Opus 5.5 fast mode is $8/$40 per million; a Format run has no tier
Anthropic prices Opus 5.5 fast mode at twice standard. Sume's Format run body has a model field but no service-tier field, so you cannot request it there.
Agents
The Sume video agent from code: Agent Completions, scheduled runs, MCP tools and timeouts, programmatic tool calling, and guardrails for paid APIs.
Start with: What is a video agent? How Sume defines and runs one
Opus 5.5 hands cyber tasks to Opus 4.8: log the model id
Anthropic says Opus 5.5 re-routes most cybersecurity tasks to Opus 4.8. Keep the model id that served each Sume Format run in your logs to explain odd results.
Gemini managed agents background:true vs a Sume Format 202 receipt
Both return an id to poll instead of holding the connection. Compare the Gemini background flag with the Sume Format run receipt and its four URLs.
Grok 4.7 Fast is only in Cursor and Grok Build, at 2x the rate
xAI's pricing page says Grok 4.7 Fast is not on the public API. Where it runs, what it costs, and what to do if your Sume agent needs a Grok model.
Claude Opus 5.5 programmatic tool calling: when video jobs fit it
Opus 5.5 supports programmatic tool calling. Fan-out video jobs fit it, sequential renders do not. Which Sume calls batch well and which stay one by one.
Agent run webhook: degraded outcome, and canceled runs send nothing
A Sume agent.run webhook has outcome ok, degraded or error, and canceled or skipped runs deliver nothing. Which branch your handler needs to cover.
Agent Completions webhook payload null: fetch result_url (1 MiB)
A Sume agent.run webhook over 1 MiB arrives with payload null and an error carrying result_url, while status still says OK. Verify, then fetch the receipt.
Cap a voiceover batch at $1: tts_create dry_run and max_spend_usd
Preview what a Sume TTS call will cost before it runs, and cap the spend. How dry_run and max_spend_usd work on tts_create, with a 20-line cost example.
Edit a photo from an AI agent: generate_image with input_references
The hosted MCP generate_image tool takes the same body as POST /v1/images, including input_references. Call tools_schema first, pass an idempotency_key.
TikTok trend search then import over Sume MCP: $0.10 + $0.15
Searching TikTok trend metadata costs about $0.10 and importing one video about $0.15 over Sume MCP, so a find-and-mirror step is about $0.25 before generation.
Who authorizes agent spend on Sume: mcp:write, key and balance
On Sume, spend is authorized by the token: mcp:read hides paid tools, mcp:write allows them, and an API key sees all. There is no mcp:paid scope.
x402 upto vs exact: how each maps to a Sume spend cap
Apify's x402 upto charges actual usage up to an allowance; exact takes a fixed $1.00 deposit and refunds the rest. Sume's analogue is a per-call spend cap.
AgentCore payments GA vs Sume's API key and credit balance
AWS made AgentCore payments GA on Aug 18, 2026 with x402 upto and MPP. Sume uses an API key or OAuth with a credit balance and per-call spend caps instead.
Hermes Agent cron job that starts a Sume Format run
A Hermes cron job begins with no memory of last week. Write the prompt, idempotency key, spend cap and SILENT or CRON_FAILURE reply so a Sume run starts once.
Hermes cron no-agent script: poll a Sume bulk queue quietly
A Hermes cron script that prints nothing while a Sume bulk queue runs and one line when every item is terminal. Includes the Python, 404 and 429 cases.
What is an AI video agent? One that talks, or one that makes
An AI video agent can mean a live on-camera persona like a Tavus PAL, or an agent that makes videos for you. Which one Sume is, and how to call it from code.
Sume Agent Completions request: required cap, model sume-agent
The minimum valid POST /v1/agent/completions body: instruction or messages, no assistant turns, model sume-agent, required generation_spend_cap_usd.
Sume Agent Completions or a Format run: which should code call?
Pick between POST /v1/agent/completions and a Format run: open-ended instruction versus a reusable recipe, fresh thread each time, schema output, and cost cap.
Sume Action spend cap: 1 dollar default, per-run cap only lowers
A Sume Action carries a default spend cap of 1 dollar. A per-run cap can lower it but not raise it, so a heavy video job needs the cap changed on the Action.
Sume Action overlap: on_active_run skip gives 200, reject gives 409
What happens when a Sume Action run starts while the last one is active: skip gives 200 with status skipped, reject gives 409 action_run_in_progress.
Scheduled Sume runs: cron or API trigger is fixed at create
A Sume Action is either cron or api triggered, chosen at creation. How to author one, why you cannot create it over the public API, and how to run the api kind.
Claude Sonnet 4.5 retires Nov 30: what to move to on Sume
Anthropic deprecated claude-sonnet-4-5-20250929 on Sep 30, retiring it Nov 30, 2026 in favor of Sonnet 5.5. Sume's catalog has no Sonnet 4.5 row.
Claude thinking blocks are model-bound: one model per thread
Sonnet 5.5 and Fable 5.1 thinking blocks only work for the model (and account) that made them. Why an agent thread should keep one model, and how to log it.
Scheduled run missing from /v1/jobs? Read /v1/action-runs instead
A Sume scheduled agent run is not a generation job. It never appears in /v1/jobs and has its own statuses, so poll /v1/action-runs/{run_id}.
Fire a cron schedule on demand: api_trigger_enabled, cron kept
A Sume cron schedule can also accept API runs. Turn on api_trigger_enabled and your service can start it now without touching the cadence.
Scheduled run body: unknown fields are silently dropped, not a 400
A typo in a Sume scheduled run body is dropped without an error, unlike a Format run. Check names, then read the receipt to see what applied.
Can I create a Sume scheduled agent by API? Read and run, not create
The Sume API can list, read, run and monitor scheduled agents, but not create, edit or delete them. Authoring is the dashboard or the Agent chat.
Claude Code mcp_tool hook skipped on SessionStart: Sume balance check
Claude Code's mcp_tool hooks are skipped on SessionStart and Setup because no MCP client exists yet. Run a Sume balance check at PreToolUse instead.
Claude Code RETRY_WATCHDOG gives up after 3 timeouts: Sume jobs
Unattended Claude Code sessions using CLAUDE_CODE_RETRY_WATCHDOG now stop after three timeouts. Persist Sume job ids so a restart resumes, not resubmits.
Codex config.toml enabled_tools and required for Sume's read tools
Codex's MCP config can allowlist tools with enabled_tools and fail startup with required. Give a task only Sume's read and wait tools and a longer timeout.
Scheduled AI runs in Q4 2026: ceiling by cadence at $1 a run
At the $1.00 default cap, weekly runs top out at $13 for Q4, daily at $90 and hourly at $2,160. How the schedule cap works and what null changes.
VS Code Copilot automations on a schedule: Sume jobs and idempotency
VS Code automations can run agent tasks hourly, daily, weekly or on demand. Make each Sume create idempotent so a rerun resumes a job instead of paying twice.
What can a $5 generation spend cap make? Clips, stills, captions
A $5 cap on an Agent Completion covers 16 five-second Wan 3.0 clips at 480p, or 50 nano-banana-2 stills, but not one Seedance 2.5 clip at 720p and 15 seconds.
Agent retry budget for paid video calls: stop on 402
An agent that calls a paid video API needs three counters: submits, estimated dollars and consecutive 402s. The stop rule, and how Sume's spend cap backs it up.
Claude Code 2.1.288 background session fix: Sume jobs keep running
Claude Code 2.1.288 fixed background sessions ending on plugin reload. A Sume job outlives the session; how to find it and avoid paying twice.
Claude Code plugin agents honor disallowedTools: block Sume paid tools
Since 2.1.288 plugin-defined agents run with their own prompt, tools, disallowedTools and effort. A reviewer agent that can read Sume jobs but never create one.
Codex 0.160 Guardian review reads prior instructions: Sume args
Codex CLI 0.160 adds opt-in Guardian review that can fetch earlier user instructions. Write Sume calls so a reviewer can approve them from the arguments alone.
Kiro Crew log MCP server vs Sume job events: which record to trust
Kiro Crew 0.7.0 added an MCP server for durable session tracking. For generated media, Sume's job records are the better source of truth. Where each fits.
Kiro Web Workflows run in the background: pairing with Sume runs
Kiro Web Workflows plan multi-step agent work in the background. Sume Agent Completions are also async. How to hand one step to the other without blocking.
Zed ask_user forms: confirm a Sume estimate before paying
Zed's ask_user tool lets agents ask with forms. Use it as a spend checkpoint with Sume's dry_run preview, so people approve a number, not a tool name.
Agent Completions: input is data, messages are the prompt
On POST /v1/agent/completions, messages or instruction become the prompt; input is written to a file as data the Agent never treats as instructions.
Sume output_schema name: slashes allowed, rewritten upstream
Names like sume/action-image-v1 are accepted (A-Z a-z 0-9 . _ / -, up to 64 chars) and echoed back unchanged. Only the structuring call sees a rewritten name.
Sume schedule: cron or API call is fixed when you create it
A Scheduled agent's trigger_type cannot change after creation. Cron schedules can also accept API runs; API-only ones never gain a cadence. How to choose.
Sume Scheduled has no MCP tool or CLI command: your options
Schedules are not exposed over Sume MCP or the CLI, and the API cannot create them. Author in the dashboard or ask the Agent in chat; run and monitor by API.
Weekly content plan from an Agent Completion: output_schema in Python
Ask the Sume agent for a week of post ideas as typed JSON. Python uses urllib, a required generation_spend_cap_usd, output_schema and a polling loop.
Claude Code /loop expires in 7 days: where a Sume job should live
A /loop task stops after 7 days and only fires while Claude Code is open. For a recurring render, keep the schedule in Sume Scheduled and let /loop watch.
Cursor Automations webhook: start a Sume agent run with a spend cap
A Cursor Automation can call Sume Agent Completions from a webhook-triggered run. Send generation_spend_cap_usd and an Idempotency-Key on every call.
HydraFusion Cascade and Critique: keep Sume paid calls from repeating
HydraFusion can draft, critique and revise a task. Put an idempotency_key on every Sume paid call so a revised pass cannot bill the same render twice.