Open the app
Cost & economics

Providers & APIs

The external services Clawlas integrates — exchanges, LLMs, market & on-chain data, RPC, aggregators, orchestration and infrastructure — with roles, pricing, limits and official docs.

Clawlas is provider-independent: every external service is an adapter behind a stable internal interface. This is the working catalogue of those services — what each is for, what it costs, and where to verify the current terms.

Start free, upgrade only on measured evidence
No paid plan is enabled on day one. A provider is upgraded only when a measured strategy shows the missing data or lower latency produces enough additional net profit to cover the subscription and its operational complexity. Every paid call is logged to ai_usage_logs or external_api_usage_logs and bounded by usage_budgets.

Exchanges, backend & LLMs

ProviderRolePricing / limitsDocs
CCXT / CCXT ProCentral CEX/DEX integration + WebSocketsFree (WS merged into the package)docs.ccxt.com
Convex (self-hosted)Reactive app backend & operational stateNo per-request bill; VPS + storage onlydocs.convex.dev/self-hosting
Google GeminiCheap classification → mid reasoningFlash-Lite $0.10 → Pro $1.25 in / 1Mai.google.dev/gemini-api/docs/pricing
OpenAIStructured tasks → advanced analysisGPT-5 mini $0.25 → GPT-5.5 $5.00 in / 1Mdevelopers.openai.com/api/docs/pricing
Anthropic ClaudeFast tool use → deep strategy reviewHaiku 4.5 $1.00 → Sonnet 4.6 $3.00 in / 1Mdocs.anthropic.com/en/docs/about-claude/pricing
DeepSeekCost-efficient reasoning (open-weight, self-hostable)V3 $0.14 in · $0.28 out / 1Mapi-docs.deepseek.com/quick_start/pricing
Alibaba QwenCheap multilingual extraction → analysis (open-weight)Flash $0.19 → Max $1.25 in / 1Malibabacloud.com/help/en/model-studio/model-pricing
Moonshot (Kimi)Agentic tool use & long-context synthesis (open-weight)Kimi K2.5 $0.60 in · $3.00 out / 1Mplatform.moonshot.ai/docs/pricing

Prices are per 1M input tokens at the reference date and change frequently — recheck before committing. Output prices and cached-input discounts are on the cost-model page. The open-weight providers (DeepSeek, Qwen, Kimi) are dual-use: a cheap hosted API now, and self-hostable weights through the gateway below once volume justifies a GPU.

Model gateway & open-source serving

ProviderRolePricingDocs
LiteLLMUnified gateway, fallbacks, budgets (policy stays in Clawlas)Open sourcedocs.litellm.ai/docs/routing
OllamaLocal dev & lightweight quantized modelsOpen sourcedocs.ollama.com
llama.cppEfficient quantized inference (CPU/GPU)Open sourcegithub.com/ggml-org/llama.cpp
vLLMHigh-throughput GPU serving (future dedicated GPU)Open sourcedocs.vllm.ai

Market, on-chain & social data

ProviderRolePricing / limitsDocs
DEX ScreenerPool/pair discovery & liquidity~60 rpm profiles · ~300 rpm pairs/searchdocs.dexscreener.com/api/reference
CoinGecko / GeckoTerminalMetadata, reconciliation, on-chain poolsFree Demo API (quota) + MCPdocs.coingecko.com
BirdeyeFaster on-chain discovery, security, WSFree → Lite $39 → Starter $99 → Premium $199 → Business $499docs.birdeye.so/docs/pricing
X APIEarly social signal (curated accounts)Pay-per-use credits; per-endpoint pricingdocs.x.com/x-api/getting-started/pricing
SearXNG (self-hosted)Project research & fallback web searchNo licence feedocs.searxng.org

Discovery starts on the free sources (DEX Screener, CoinGecko Demo, public RPC). Birdeye and X are added only when their data measurably improves opportunity capture, each behind a budget with auto-stop.

On-chain execution & RPC

ProviderRolePricing / limitsDocs
JupiterSolana routing & executionFree APIdev.jup.ag
HeliusSolana RPC & dataFree tier → paid; recheckhelius.dev/pricing
0xEVM swap aggregation (executable tx)Per dashboard/API; log zeroExFeedocs.0x.org
1inchEVM swap aggregation (alternative)Per portal pricingportal.1inch.dev/pricing
AlchemyMulti-chain EVM RPCFree 30M CU/mo, 25 rps → pay-as-you-goalchemy.com/pricing

Aggregators (Jupiter, 0x, 1inch) are interchangeable behind the VenueAdapter interface; RPC providers run primary + fallback. Premium RPC is justified only by measured landing-rate or latency impact on net PnL.

Orchestration, infrastructure & ops

Provider / toolRolePricing / limitsDocs
LangGraphDurable agent orchestration & human-in-the-loopOpen sourcedocs.langchain.com/oss/javascript/langgraph/overview
ValkeyEvent streams, cache, locks, rate limitsOpen sourcevalkey.io
BullMQ / Dramatiq / CeleryJob queues, retries, schedulingOpen sourcedocs.bullmq.io
Hostinger VPS (KVM 4)Shared host (app, Convex, workers)$0 incremental (already owned)hostinger.com/vps-hosting
Docker / ComposeService isolation & deploymentFree for this usedocs.docker.com
GitHub ActionsCI/CDFree tier 2,000 min/mogithub.com/pricing
Cloudflare R2Off-site backups10 GB free, then $0.015/GB-mo, free egressdevelopers.cloudflare.com/r2/pricing
ResticEncrypted backups → R2Open sourcerestic.net
Uptime KumaEndpoint & worker monitoringOpen sourcegithub.com/louislam/uptime-kuma
ResendEmail alerts (Telegram is primary)Per planresend.com/pricing
URLs are references, not endpoints
The Docs column lists official documentation domains to verify current pricing, rate limits, supported chains and terms before integration. All figures here are planning estimates.