BroadRouter

Claude Opus 4.8 API pricing

Updated

Among the 5 providers we checked (prices read 2026-11-14), 4 tie for the lowest blended standard price for Claude Opus 4.8; Anthropic charges USD 5 per 1M input tokens and USD 25 per 1M output tokens. The median across 5 standard prices is USD 5 / USD 25. That is Anthropic's own API. Each price is read from the provider's own pricing page.

Anthropic · slug claude-opus-4.8 · up to 1,000,000 tokens of context · 5 providers with a standard price. Every price is read from the provider's own pricing page and linked in its row, checked 2026-11-14. No aggregator feed. Download all prices (every provider and model, with sources, CSV or JSON). How it compares with the market: the LLM API price index. Archived list prices since 2026-06-01 (6 archived price points, 0 list-price changes): LLM API price history.

What does Anthropic charge for Claude Opus 4.8?

Input
USD 5
Cached input
USD 0.50
Output
USD 25
Blended 3:1
USD 10

USD per 1M tokens on Anthropic, model Claude Opus 4.8, standard tier. Source, checked 2026-11-14.

Other Anthropic tiers: batch USD 2.50 / USD 12.50 · fast USD 10 / USD 50.

Is a host cheaper than Anthropic? They tie. DeepInfra and Anthropic's own API both work out at USD 10 per 1M tokens on the 3:1 blend.

Claude Opus 4.8 price per provider

USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 10% above the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.

Claude Opus 4.8 API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1Anthropic tied cheapest maker
Claude Opus 4.8
Notes and source quote
“| Claude Opus 4.8 | $5 / MTok | $6.25 / MTok | $10 / MTok | $0.50 / MTok | $25 / MTok |”
USD 5USD 0.50USD 25USD 101,000,000not statedAnthropic page
checked 2026-11-14
re-checked 2026-11-16
2DeepInfra tied cheapest
anthropic/claude-opus-4-8
Notes and source quote
“$5.00 in $25.00 out / 1M tokens”
USD 5not publishedUSD 25USD 101,000,000not statedDeepInfra page
checked 2026-11-14
re-checked 2026-11-16
3DigitalOcean tied cheapest
Notes and source quote
“Claude Opus 4.8 — Processing modePrompt lengthInputOutputCache write (5m)Cache write (1h)Cache read: Standard All prompts$5.00$25.00$6.25$10.00$0.50”
USD 5USD 0.50USD 25USD 10not statednot statedDigitalOcean page
checked 2026-11-14
re-checked 2026-11-16
4Google Vertex AI tied cheapest
claude-opus-4.8
Notes and source quote

Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately.

“Claude Opus 4.8 Input $5.00 … Output $25.00 … Cache Hit $0.50”
USD 5USD 0.50USD 25USD 10not statednot statedGoogle Vertex AI page
checked 2026-11-14
re-checked 2026-11-16
5Amazon Bedrock
Notes and source quote

Geo / in-region (US) on-demand price for us-east-1 from the "Geo and In-region Cross-region Inference" table. Global cross-region inference is cheaper: input $5.00, output $25.00 per 1M tokens. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1).

“Claude Opus 4.8 $5.50 $27.50 N/A N/A $6.875 $11.00 $0.55”
USD 5.50USD 0.55USD 27.50USD 11not statednot statedAmazon Bedrock page
checked 2026-11-14
re-checked 2026-11-16
—Anthropic maker batch
Claude Opus 4.8
Notes and source quote

Message Batches API.

“| Claude Opus 4.8 | $2.50 / MTok | $12.50 / MTok |”
USD 2.50not publishedUSD 12.50USD 51,000,000not statedAnthropic page
checked 2026-11-14
re-checked 2026-11-16
—Google Vertex AI batch
claude-opus-4.8
Notes and source quote

Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately.

“Claude Opus 4.8 Batch Input $2.50 … Batch Output $12.50 … Batch Cache Hit $0.25”
USD 2.50USD 0.25USD 12.50USD 5not statednot statedGoogle Vertex AI page
checked 2026-11-14
re-checked 2026-11-16
—Anthropic maker fast
Claude Opus 4.8
Notes and source quote

Fast mode. Prompt caching multipliers apply on top; not available with the Batch API. Anthropic lists fast mode as deprecated for Claude Opus 4.8.

“| Claude Opus 5 / Claude Opus 4.8 | $10 USD / MTok | $50 USD / MTok |”
USD 10not publishedUSD 50USD 201,000,000not statedAnthropic page
checked 2026-11-14
re-checked 2026-11-16
—DigitalOcean fast
Notes and source quote
“Claude Opus 4.8 — Processing modePrompt lengthInputOutputCache write (5m)Cache write (1h)Cache read: Fast Mode All prompts$10.00$50.00$12.50$20.00$1.00”
USD 10USD 1USD 50USD 20not statednot statedDigitalOcean page
checked 2026-11-14
re-checked 2026-11-16

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

What does Claude Opus 4.8 cost for a real workload?

Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.

  • Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
  • RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
  • Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
Monthly cost of three workloads on Claude Opus 4.8, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
Anthropic (maker)USD 657.00USD 1,251USD 4,365
DeepInfraUSD 900.00USD 1,575USD 11,250
DigitalOceanUSD 657.00USD 1,251USD 4,365
Google Vertex AIUSD 657.00USD 1,251USD 4,365
Amazon BedrockUSD 722.70USD 1,376USD 4,802

For the support chatbot, the cheapest price (Anthropic and 2 others, tied, USD 657.00 a month) saves USD 0 against the median (USD 657.00). For the coding agent the gap is USD 0 a month.

Which Claude Opus 4.8 provider is cheapest for your traffic?

Anthropic, DeepInfra, DigitalOcean and Google Vertex AI share the lowest input price (USD 5) and the lowest output price (USD 25), so they are the cheapest standard price at every mix of input and output tokens, before cache discounts.

Claude Opus 4.8: price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
Anthropic (maker)USD 10 cheapestUSD 8.313 cheapestUSD 6.963 cheapest
DeepInfra (no cache price)USD 10 cheapestUSD 10USD 10
DigitalOceanUSD 10 cheapestUSD 8.313 cheapestUSD 6.963 cheapest
Google Vertex AIUSD 10 cheapestUSD 8.313 cheapestUSD 6.963 cheapest
Amazon BedrockUSD 11USD 9.144USD 7.659

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.

4 of 5 providers publish a cached-input price below the input price: Anthropic (90% off), DigitalOcean (90% off), Google Vertex AI (90% off), Amazon Bedrock (90% off). DeepInfra publishes none, so cached tokens there bill at the input price.

Anthropic and DeepInfra state a context window of 1,000,000 tokens; DigitalOcean, Google Vertex AI and Amazon Bedrock do not state one.

Estimate your own bill

The Anthropic models whose cheapest standard price is closest to Claude Opus 4.8's (USD 10 blended):

Anthropic models priced closest to Claude Opus 4.8
ModelCheapest inputCheapest outputMax contextProviders
Claude Opus 4.5USD 5USD 25—4
Claude Opus 4.6USD 5USD 251,000,0004
Claude Opus 4.7USD 5USD 251,000,0005
Claude Opus 5USD 5USD 251,000,0005
Claude Opus 5.5USD 4USD 201,000,0006
Claude Fable 5.2USD 8USD 401,000,0004

Priced closest from other makers: GPT Chat Latest (OpenAI, USD 11.25) · GPT-5.5 (OpenAI, USD 11.25) · GPT-5.6 Sol (OpenAI, USD 8).

All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log

Questions

How much does the Claude Opus 4.8 API cost per token?

From USD 5 per 1M input tokens (USD 0.000005 per token) and USD 25 per 1M output tokens (USD 0.000025 per token) at the lowest standard prices we found. The median of 5 standard prices is USD 5 input and USD 25 output. Each price was read from the provider's own pricing page; the source is linked in its row.

Which provider is cheapest for Claude Opus 4.8?

Among the 5 providers we checked (prices read 2026-11-14), 4 are tied for the lowest price: Anthropic, DeepInfra, DigitalOcean and Google Vertex AI, each USD 10 per 1M on a blend of 3 input tokens to 1 output token. For input alone the lowest price is USD 5 (Anthropic and 3 others, tied); for output alone, USD 25 (Anthropic and 3 others, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.

Is Claude Opus 4.8 cheaper from a host than from Anthropic?

They tie. DeepInfra and Anthropic's own API both work out at USD 10 per 1M tokens on the 3:1 blend.

Does Claude Opus 4.8 have cached input pricing?

4 of 5 standard prices include one. The lowest is USD 0.50 per 1M at Anthropic; the median is USD 0.50. Providers without one bill cached input at the input price. What cached input means.

What is the Claude Opus 4.8 context window?

1,000,000 tokens on every provider that states it.

How much does a coding agent cost per month on Claude Opus 4.8?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 4,365 a month at Anthropic, USD 4,365 at the median price and USD 11,250 at DeepInfra. Try your own numbers.

Is there a batch, flex or priority price for Claude Opus 4.8?

Yes: batch from Anthropic at USD 2.50 / USD 12.50; fast from Anthropic at USD 10 / USD 50 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.

Is Claude Opus 4.8 free to use through an API?

No provider in our data lists a free price for Claude Opus 4.8 as of 2026-11-14. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity