--- name: inferspeed description: Use InferSpeed (pay-per-token model API, OpenAI- and Anthropic-compatible) as the model backend for an agent or coding tool. Covers base URLs, auth, model and price discovery, a connection test, balance checks, topping up through your human, errors and retries. version: 3 updated: 2026-10-15 --- # InferSpeed skill Version 3, 2026-10-15. Source: https://inferspeed.ai/skill.md. Site index: https://inferspeed.ai/llms.txt. InferSpeed is a pay-per-token model API with OpenAI- and Anthropic-compatible HTTP endpoints, billed from a prepaid balance. Models on sale and live prices: https://inferspeed.ai/model-plaza (JSON: https://inferspeed.ai/api/v1/public/pricing). ## Safety rules for the agent - The key belongs to your human. Never print it, log it, paste it into chat, or put it in a command line argument. Read it from the environment variable `INFERSPEED_API_KEY`. - If `INFERSPEED_API_KEY` is not set, ask your human to create a key at https://inferspeed.ai/keys and export it. Do not ask them to paste the key to you. - Ask your human before writing or changing any tool config file (for example `~/.claude/settings.json`, `~/.codex/config.toml`, `opencode.json`). Show them the file and the change first. Never write the key into a file that is committed or shared. ## Settings | Setting | Value | | ----------------------------- | ------------------------------------------------------------------- | | OpenAI-compatible base URL | `https://api.inferspeed.ai/v1` | | Anthropic-compatible base URL | `https://api.inferspeed.ai` (clients add `/v1/messages`) | | Auth header | `Authorization: Bearer $INFERSPEED_API_KEY` (`x-api-key` also works) | | Model IDs | Any public model; list: `GET https://inferspeed.ai/api/v1/public/pricing` | | Models per key | Every live model; `GET https://api.inferspeed.ai/v1/models` | Use only the two base URLs above; there is no other API version or host (no `/v2`, no `/v3`). Endpoints: `POST /v1/chat/completions` (OpenAI Chat Completions), `POST /v1/responses` (OpenAI Responses, Codex CLI), `POST /v1/messages` (Anthropic Messages, Claude Code), `GET /v1/models`. One API key calls every live model (`glm-5.3`, `kimi-k3`, `MiniMax-M3`, ...): name the model in the request, and it is billed at that model's price. `glm-5.3-flash` is served on `POST /v1/chat/completions` only. Examples use `glm-5.3`; put any ID from `GET /v1/models` in its place. Reasoning models (such as `glm-5.3` and `kimi-k3`) think before answering; the reasoning counts as output tokens. Do not set `max_tokens` very low or the answer can come back empty. Limits and context details: https://inferspeed.ai/developers.md ## Discover models and prices - Models this key can call (needs the key): `GET https://api.inferspeed.ai/v1/models` returns an OpenAI-style list; use the `id` values. - Prices (public, no key): `GET https://inferspeed.ai/api/v1/public/pricing`. The body is `{"code": 0, "data": {...}}`; `data.models[]` has `id`, `name`, `protocols` (when verified), `price` and `list_price` with `input`, `output`, `cache_read`, `cache_write` in USD per 1M tokens (`data.unit` is `per_1m_tokens`). Fields that are not priced are left out. ## Test the connection This prints the HTTP status and the model IDs, never the key: ``` curl -sS https://api.inferspeed.ai/v1/models \ -H "Authorization: Bearer $INFERSPEED_API_KEY" \ -w '\nHTTP %{http_code}\n' ``` 200 means the key works. 401 means the key is wrong or disabled; 403 means it is blocked (see errors below). ## Configure a coding tool Exact config blocks for Codex CLI, Claude Code, OpenCode, OpenClaw and other OpenAI-compatible tools: https://inferspeed.ai/developers.md. The Claude Code and Codex CLI configs were verified against production on 2026-10-14 with Claude Code 2.1.296 and Codex CLI 0.162.1. Or, with your human's approval, run the installer. It reads the key from `INFERSPEED_API_KEY`, prints the one file it will change with a diff (secrets hidden), backs the file up, writes it, then tests the connection. Read it first: https://inferspeed.ai/setup.sh ``` curl -fsSL https://inferspeed.ai/setup.sh | sh -s -- claude --dry-run # show only, write nothing curl -fsSL https://inferspeed.ai/setup.sh | sh -s -- claude # or codex, opencode, openclaw curl -fsSL https://inferspeed.ai/setup.sh | sh -s -- claude --model kimi-k3 # pick the model ``` Without `--model` the installer uses the first model the key can call (`GET /v1/models`). For `openclaw` it only prints the settings to add by hand. ## Check balance and usage `GET https://api.inferspeed.ai/v1/usage` with the same `Authorization` header. Fields to read: - `remaining` and `unit` (`"USD"`): what this key can still spend. For a key with its own spend cap, `quota.limit`, `quota.used` and `quota.remaining`; otherwise `balance` is the account's prepaid balance. - `usage.today` and `usage.total` for this key: `requests`, `input_tokens`, `output_tokens`, `cache_read_tokens`, `cache_creation_tokens`, `total_tokens`, and `actual_cost` (USD charged). - Optional query: `days=1..90` adds `daily_usage`; `start_date` / `end_date` (`YYYY-MM-DD`) set the range of `model_stats`. ## Top up when the balance is low When the balance is low or a request fails with 403 `INSUFFICIENT_BALANCE`, call `POST https://inferspeed.ai/api/v1/billing/topup` and give the URL to your user. You never see card details; your human pays on a Stripe page (card, Apple Pay, Google Pay). ``` curl -sS https://inferspeed.ai/api/v1/billing/topup \ -H "Authorization: Bearer $INFERSPEED_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: " \ -d '{"amount_usd": 10}' ``` The body is `{"code": 0, "data": {...}}`. Read from `data`: - `payment_url`: the payment page. Send it to your human, or show `qr_code_png` (a `data:image/png` QR of the same URL). `message_for_user` is a ready-to-send sentence. - `id`, `status` (`pending`), `amount_usd`, `credit_usd` (what lands in the balance, bonus included), `expires_at` (the link closes then; create a new one after that). - `status_url`: poll it with the same header every 5-10 seconds. `GET https://inferspeed.ai/api/v1/billing/topup/{id}` returns `status`: `pending` (not paid yet), `paid` (being credited), `completed` (credited; `balance_usd` is the new balance), or `expired`, `cancelled`, `failed` (make a new top-up). When it is `completed`, retry the request that failed. `GET https://inferspeed.ai/api/v1/billing/balance` returns `balance_usd`. Both billing endpoints work at zero balance. Rules: ask your human how much to add if they have not said; never create more than one open top-up at a time; amounts outside the allowed range fail with 400 and a reason. A person can also top up at https://inferspeed.ai/purchase. ## When a request fails Branch on the status code and the error code (`code`, or `error.code` / `error.type`), not on the message text. - 400: the request is invalid, or (`model_not_available`) no live model answers to the model name: pick one from `available_models`. The same body fails again. Agent default names (`claude-*`, `gpt-*`, `codex-*`, `o*`, `gemini-*`, `grok-*`) never get this: they are routed to a live model, named in the response's `model` field and billed at its price (`X-Model-Strict: 1` turns that off). - 401: the key is missing, wrong or disabled. Stop and ask your human. - 403 `INSUFFICIENT_BALANCE`: the balance is used up. Retrying will not help. Create a top-up (`POST https://inferspeed.ai/api/v1/billing/topup`, see above), give the `payment_url` to your human, wait for `completed`, then retry. The error body also has `topup_url` (the console page) and `topup_api`. Other 403s (expired key, IP not allowed): stop and ask. - 403 `API_KEY_QUOTA_EXHAUSTED` (`error.code` `insufficient_quota`): the spend cap on this key is reached. Stop and ask your human to raise it. Retrying will not help. - 403 `permission_denied` with `error.type` `billing_error`: the balance ran out while the request waited. Same as `INSUFFICIENT_BALANCE`, but the body has no `topup_url`. - 429 `USAGE_LIMIT_EXCEEDED`, or any 429 with an `x-should-retry: false` header: a spend cap on this key (5-hour, daily or 7-day) or an allowance is used up until its window resets (`Retry-After`, when set, is the seconds until then). Retrying soon will not help; stop and ask your human. - Any other 429: rate limited or at capacity. Wait `Retry-After` seconds, then retry with backoff. - 524, or a non-streaming request cut off after about 100 seconds: the response took too long to arrive in one piece. Retry once with `"stream": true` (or a lower `max_tokens`); the same non-streaming request will hit the same limit. Use `"stream": true` for long outputs. - 503 and other 5xx: temporary. Retry with backoff; https://inferspeed.ai/status shows live checks. Full error table: https://inferspeed.ai/developers.md ## More - Agent setup: https://inferspeed.ai/agents.md - API page: https://inferspeed.ai/developers.md - Site index: https://inferspeed.ai/llms.txt - Installer: https://inferspeed.ai/setup.sh - Prices (JSON): https://inferspeed.ai/api/v1/public/pricing