M
- Last verified2026-09-10
- View tool pricing and billing rules
What are we making today?
Bring an idea, a question, or a first draft.
01
What this model is for
Claude Sonnet 5 is the balanced Claude coding route for daily agent work, with 1M context, vision, and structured tool use below the Opus 5 rate.
Claude Sonnet 5 is positioned as the daily-work member of the current Claude family: the same listed 1M context, visual input, and structured tool-use categories as Opus 5, but at a lower input and output token rate. That makes it a practical default for coding sessions that repeatedly read, edit, test, and review code.
Use the claude-sonnet-5 model ID through OmniaKey's supported API surface without changing the surrounding account or balance when you later compare Opus or Haiku. Client support still depends on how each tool exposes custom endpoints and model selection.
Best-fit coding workloads
Daily implementation
Build features, fix scoped bugs, and iterate on tests without starting at the Opus rate.
Repository maintenance
Review pull requests, update dependencies, and make coordinated edits across familiar code.
Tool-driven coding loops
Run search, edit, and test tools through clients that support structured tool calls.
02
Technical specification
Catalog facts and integration details verified for this route.
- Model ID
- claude-sonnet-5
- Context
- 1M
- Inputs and tools
- Vision · Tool use
- API endpoint
- /v1/chat/completions
- Cache hit / 1M
- $0.056 USD
- Coding clients
- Claude Code · Cursor · Cline · Aider
Limits to plan around
- Sonnet 5 is not automatically the right choice for every difficult task. Ambiguous architecture or high-cost decisions may justify moving to Opus 5.
- The listed 1M context window does not remove client limits or retrieval quality problems; send the evidence needed for the task instead of unfiltered files.
- Tool access is controlled by the client and your permissions. Model support does not make destructive commands or unreviewed writes safe.
03
Compare nearby models
Compare workload fit and current listed token rates before choosing a route.
| Model | Best for | Context | Input | Output |
|---|---|---|---|---|
| Claude Sonnet 5This page claude-sonnet-5 | Daily coding, tests, reviews, and sustained agent iteration with a lower rate than Opus 5. | 1M | $0.56 USD Official price $2 USD | $2.8 USD Official price $10 USD |
| Claude Opus 5 claude-opus-5 | Harder cross-system analysis and high-cost-of-error work where deeper effort can justify more spend. | 1M | $1.4 USD Official price $5 USD | $7 USD Official price $25 USD |
| Claude Haiku 4.5 claude-haiku-4-5 | Narrow, frequent support tasks when 200K context is enough and the lowest Claude rate leads. | 200K | $0.28 USD Official price $1 USD | $1.4 USD Official price $5 USD |
04
SDK quickstarts
Use one base URL and model ID from cURL, Python, or TypeScript.
curl https://api.omniakey.com/v1/chat/completions \
-H "Authorization: Bearer $OMNIAKEY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-sonnet-5",
"messages": [
{"role": "user", "content": "Review this pull request"}
],
"stream": true
}'05
Estimate token cost
Enter expected input and output tokens to compare current listed rates.
- OmniaKey estimate
- $0.112
- Official-rate estimate
- $0.40
- Estimated savings
- $0.288
Estimate covers input and output tokens only. Cache usage, retries, tools, and client-side token accounting can change the final charge.
06
Related coding guides
Deeper selection, setup, and troubleshooting guidance for this model family.
Opus 5.5 vs Sonnet 5
Choose a model by task difficulty and total cost.
Read guideClaude Sonnet 5 vs GPT-5.6 Terra for Coding
Start with Sonnet 5 for Claude-native, tool-heavy repository work; start with Terra for Codex, Responses, and the current OmniaKey rate.
Read guideClaude Opus 5 vs Sonnet 5
Use Sonnet 5 for routine repository work and move to Opus 5 when ambiguity, architectural scope, or the cost of a wrong answer outweighs the higher token rate.
Read guideClaude Code Pricing
Choose a subscription for a recurring allowance and hosted features, or API billing when you need metered usage, explicit model costs, and project-level spend control.
Read guide07
Sources and verification
Model facts and links were checked on 2026-09-10. Provider documentation remains the authority for upstream behavior.
Frequently asked questions
How much does Claude Sonnet 5 cost on OmniaKey?
OmniaKey charges $0.56 USD per 1M input tokens and $2.8 USD per 1M output tokens, in USD. Official prices are $2 USD and $10 USD; you save 72%.
What is the context window for Claude Sonnet 5?
The listed context window is 1M. Actual usable limits can also depend on the client and upstream request format.
Is Claude Sonnet 5 a good default for Claude Code?
It is the practical starting point in this catalog for daily Claude Code work because it combines 1M context and tool use with a lower listed rate than Opus 5. Keep task-specific evaluations: difficult architecture work may still benefit from Opus, while narrow repetitive jobs may fit Haiku.
When should I move from Sonnet 5 to Opus 5?
Escalate when the task remains stuck after good context and tools, spans unfamiliar architectural boundaries, or has a high cost of an incorrect answer. Switching models should be a task decision, not an automatic retry rule.
Does Claude Sonnet 5 support streaming and tool calls through OmniaKey?
The catalog lists structured tool use, and the OpenAI-compatible examples on this page show streaming and a tool definition. Verify your specific client because SDK versions and custom-endpoint support can change the exact request shape.