Skip to content
Keln

Anthropic-compatible API

POST https://anthropic.keln.ai/v1/messages, the Anthropic Messages schema, streaming and non-streaming, for every catalog model. Built for tools that use the Anthropic API: Claude Code works with Keln through three environment variables (see below).

Same account, same key, same models, same prices: only the request shape differs.

curl https://anthropic.keln.ai/v1/messages \
  -H "x-api-key: $KELN_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshotai/kimi-k3",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Say hello from Keln."}]
  }'

Authentication

Send your normal Keln API key in the x-api-key header, the Anthropic convention. Keln accepts the anthropic-version header as clients send it.

Models

Use Keln model ids (moonshotai/kimi-k3, deepseek-ai/deepseek-v4-flash, …), the ids from /v1/models, not Anthropic model names. Every model on the Models & pricing page is available on this API.

What's supported

Feature Contract
messages, system, max_tokens standard Messages semantics
stream: true the full Anthropic event lifecycle: message_start → content_block_start → content_block_delta → content_block_stop → message_delta → message_stop
Thinking models the reasoning trace comes back as thinking content blocks, exactly where Anthropic clients expect it
tools, tool_choice (incl. forced {"type": "tool", "name": …}) Anthropic input_schema tool shape, tool_use content blocks out, tool_result blocks in, full agent loops work
usage input_tokens / output_tokens on every response. Billing is the same as on chat completions and Responses: the per-model rates on Models & pricing, with reasoning billed as output and repeated context at the cached rate
Everything else the same routing, validation, and zero-data-retention contracts as the rest of Keln

Using Claude Code

Point Claude Code at Keln with environment variables, no config file needed. For the desktop app, see Claude Desktop with Keln.

export ANTHROPIC_BASE_URL="https://anthropic.keln.ai"
export ANTHROPIC_API_KEY="sk-keln-…"          # your Keln API key
export ANTHROPIC_MODEL="moonshotai/kimi-k3"   # any catalog model with tool calling

Then run claude as usual.

Notes:

  • Model choice. Agent sessions need tool calling, so pick a model that supports it.
  • Long sessions. Keln bills repeated context at the per-model cached rate automatically. There is nothing to configure.
  • Background tasks. Point ANTHROPIC_SMALL_FAST_MODEL at a cheaper catalog model, for example deepseek-ai/deepseek-v4-flash, for Claude Code's background tasks.

Send Anthropic's server tool, { "type": "web_search_20250305", "name": "web_search" }, and Keln runs the search and answers in Anthropic's own shape: server_tool_use and web_search_tool_result blocks with the results, citations on the text, and usage.server_tool_use.web_search_requests. Claude Code's WebSearch uses this tool, so it works through Keln as it does against Anthropic. Send the result block back on the next turn and the model keeps its findings. Details and price on Web search.