SOPs & process documentation
Turn how your team actually works into SOPs people can follow and agents can use.
Claude is Anthropic's model family. Its current Fable 5.1 and Opus, Sonnet and Haiku 5.5 models accept text and images and return text, with tool support and a 1M-token context window. Choose by measured task quality, latency and total cost rather than the family name alone.
Claude names both Anthropic’s model family and its assistant product. An app subscription and direct API usage have different entitlements and billing; cloud-provider deployments can add their own conditions.
API requests select a model and supported thinking settings. Fable 5.1 and Opus 5.5 keep thinking enabled; other current models allow different controls. Tools extend the model with retrieval or actions, executed by the application or provider.
The dated table lists direct API base token prices. Haiku’s lowest rate applies only through 100,000 prompt tokens. Cache writes, tool use and location-specific charges can change total cost. Anthropic also notes a newer tokenizer from Claude 4.7 onward can produce roughly 30% more tokens for the same text, depending on the material.
The published model options support comparisons across latency, cost and task complexity. Large context windows can accommodate substantial source material, though capacity does not guarantee reliable use of every detail. Remote MCP connectors can connect the assistant to other services, subject to plan and organization controls.
The core models output text; generating an image requires a separate tool. API limits are not promises of identical app limits. Benchmark the complete workflow, including retrieval, permissions and review. This page records documentation evidence and does not claim comparative hands-on testing.
Snapshot from official sources on Oct 18, 2026. Model lineups and prices change often; this page is re-verified every 30 days.
| Current lineup | Fable 5.1, Opus 5.5, Sonnet 5.5, Haiku 5.5 [1] |
| Vendor starting recommendation | Opus 5.5 for most workloads; not an IonBin benchmark [1] |
| Context / maximum output | 1M / 128K tokens; app and endpoint limits may differ [1] |
| Reliable knowledge cutoff | June 2026 for these four models [1] |
| Standard direct API USD per 1M input / output tokens | Fable $10/$50; Opus $4/$20; Sonnet $2/$10; Haiku $0.10/$0.50 for prompts up to 100K, $0.50/$2.50 above 100K [2] |
| Batch and caching | Batch token prices 50% lower; cache reads and writes have separate rates [2] |
| App subscription USD | Free; Pro $20 monthly or $200 upfront yearly (advertised rounded $17/month); Team standard $25/seat monthly or $20/seat/month annually, 2-150 members [3] |
| Remote MCP custom connectors | Free, Pro, Max, Team and Enterprise; Free limited to one custom connector; organization policies apply [4] |
Turn how your team actually works into SOPs people can follow and agents can use.
Competitor, market and search research with sources you can cite.
Pull numbers from the systems you already use into one place an agent can analyze and explain.
| API access | Yes | Official docs ↗ |
| Apps | Claude web, desktop and mobile; subscription/model availability varies | |
| Also offered via | Amazon Bedrock, Google Cloud, Microsoft Foundry, Claude Platform on AWS; check model and regional availability | |
| Tool in this entry | How agents connect |
|---|---|
| Claude | Agent platform MCPAPI/CLIFile import |
Levels come from each tool's recorded, sourced compatibility. How the levels work.
Practitioner views are restated in our words and labeled as views, not measured results. Product facts come from official sources dated above.
IonBin's wiki isn't user-edited. Corrections go to our Directory Curator, who checks them against primary sources before anything changes. Spot something wrong or out of date on “Claude (Anthropic)”? Email us with a link to a primary source.
Suggest an edit by email or write to contact@ionbin.com