StatusOperational Live status
LLMAPI discountUp to −25%
Models on LLMAPI12
From$2 / 1M blended
RegionsUS, EU
Best uptime (24h)99.98%
Verdict
Anthropic builds the Claude family of large language models, known for strong reasoning, coding ability, and context windows up to 200K tokens. Through LLMAPI you reach 6 Anthropic models on the same OpenAI-compatible endpoint as every other provider, so switching between them is a one-string change.
Good fit for
- Text Generation
- Code Generation
- Reasoning & Logic
- Mathematics
- Long Context
- Function Calling / Tool Use
Consider another provider for
- No image generation models in this catalog
- No vision models in this catalog
- No video generation models in this catalog
- No video understanding models in this catalog
Key facts
Where a provider does not document something we say so rather than guess. Everything LLMAPI records about Anthropic, in one table.
Overview | |
| Provider | Anthropic |
| Website | anthropic.com |
| Best for | Long-document analysis, coding assistants, and agents that need careful reasoning |
| Models on LLMAPI | 12 |
| Popular models | Claude Fable 5.1, Claude Opus 5, Claude Opus 5.5, Claude Fable 5, Claude Opus 4.8, Claude Opus 4.7 |
Access & routing | |
| API compatibility | OpenAI-compatible — /v1/chat/completions |
| Model ID prefix | anthropic/<model> |
| Regions | US, EU |
| Fallback | Configurable — on 429 or 5xx the router switches to any other model or provider on your list |
| Billing | One invoice across every provider, with per-key spend limits |
| Volume discount | Eligible |
Performance (median across listed models) | |
| Blended price / 1M | $10 |
| Uptime (24h) | 99.59% (median across listed models) |
Modality | |
| Tags | |
Capability | |
| Tags | |
Workflow | |
| Tags | |
Audience | |
| Tags | |
Other | |
| Tags | |
Privacy & data | |
| Inference location | US, with EU options on enterprise agreements |
| Data residency | Documented in the enterprise agreement |
| Default retention | 30 days for trust and safety, then deleted |
| Zero-data retention | On request Zero retention available on enterprise agreements |
| Training on API data | No API inputs and outputs are not used to train models |
| Human review | Flagged abuse cases only |
Compliance & lifecycle | |
| Certifications | SOC 2 Type II · ISO 27001 · GDPR DPA · HIPAA BAA available |
| Deprecation notice | Model deprecation dates published in advance |
| Operational status | Operational Live status |
Prices and context from the OpenRouter public catalogue; uptime and output speed from OpenRouter provider endpoints; quality scores from LiveBench. Refreshed nightly — last updated 2026-09-29. — means no figure is published for that model.
Best Anthropic models
A quick view of how Anthropic 's 6 models compare on intelligence, output speed and price — so you can pick the right one for your use case.
Most intelligent
#1Claude 3.5 Haiku41
#2Claude Opus 438
#3Claude Opus 4.131
#4Claude Sonnet 4.529
Intelligence index · 6 models
Fastest
#1Claude 3.5 Haiku457 t/s
#2Claude Opus 4454 t/s
#3Claude Sonnet 4.5422 t/s
#4Claude Haiku 4.5308 t/s
Output tokens / second · 6 models
Lowest price
#1Claude Opus 4.1$4.92
#2Claude Sonnet 4$5.45
#3Claude Opus 4$5.54
#4Claude 3.5 Haiku$7.72
Blended price per 1M tokens · 6 models
Compared with other hosts
How Anthropic sits against the rest of the catalog, using the same measurements shown on every provider page.
- Price. Median blended price of $6.63 per 1M tokens — 8% above the $6.13 median across all 50 providers in the catalog.
- Throughput. Median output speed of 365 tokens/s, 5% faster than the 348 tok/s catalog median.
- Catalog depth. 6 models listed, against a catalog average of 5 per provider.
- Integration. Identical to every other provider here — same endpoint, same SDK, same keys, so a switch costs one string change.
Median blended price per 1M tokens
lower is better| Anthropic | $6.63 | |
| Reka AI | $6.69 | |
| Thinking Machines | $6.75 | |
| DeepSeek | $6.77 | |
| Inception | $6.82 | |
| $6.31 |
Median output speed
higher is better| Anthropic | 365 tok/s | |
| Reka AI | 249 tok/s | |
| Thinking Machines | 119 tok/s | |
| DeepSeek | 236 tok/s | |
| Inception | 287 tok/s | |
| 239 tok/s |
Figures are medians across the models listed on each provider page and are refreshed with the catalog.
Models & pricing
Every Anthropic model reachable with your LLMAPI key. Click a column heading to sort.
| Model | API model name | Uptime 24h | Price / 1M | Context |
|---|---|---|---|---|
| Claude Fable 5.1 | claude-fable-5-1 | 99.16% | $ 20 | 1000 k |
| Claude Opus 5 | claude-opus-5 | 99.97% | $ 10 | 1000 k |
| Claude Opus 5.5 | claude-opus-5-5 | 99.97% | $ 8 | 1000 k |
| Claude Fable 5 | claude-fable-5 | 99.13% | $ 20 | 1000 k |
| Claude Opus 4.8 | claude-opus-4-8 | 99.98% | $ 10 | 1000 k |
| Claude Opus 4.7 | claude-opus-4-7 | 99.73% | $ 10 | 1000 k |
| Claude Sonnet 4.6 | claude-sonnet-4-6 | 99.40% | $ 6 | 1000 k |
| Claude Opus 4.6 | claude-opus-4-6 | 99.24% | $ 10 | 1000 k |
| Claude Opus 4.5 | claude-opus-4-5-20251101 | 99.79% | $ 10 | 200 k |
| Claude Haiku 4.5 | claude-haiku-4-5 | 99.69% | $ 2 | 200 k |
| Claude Sonnet 4.5 | claude-sonnet-4-5 | 99.48% | $ 6 | 200 k |
| Claude Sonnet 5 | claude-sonnet-5 | 99.30% | $ 4 | 1000 k |
Price is a blended per-1M-token figure; latency is time to first token and throughput is output tokens per second, measured on the LLMAPI edge.
Cost calculator
Pick a model, enter your traffic, and see the monthly bill at LLMAPI rates.
Estimates use the blended per-1M-token price shown in the table above. Word counts differ by language — Cyrillic and CJK text uses 2–3× more tokens per word.
Anthropic via LLMAPI
Same models, same features, one key. Prefix the model ID with anthropic/ and point your OpenAI client at our base URL.
# Python · OpenAI SDK from openai import OpenAI client = OpenAI( base_url="https://api.llmapi.ai/v1", api_key="LLMAPI_KEY", ) r = client.chat.completions.create( model="anthropic/claude-opus-4-1", messages=[{"role": "user", "content": "Hello"}], )
| Pricing | Eligible for LLMAPI volume discounts; billed on one invoice with every other provider. |
| Features | Full pass-through — tool calling, JSON schema, streaming, vision and reasoning behave exactly as on Anthropic’s own API. |
| Fallback | Configurable. On 429 or 5xx the router switches to any model or provider on your fallback list. |
| Regions | US, EU |
| Your data | LLMAPI stores request metadata only — model, token counts, latency and status. No prompt or completion content. |
Capabilities & use cases
Each tag below is its own catalog page listing every provider that shares it.
Developer resources
Where to go next.
Join thousands of developers building on one API key
Every provider in the catalog, one key, one invoice.
Questions
How do I call Anthropic models through LLMAPI?
Point any OpenAI-compatible client at https://api.llmapi.ai/v1 and use the model ID anthropic/claude-opus-4-1. No other change is needed.
Does Anthropic cost more through LLMAPI?
No. This provider is eligible for LLMAPI volume discounts, so heavy usage lands below list price.
Which regions are used?
US, EU
What happens if the provider returns an error?
On 429 or 5xx responses the router falls back to any other model or provider on your configured list, so requests keep succeeding.
How many Anthropic models are available?
6 at the moment, all listed in the models table above and updated as the provider ships new ones.
Related providers
Providers covering similar use cases.