agentutility$ man prompt-compress
/prompt-compress
PRICE / CALL
$0.005
USDC · base mainnet · scheme: exact
METHOD
POST
CLUSTER
wordmintCATEGORY
uncategorized
STATUS
● live
NAME
prompt-compress — prompt compressor / context shrinker / prompt distiller / cost-cutter for long system prompts
SYNOPSIS
POST https://x402.agentutility.ai/prompt-compress
Content-Type: application/json
X-PAYMENT: <signed-transferWithAuthorization>
{ ... }↳ first call →
402 Payment Required. Sign USDCtransferWithAuthorization, retry with theX-PAYMENT header.DESCRIPTION
Prompt compressor / context shrinker / prompt distiller / cost-cutter for long system prompts. Rewrites a long prompt down to a target ratio of its original length while preserving every instruction, constraint, and example's intent. Drops filler words, redundant repetition, and ceremonial politeness. Powered by Venice mistral-small-3-2-24b.
INPUT — request schema
| property | type | description | req? |
|---|---|---|---|
| prompt | string | Prompt to compress. Up to 60,000 chars. | required |
| target_ratio | number | Target length as a fraction of original. Range [0.1, 1.0]. Default 0.4. | optional |
OUTPUT — response shape
| field | type | description |
|---|---|---|
| original | string | Original long prompt text submitted by the caller, returned verbatim for diff and comparison. |
| compressed | string | Rewritten shorter prompt preserving every instruction, constraint, and example intent from the original. |
| original_chars | string | Character count of the original input prompt before compression. |
| compressed_chars | string | Character count of the compressed output prompt after rewriting. |
| target_ratio | string | Requested compression ratio (compressed length divided by original length) the caller asked for. |
| actual_ratio | string | Achieved compression ratio (compressed_chars divided by original_chars) after the rewrite. |
| model | string | Underlying LLM used to compress the prompt, currently Venice mistral-small-3-2-24b. |
| source | string | Provider behind the compression model, here Venice. |
EXAMPLES — two ways to call
EXAMPLE 1 · curl
curl -X POST https://x402.agentutility.ai/prompt-compress \
-H 'Content-Type: application/json' \
-d '{ }'first response =
402 Payment Required with payment requirements; sign + retry with X-PAYMENT.EXAMPLE 2 · mcp
# MCP packages on npm under # @agentutility/mcp-* (one per cluster) # # Catalog + install: # https://mcp.agentutility.ai # # Or call prompt-compress directly over HTTP — see above.
MCP server handles payment automatically — your coding agent just calls the tool by name.
METADATA
- tags
- wordmintprompt-engineeringprompt-optimizationtoken-reductioncontext-compressioncost-optimizationllm-toolingprompt-compress
- methods
- POST
- cluster
- wordmint
- price
- $0.005 USDC per call
ADJACENT — other endpoints in wordmint
| endpoint | description | price |
|---|---|---|
| card-resolve | Card resolver / graded card string normalizer / free-form card text to canonical card object. | $0.005 |
| detect-language | Language detector / language identification. | $0.005 |
| extract-entities | Named entity recognition (NER) / entity extractor. | $0.005 |
| pii-redact | PII redactor / mask emails phones SSNs IBANs credit cards IPs / GDPR safe text / privacy scrubber. | $0.005 |
| retrieval-rerank | Retrieval reranker / RAG reranker / document scoring / top-k filter / cross-encoder substitute. | $0.005 |
| text-classify | Text classifier. | $0.005 |
| tool-card-generate | Tool card generator / OpenAI function-calling spec / A2A tool-card / agent tool description. | $0.005 |
| translate | AI translator. | $0.005 |
SEE ALSO