BroadRouter

Claude Opus 5 vs Claude Sonnet 5 API pricing

Updated

Claude Opus 5: USD 5 input, USD 25 output per 1M tokens (Anthropic and 3 others). Claude Sonnet 5: USD 2 input, USD 10 output per 1M tokens (Anthropic and 2 others). At 3 input tokens per output token, Claude Opus 5 costs 2.5× as much as Claude Sonnet 5 (USD 10 vs USD 4 per 1M).

Claude Opus 5 and Claude Sonnet 5 are neighbouring tiers of one Anthropic generation (Opus and Sonnet, by name), so this page shows what the step up costs. Price only: every number is computed from prices read from each provider's own pricing page (linked per cell, newest check 2026-11-14), with no claim about quality, speed or accuracy.

How do Claude Opus 5 and Claude Sonnet 5 differ on price?

Claude Opus 5 and Claude Sonnet 5 prices side by side

USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.

Claude Opus 5 and Claude Sonnet 5 API prices compared
PriceClaude Opus 5Claude Sonnet 5
Model pageClaude Opus 5
Anthropic · 5 providers
Claude Sonnet 5
Anthropic · 5 providers
Cheapest standard price, blended 3:1USD 10
USD 5 in / USD 25 out at Anthropic and 3 others
Anthropic page checked 2026-11-14
USD 4 lower
USD 2 in / USD 10 out at Anthropic and 2 others
Anthropic page checked 2026-11-14
Cheapest inputUSD 5
Anthropic source
USD 2 lower
Anthropic source
Cheapest cached inputUSD 0.50
Anthropic source
USD 0.20 lower
Anthropic source
Cheapest outputUSD 25
Anthropic source
USD 10 lower
Anthropic source
Maker's own APIUSD 5 / USD 25
Anthropic source
USD 2 / USD 10
Anthropic source
Median standard priceUSD 5 / USD 25
input / output, 5 prices
USD 2 / USD 10
input / output, 5 prices
Context window1,000,000 tokens, largest stated1,000,000 tokens, largest stated
Providers with a standard price55

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What do Claude Opus 5 and Claude Sonnet 5 cost for a real workload?

30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).

Monthly cost of three workloads on Claude Opus 5 and Claude Sonnet 5
WorkloadClaude Opus 5Claude Sonnet 5Difference
Support chatbot
2,000 requests a day, 1,500 input tokens (60% cached), 300 output
USD 657.00
Anthropic
USD 262.80
Anthropic
USD 394.20
Claude Sonnet 5 lower
RAG over documents
1,000 requests a day, 8,000 input tokens (30% cached), 500 output
USD 1,251
Anthropic
USD 500.40
Anthropic
USD 750.60
Claude Sonnet 5 lower
Coding agent (one developer)
1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning
USD 4,365
Anthropic
USD 1,746
Anthropic
USD 2,619
Claude Sonnet 5 lower

Claude Sonnet 5 is cheaper on all three workloads. The widest gap is on Support chatbot: the dearer model costs 2.5× as much as the cheaper one.

Does the cheaper model change with your input:output ratio?

Claude Sonnet 5 is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Claude Opus 5's, so the input:output ratio never changes the answer.

Price per 1M tokens of Claude Opus 5 and Claude Sonnet 5 at different input:output mixes
Input : output tokensClaude Opus 5Claude Sonnet 5
1 : 3 (long answers)USD 20
Anthropic
USD 8 lower
Anthropic
1 : 1USD 15
Anthropic
USD 6 lower
Anthropic
3 : 1 (the site’s blend)USD 10
Anthropic
USD 4 lower
Anthropic
10 : 1 (retrieval, long prompts)USD 6.818
Anthropic
USD 2.727 lower
Anthropic
30 : 1 (agents, big contexts)USD 5.645
Anthropic
USD 2.258 lower
Anthropic

USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.

What do Claude Opus 5 and Claude Sonnet 5 cost per character in other languages?

Not measured: the real cost by language dataset covers only tokenizers we could measure from published files, and Claude Opus 5 and Claude Sonnet 5 are not among them. Count tokens on your own text with the counters below.

Check it on your own traffic

More comparisons: Claude Opus 5.5 vs Claude Opus 5 · Claude Fable 5 vs Claude Opus 5 · Claude Sonnet 5.5 vs Claude Sonnet 5 · Claude Sonnet 5 vs Claude Sonnet 4.6 · every Claude Opus 5 comparison · every Claude Sonnet 5 comparison · all 662 price comparisons

Questions

Is Claude Opus 5 cheaper than Claude Sonnet 5?

No. On a blend of 3 input tokens to 1 output token, Claude Sonnet 5 costs USD 4 per 1M tokens and Claude Opus 5 USD 10, at each model's cheapest standard price. For input alone, Claude Sonnet 5 is cheaper (USD 2 against USD 5 per 1M); for output alone, Claude Sonnet 5 is (USD 10 against USD 25). This compares price only, not quality.

What do Claude Opus 5 and Claude Sonnet 5 cost per 1M tokens?

Claude Opus 5: from USD 5 input and USD 25 output at Anthropic and 3 others; Anthropic's own API charges USD 5 / USD 25; median of 5 standard prices USD 5 / USD 25. Claude Sonnet 5: from USD 2 input and USD 10 output at Anthropic and 2 others; Anthropic's own API charges USD 2 / USD 10; median of 5 standard prices USD 2 / USD 10. Each price is read from the provider's own pricing page; the source is linked in the table.

Which providers sell both Claude Opus 5 and Claude Sonnet 5?

5 providers have a standard price for both: Anthropic (USD 10 and USD 4 at 3:1), DigitalOcean (USD 10 and USD 4 at 3:1), Google Vertex AI (USD 10 and USD 4 at 3:1), Amazon Bedrock (USD 11 and USD 4.40 at 3:1), DeepInfra (USD 10 and USD 6 at 3:1). The first 3 tie for the lowest combined price. Buying each model from its own cheapest provider costs USD 10 and USD 4.

Which is cheaper for a coding agent or a chatbot, Claude Opus 5 or Claude Sonnet 5?

For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 4,365 a month on Claude Opus 5 (Anthropic) against USD 1,746 on Claude Sonnet 5 (Anthropic), a difference of USD 2,619. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 657.00 a month on Claude Opus 5 (Anthropic) against USD 262.80 on Claude Sonnet 5 (Anthropic), a difference of USD 394.20. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.

At what input:output ratio does the cheaper of Claude Opus 5 and Claude Sonnet 5 change?

Claude Sonnet 5 is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Claude Opus 5's, so the input:output ratio never changes the answer.

Do Claude Opus 5 and Claude Sonnet 5 have cached input pricing?

Claude Opus 5 from USD 0.50 per 1M cached input tokens (Anthropic; 4 of 5 standard prices list a discount). Claude Sonnet 5 from USD 0.20 per 1M cached input tokens (Anthropic; 4 of 5 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.

Which has the larger context window, Claude Opus 5 or Claude Sonnet 5?

Both go up to 1,000,000 tokens on the providers that state it.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity