ClaudeStore/Docs
⚠ These docs are a work in progress. Some content may be inaccurate or temporarily AI-generated.

Models

All Claude models available via API — Opus 4.6 (1M context), Opus 4.6, Sonnet 4.6, Haiku 4.5. Stable IDs, short aliases, pricing per token, context windows.

ClaudeStore supports the full Claude lineup via api2.claudestore.store: Claude Opus 4.6 (flagship, 200K standard context, 1M token beta context via anthropic-beta: context-1m-2025), Claude Opus 4.6, Claude Sonnet 4.6, and Claude Haiku 4.5. Short aliases opus, sonnet, haiku always resolve to the latest version of each tier. Pinned IDs (claude-opus-4.6, claude-sonnet-4.6, claude-haiku-4.5) are recommended for production. Billing uses of Anthropic-equivalent token usage.

Recommended Model IDs

Use the stable model IDs listed below in your API requests. These IDs are consistent across both Anthropic and OpenAI-compatible endpoints.

ModelModel IDMax InputMax OutputThinkingVision
Claude Opus 4.6claude-opus-4.6200K (1M beta)32KYesYes
Claude Opus 4.6claude-opus-4.6200K32KYesYes
Claude Sonnet 4.6claude-sonnet-4.6200K16KYesYes
Claude Haiku 4.5claude-haiku-4.5200K8KNoYes

Legacy model IDs (e.g. claude-sonnet-4.5, claude-opus-4.5, claude-sonnet-4) still resolve for backward compatibility but are not recommended for new integrations.

Short Aliases

For quick experimentation you can use short aliases instead of pinned IDs. Aliases always resolve to the latest version of each tier — convenient for chat clients, risky for production.

AliasResolves toRecommended for
opusclaude-opus-4.6Quick CLI calls, sandboxes
sonnetclaude-sonnet-4.6Quick CLI calls, sandboxes
haikuclaude-haiku-4.5Quick CLI calls, sandboxes
For production deployments use pinned IDs. Aliases will silently upgrade to the next major version (e.g. opusclaude-opus-5.0 when released), which can change behaviour, output length, and pricing without warning.

Long Context (1M tokens)

Claude Opus 4.6 supports a 1 million token context window in beta. Enable it by sending the anthropic-beta header on each request:

Enabling 1M context on Opus 4.6bash
curl https://api2.claudestore.store/v1/messages \
 -H "x-api-key: YOUR_API_KEY" \
 -H "anthropic-version: 2023-06-01" \
 -H "anthropic-beta: context-1m-2025" \
 -H "content-type: application/json" \
 -d '{
 "model": "claude-opus-4.6",
 "max_tokens": 4096,
 "messages": [{"role": "user", "content": "."}]
 }'
1M context is billed at the same per-token rate as standard context — the cap is just larger. Useful for whole-codebase analysis, long-form research, and very large RAG payloads.

Direct Anthropic-equivalent Rates

Claude Code API uses direct Anthropic-equivalent billing, with .

ModelInput / 1MCache write / 1MCache read / 1MOutput / 1M
Claude Opus 4.6$15.00$18.75$1.50$75.00
Claude Opus 4.6$15.00$18.75$1.50$75.00
Claude Sonnet 4.6$3.00$3.75$0.30$15.00
Claude Haiku 4.5$0.80$1.00$0.08$4.00

Opus 4.6 pricing matches Opus 4.6 at launch and is subject to change. 1M-context requests use the same rate as 200K-context requests.

Choosing a Model

  • Opus 4.6 — flagship reasoning, whole-codebase tasks (1M context), long-form research
  • Opus 4.6 — heaviest reasoning at 200K, complex refactors
  • Sonnet 4.6 — best value for daily coding, general tasks
  • Haiku 4.5 — fastest and cheapest, ideal for autocomplete and classification

See Key Controls to restrict which models a specific API key can use.

Listing Models via API

You can retrieve the list of available models programmatically:

GET https://api2.claudestore.store/v1/models

For detailed model information including pricing rates:

GET https://api2.claudestore.store/v1/models/info

Ready to start?

Get API access to all Claude models in under 2 minutes.

View Plans