# Dasha Compute Dasha Compute is Mac inference on getdasha.com — not Dasha.AI voice. Mac Ask / Provide / OpenAI-compatible chat completions. A run factory with a public signed receipt chain, not an account ledger. ## Build on Dasha mint 53uxQtB9pcjWvCHguz3JTTndvuKqGxhrD37EetnCpump Buy via site Buy — https://www.getdasha.com/how-to-buy · https://jup.ag/tokens/53uxQtB9pcjWvCHguz3JTTndvuKqGxhrD37EetnCpump base_url https://lobby.getdasha.com/compute/api/v1 guest-keys POST /compute/api/guest-keys mcp https://www.getdasha.com/compute/mcp.json skill https://www.getdasha.com/compute/skill.md UI is yours; we expose mint + run factory. base https://lobby.getdasha.com/compute/api/v1 www https://www.getdasha.com/compute/api/v1 healthz https://lobby.getdasha.com/compute/api/healthz network https://lobby.getdasha.com/compute/api/v1/network auth Bearer API key no key needed for healthz + network + models; key needed for chat live 24h counters GET /compute/api/factory settled_24h — tokens/jobs/cents, no key needed models entries carry pricing.request (USD per chat, flat - no per-token metering) + measured tok/s when benchmarked guest key POST /compute/api/guest-keys — 24h chat+models, 3/hour/IP (scope: chat + models only; other endpoints 403 guest_key_scope; tools/function calling 400s) curl -sS -X POST https://lobby.getdasha.com/compute/api/guest-keys -H 'Content-Type: application/json' -d '{}' ## Agents base_url https://lobby.getdasha.com/compute/api/v1 OpenAI-compatible. OpenAI SDK, Aider, Goose, OpenHands (BYOK). Mint: POST /compute/api/guest-keys reasoning_effort low|medium|high (alias effort). Hosted applies it. Community may ignore — honesty on dasha. MCP catalog (static, not streamable): https://www.getdasha.com/compute/mcp.json Connect a tool via skill + kit. Not a video CMS. v1 chat/completions = community Macs. None advertise the model → fail-loud `no_mac_online` (poll /compute/api/network · join /compute#provide). Hosted Ask = browser POST /compute/api/chat (status.live Workers AI) — never a silent v1 swap. ## Which key / which base Compute: https://lobby.getdasha.com/compute/api/v1 · dsk_ or guest dgk_ (POST /compute/api/guest-keys) OCM: https://www.getdasha.com/compute/ocm/v1 · ocm_live_ Never swap keys. Compute X session is not an OCM session. First path: POST /compute/api/guest-keys. Or sign in at /compute#build for dsk_. ## First call Start with qwen3-4b - 27b-class picks can wait minutes for a Mac, and cold users hit that first. base https://lobby.getdasha.com/compute/api/v1 www https://www.getdasha.com/compute/api/v1 curl -sS https://lobby.getdasha.com/compute/api/healthz curl -sS https://lobby.getdasha.com/compute/api/v1/network curl -sS https://lobby.getdasha.com/compute/api/v1/models curl -sS https://lobby.getdasha.com/compute/api/v1/chat/completions \ -H "Authorization: Bearer $DASHA_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"gemma3-27b","messages":[{"role":"user","content":"hi"}]}' from openai import OpenAI OpenAI(base_url="https://lobby.getdasha.com/compute/api/v1", api_key=os.environ["DASHA_API_KEY"]) new OpenAI({ baseURL: "https://lobby.getdasha.com/compute/api/v1", apiKey: process.env.DASHA_API_KEY }) Community: a peer Mac runs the job. v1 chat/completions: community Macs. None advertise the model → no_mac_online (poll /compute/api/network · join /compute#provide). Hosted Ask: browser POST /compute/api/chat (status.live Workers AI). Not a silent v1 swap. Hosted Flash: bigger-than-Mac (Spark / Engram-class Flash when offered). Model id `deepseek-flash` (Hosted). Never Community. Same base_url. Watch x-dasha-route. Engram/SSD-stream local recipes stay Hosted/Provide-Max — not Air kit. Hosted Astra: GPT-6 when offered. Model id `gpt-6-astra` (Hosted). Never Community. Same base_url. Watch x-dasha-route · x-dasha-model. Async tools / mid-turn steering / computer use stay Hosted-class only. spend caps every key carries its own USD cap - $5/month default, $1-$1,000 or uncapped at creation, monthly or weekly reset; 402 key spend limit reached on exceed - https://www.getdasha.com/caps spend headers x-dasha-route · x-dasha-model · x-dasha-spend-usd when known (Community omits unknown USD) receipts include route community|hosted (same as x-dasha-route); turns only when counted — never invented Verify a receipt without trusting this site: GET /compute/api/chain (receipts) + /keys.json (signer key). Rebuild the signed body as {"job_id":...,"engine":...,"tokens":...,"cents":...,"at":...,"prev_hash":...} - exactly those keys in that order (job_id string|null, engine string, tokens/cents non-negative integers, at unix-ms integer|null, prev_hash = previous receipt hash or "GENESIS"). receipt.hash = sha256(JSON.stringify(body)) hex; receipt.sig = ed25519 over the UTF-8 bytes of that hex string, verified with the signer's spki_pem; signer = first 16 hex chars of sha256(spki_pem). Chain continuity: each prev_hash equals the previous hash. Find your own receipt by the request_id you sent on chat/completions (echoed as receipt.request_id) or by job_id from the completion response. Machine verdict: GET /compute/api/verify?hash= - the 64-hex chain hash, the job_ id, or your request_id; the rcp_ receipt id is not a lookup key. v1 model gpt-oss-20b is dasha-hosted and NOT LISTED on /compute/api/v1/models while it is not serving; a direct chat/completions call for it still fails loud hosted_offline (not no_mac_online). Community models keep no_mac_online. The browser Hosted Ask on /compute is a separate door. Heads log: GET /heads serves the last 24h of signed anchor heads (each covers a chain tip; prev_head_hash links head to head). The first head in the window usually chains to an older head outside the window: X-Dasha-Heads-Truncated: true marks that and Link rel="prev-archive" points at the full UTC day bucket. Page backward with GET /heads/archive/YYYY-MM-DD.json. Verdict tiers: ANCHORED = tip covered by a head under 1h old; heads mint on demand when /heads or /compute/api/verify is hit, so quiet windows honestly read SELF-CONSISTENT until the next hit. Checkpoint: GET /heads/checkpoint returns a signed note (dasha-checkpoint-v1: signer / ts / head_hash / chain_tip, newline-separated) over the current tip and freshest covering head; sig = ed25519 over the note text with the /keys.json signer key. Store one and compare against later /heads responses to detect a rewritten tail. Launch: Dasha Compute launches on Product Hunt September 18, 2026 - GET /launch (pre-launch page; notify signup POST /compute/api/launch-notify {email}, count at /compute/api/launch-notify/count). Network board: GET /compute/leaderboard - live public board (jobs/tokens/cents settled on the signed chain + measured tok/s by model, no key needed); raw data GET /compute/api/chain + /compute/api/network. Org enroll: POST /compute/api/org-enroll (login; mints a quota+expiry code) -> share the code -> POST /compute/api/providers/enroll {code,name,models} (no login) registers each Mac under the owner account; list/revoke GET /compute/api/org-enroll + DELETE /compute/api/org-enroll/. ## Provide speed Community Macs publish measured tok/s via network capacity (measured_providers). Never invent. Join a Mac at /compute#provide — kit soft-doctor and enroll-code live there. Kit uses OLLAMA_KEEP_ALIVE (launch agent / service — a shell export is not enough). Smaller is faster: qwen3-4b · qwen3-8b · gemma3-12b · gemma3-27b. Send a recipe — MLX / Ollama / llama.cpp Apple Silicon. We pin winners. Hosted-only when offered: Flash-class · DGX Spark · Qwen 3.8 Flash-Next · Astra. Never a Community Mac. compute https://www.getdasha.com/compute proof https://www.getdasha.com/compute/proof - live proof page; machine twin GET /compute/proof.json Use a Mac https://www.getdasha.com/compute#ask Join a Mac https://www.getdasha.com/compute#provide agent.json https://www.getdasha.com/.well-known/agent.json skill https://www.getdasha.com/compute/skill.md skills https://www.getdasha.com/compute/skills/dasha-compute/SKILL.md mcp https://www.getdasha.com/compute/mcp.json site https://www.getdasha.com/llms.txt full https://www.getdasha.com/llms-full.txt