0.625 USD credit/million total tokensapi.aabao.top "Grok官逆" ·
Official and inference-provider prices are cash; relay prices are site credit (USD credit or CNY credit), a different unit, compared separately. Relay prices are per million total tokens at 75% input and 25% output.
xAI · grok-4.20-multi-agent official price: input 1.25, output 2.5 USD per million tokens (xAI, observed 2026-10-24). Cheapest inference provider: OpenRouter, input 1.25, output 2.5 USD per million tokens. Cheapest relay: api.aabao.top, group "Grok official reverse-engineered [machine translation] (on site: Grok官逆)" 0.625 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-23). 15 sites have comparable prices; 26 sites list this model.Relay blended price uses 75% input and 25% output. Conditions: Context tier: PROMPT_LT_200K · long context pricing: a prompt reaching 200k tokens bills all tokens of the request at the higher rate · Context tier: OPENROUTER_DEFAULT_WHEN_NO_OVERRIDE · Additional web_search price 0.005 USD (per unit as declared by OpenRouter)
Price ranges per million tokens
Official cash prices · Lowest 1.5625 · median 2.3438 · highest 3.125 · 2 quotes USD / per million tokens
Inference provider cash prices · Lowest 1.5625 · median 1.5625 · highest 1.5625 · 1 quotes USD / per million tokens
Relay USD credit prices · Lowest 0.625 · median 1.0938 · highest 1.5625 · 2 quotes USD / per million tokens, site credit
Official price
Provider
Tariff
Input
Output
Cache read
Cache write
Unit
Observed
Conditions and source
xAI
Standard
1.25
2.5
0.2
—
USD / 1M tokens
Context tier: PROMPT_LT_200K · long context pricing: a prompt reaching 200k tokens bills all tokens of the request at the higher rateFull price conditions
{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": "PROMPT_LT_200K",
"processingMode": null,
"conditionNotes": [
"long context pricing: a prompt reaching 200k tokens bills all tokens of the request at the higher rate"
],
"effectiveFrom": null,
"effectiveUntil": null
}
Context tier: PROMPT_GE_200K · long context pricing: a prompt reaching 200k tokens bills all tokens of the request at the higher rateFull price conditions
{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": "PROMPT_GE_200K",
"processingMode": null,
"conditionNotes": [
"long context pricing: a prompt reaching 200k tokens bills all tokens of the request at the higher rate"
],
"effectiveFrom": null,
"effectiveUntil": null
}
Official prices are the vendor's cash prices. Inference providers also list cash prices and can be compared directly. Relays list prices in site credit; what you actually pay depends on each site's top-up rate, so they cannot be compared with official prices directly.
Inference providers
Provider
Tariff
Input
Output
Cache read
Cache write
Unit
Observed
Conditions and source
vs official
OpenRouter · Aggregator
Standard
1.25
2.5
0.2
—
USD / 1M tokens
Context tier: OPENROUTER_DEFAULT_WHEN_NO_OVERRIDE · Additional web_search price 0.005 USD (per unit as declared by OpenRouter)Full price conditions
Context tier: OPENROUTER_MIN_PROMPT_TOKENS_200000 · OpenRouter override for prompts from 200000 tokens (boundary inclusivity not stated) · Additional web_search price 0.005 USD (per unit as declared by OpenRouter)Full price conditions
{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.0000004",
"input": "0.0000025",
"output": "0.000005"
},
"conditions": [
"OpenRouter override for prompts from 200000 tokens (boundary inclusivity not stated)"
],
"contextTier": "OPENROUTER_MIN_PROMPT_TOKENS_200000",
"processingMode": null,
"conditionNotes": [
"Additional web_search price 0.005 USD (per unit as declared by OpenRouter)"
],
"effectiveFrom": null,
"effectiveUntil": null
}
Context tier: OPENROUTER_MIN_PROMPT_TOKENS_200000 · OpenRouter override for prompts from 200000 tokens (boundary inclusivity not stated) · Additional web_search price 0.005 USD (per unit as declared by OpenRouter)Full price conditions
{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.0000004",
"input": "0.0000025",
"output": "0.000005"
},
"conditions": [
"OpenRouter override for prompts from 200000 tokens (boundary inclusivity not stated)"
],
"contextTier": "OPENROUTER_MIN_PROMPT_TOKENS_200000",
"processingMode": null,
"conditionNotes": [
"Additional web_search price 0.005 USD (per unit as declared by OpenRouter)"
],
"effectiveFrom": null,
"effectiveUntil": null
}
These plans are marked as test, internal, disabled, gated by top-up or membership, or have a near-zero ratio. They may not be purchasable or stable, so they are listed separately and left out of the ranking and statistics.
All per-token prices: 93,968 prices from 854 sites (about 751 companies). 84,786 are ranked, from 838 sites (about 736 companies); 9,182 more are listed separately and not ranked. Prices collected up to 2026-10-24.
This model has 64 recorded prices; 39 can be compared directly (38 ranked, 1 listed separately). Not comparable yet: ratio looks unset 10, display unit not confirmed 4, billed per request or another unit 4, price not parsed yet 4, tiered by rules (see Tiered prices) 3
2 recent · 0 stale (older than 10 days, or not updated by this refresh) · 0 unverified timestamps. Minimum and median only count recent paid prices; older prices stay in the table. 0 zero-valued pairs are separately unverified, without proof of free eligibility. Timing does not verify payment, upstream identity or quality.
Prices are converted to site credits using each site’s published ratio. What you actually pay depends on its top-up rate. Input, output and cache prices in each row come from the same plan. Several sites run by the same company take one place in the ranking: its cheapest plan, with the other sites listed under it. We judge “same company” by identical prices, status pages or homepage code; this is not a legal finding. To see every site’s prices, choose “All plans” or filter by provider.
“Self-declared unofficial channel” means the plan name itself says “reverse-engineered” or similar. We have not verified their source or quality. Minimum and median only count regular plans.
Which API is cheapest for xAI · grok-4.20-multi-agent?
api.aabao.top, group "Grok官逆 (Grok official reverse-engineered)", 0.625 USD credit per million total tokens, observed 2026-10-23. 15 sites have comparable prices.
What is the official price for xAI · grok-4.20-multi-agent?
Input 1.25, output 2.5 USD per million tokens, checked 2026-10-24. Lowest inference provider: OpenRouter, input 1.25, output 2.5 USD per million tokens.
How do I use xAI · grok-4.20-multi-agent in Claude Code or Codex?
Install Grandet Skill, then say "Connect the cheapest xAI · grok-4.20-multi-agent API to Claude Code for me".Install Skill →