Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.crazyrouter.com/llms.txt

Use this file to discover all available pages before exploring further.

​
Official Model Pricing Methods

This page explains upstream vendor pricing rules only. It does not describe Crazyrouter resale prices.
  • Upstream pricing: the vendor’s own input, output, cached input, tool call, search grounding, prompt caching, and similar billing rules
  • Crazyrouter pricing: Crazyrouter’s own sell price, multiplier, discount, channel variation, and settlement logic
This page reflects vendor documentation checked on 2026-04-27. Vendors can change prices, preview-model policies, long-context rules, search-tool fees, and caching behavior. Recheck the official source links before relying on any number in production.

​
Official Example Price Table

The examples below intentionally use the most common pricing tier that is easiest to map to budget planning:
  • Anthropic: standard API price, excluding Fast mode, US-only inference, and Batch discounts
  • OpenAI: Standard price, excluding Batch, Priority, and Regional Processing surcharges
  • Gemini: Standard price, usually the text/image/video default path, and for Gemini 3* models the <= 200K prompt tier
  • xAI: if the public static docs do not list a standalone price for the exact routed name, this page says so explicitly
  • Z.AI: the official Text Models price
  • MiniMax: the main table uses Pay as You Go; subscription-style pricing is listed separately under Token Plan
Unless otherwise noted, prices below are USD / 1M tokens.

​
Anthropic Example Prices

Crazyrouter NameOfficial ModelBase InputCache 5m / 1h / HitOutputNotes
claude-sonnet-4-6claude-sonnet-4-6$3$3.75 / $6 / $0.30$151M context uses the standard rate; Batch is roughly 50% off
claude-opus-4-6claude-opus-4-6$5$6.25 / $10 / $0.50$25Fast mode is billed at 6x the standard price
claude-opus-4-7claude-opus-4-7$5$6.25 / $10 / $0.50$25US-only inference has an extra regional multiplier in the official docs
claude-sonnet-4-5-20250929claude-sonnet-4-5 snapshot$3$3.75 / $6 / $0.30$15Snapshot IDs keep the Sonnet 4.5 price; they do not define a separate pricing table

​
OpenAI Example Prices

Crazyrouter NameOfficial ModelInputCached inputOutputNotes
gpt-54gpt-5.4$2.50$0.25$15.00Standard price applies below 270K context; long-context multipliers apply above that
gpt-4ogpt-4o$2.50$1.25$10.00Classic three-part token pricing
gpt-5gpt-5$1.25$0.125$10.00Tool charges are separate
gpt-51-codex-maxgpt-5.1-codex-max$1.25$0.125$10.00Commonly used in Codex and agentic coding workflows, but still billed with the standard three-part structure
gpt-5-minigpt-5-mini$0.25$0.025$2.00Lower-cost GPT-5 variant
gpt-5-nanogpt-5-nano$0.05$0.005$0.40Lowest-cost GPT-5 route
gpt-5.2gpt-5.2$1.75$0.175$14.00Earlier flagship tier, still standard three-part token pricing
gpt-5.5gpt-5.5$5.00$0.50$30.00Current flagship tier; the official standard-price note applies below 270K context

​
Gemini Example Prices

Crazyrouter NameOfficial ModelStandard InputStandard CacheStandard OutputNotes
gemini-3-progemini-3-pro$2.00$0.20 + $4.50 / 1M tok / hr storage$12.00<= 200K prompt tier; > 200K becomes $4 / $0.40 / $18; Google also lists Search and Maps free quotas plus $14 / 1,000 search queries
gemini-2.5-flash-litegemini-2.5-flash-lite$0.10 for text / image / video$0.01 for text / image / video + $1.00 / 1M tok / hr storage$0.40Audio input is $0.30, audio cache is $0.03; Search is 1,500 RPD free then $35 / 1,000 grounded prompts

​
xAI Example Prices

Crazyrouter NameOfficial MappingPrompt / Cached / OutputTool FeesNotes
grok-4.1-thinkingInternal reasoning routeThe public static docs do not list a standalone grok-4.1-thinking token priceweb_search $5 / 1k, x_search $5 / 1k, code_execution $5 / 1k, attachment_search $10 / 1k, collections_search $2.50 / 1kreasoning tokens are billed at the completion token price
grok-4.1Internal Grok 4.1 routeThe public static docs do not list a standalone grok-4.1 token pricesame as aboveThe Crazyrouter route name should not be treated as a public xAI static SKU
What the current xAI static docs reliably expose is the token-category structure, tool-invocation pricing, Batch 50% off, and the instruction to check model details or the console for model-specific token prices. Since grok-4.1 and grok-4.1-thinking are not individually priced in the static public docs, this page does not assign another SKU’s numbers to them.

​
Z.AI / GLM Example Prices

Crazyrouter NameOfficial ModelInputCached inputCached input storageOutputNotes
glm-5GLM-5$1.0$0.2Limited-time Free$3.2Web Search is billed separately at $0.01 / use

​
MiniMax Example Prices

​
Pay as You Go

Crazyrouter NameOfficial ModelInputPrompt caching readPrompt caching writeOutputNotes
MiniMax-M27MiniMax-M2.7$0.3$0.06$0.375$1.2This is the clearest tier to use for direct API budgeting

​
Token Plan

PlanMonthly PriceM2.7 Quota
Starter$10 / month1,500 requests / 5hrs
Plus$20 / month4,500 requests / 5hrs
Max$50 / month15,000 requests / 5hrs

​
Anthropic

Anthropic pricing is not just a simple input / output split. The official structure breaks out:
  • Base Input Tokens
  • 5m Cache Writes
  • 1h Cache Writes
  • Cache Hits & Refreshes
  • Output Tokens
Two common rules also matter:
  • Batch API usually bills input and output at roughly 50% off
  • Prompt caching follows the public multiplier rules: 5-minute cache write = 1.25x input, 1-hour cache write = 2x input, and cache hit = 0.1x input
Crazyrouter NameOfficial MappingOfficial Billing MethodNotes
claude-sonnet-4-6Anthropic claude-sonnet-4-6billed as base input / 5m cache write / 1h cache write / cache hit / outputAnthropic explicitly documents Sonnet 4.6 with 1M context, still using standard pricing
claude-opus-4-6Anthropic claude-opus-4-6billed as base input / 5m cache write / 1h cache write / cache hit / outputOpus 4.6 also supports 1M context; Fast mode uses a separate multiplier
claude-opus-4-7Anthropic claude-opus-4-7billed as base input / 5m cache write / 1h cache write / cache hit / outputOpus 4.7 is a distinct model on the official Anthropic pricing surface
claude-sonnet-4-5-20250929Anthropic snapshot ID claude-sonnet-4-5-20250929, usually displayed publicly as claude-sonnet-4-5still billed under the Sonnet 4.5 base input / cache write / cache hit / output structureSnapshot IDs are dated API names, not separate product prices
Official links:

​
OpenAI

OpenAI pricing is the most uniform of the set. The public structure is usually:
  • Input
  • Cached input
  • Output
Common extra rules:
  • Responses API itself does not add a separate model fee; billing still follows the selected model’s token rates
  • Web search, containers/code execution, Computer Use, and other tools are billed separately
  • Batch API usually discounts token pricing by about 50%
Crazyrouter NameOfficial MappingOfficial Billing MethodNotes
gpt-54internal alias, usually meaning OpenAI gpt-5.4billed as input / cached input / outputthe public standard price applies below 270K context; regional processing endpoints add another surcharge
gpt-4oOpenAI gpt-4obilled as input / cached input / outputclassic unified OpenAI pricing structure
gpt-5OpenAI gpt-5billed as input / cached input / outputtool usage is billed separately; there is no separate public “thinking token price” line item
gpt-51-codex-maxshould map to OpenAI gpt-5.1-codex-maxbilled as input / cached input / outputCodex-oriented naming, but the public price structure still matches the regular GPT-5.1 token format
gpt-5-miniOpenAI gpt-5-minibilled as input / cached input / outputsmaller lower-cost tier
gpt-5-nanoOpenAI gpt-5-nanobilled as input / cached input / outputnano tier, same billing structure
gpt-5.2OpenAI gpt-5.2billed as input / cached input / outputstill part of the GPT-5 pricing pattern
gpt-5.5OpenAI gpt-5.5billed as input / cached input / outputcurrent flagship tier; use the latest long-context notes from OpenAI before production rollout
Official links:

​
Google Gemini

Gemini pricing differs the most from OpenAI and Anthropic because Google often publishes multiple processing modes:
  • Standard
  • Batch
  • Flex
  • Priority
And it often breaks out:
  • Input
  • Output (including thinking tokens)
  • Context caching price
  • Context caching storage
  • Grounding with Google Search
  • Grounding with Google Maps
Crazyrouter NameOfficial MappingOfficial Billing MethodNotes
gemini-3-proGoogle gemini-3-pro, often displayed internally as gemini-3-proofficially split by Standard / Batch / Flex / Priority, and then by input / output / caching / search grounding / maps groundingpreview model, with separate <= 200K and > 200K prompt pricing tiers
gemini-2.5-flash-liteGoogle gemini-2.5-flash-litepriced by Standard / Batch / Flex / Priority, with separate input / output / context caching / storage / Google Search / Google Mapsstable model rather than preview; official output pricing explicitly includes thinking tokens
Official links:

​
xAI Grok

xAI pricing is best understood as token categories plus tool billing, rather than a separate pricing table for every visible route name:
  • Prompt tokens
  • Cached prompt tokens
  • Completion tokens
  • Reasoning tokens
xAI also explicitly states:
  • Reasoning tokens are billed at the completion token price
  • Web Search, X Search, Code Execution, and similar server-side tools are billed separately per 1,000 calls
  • Batch API usually applies a 50% token discount
Crazyrouter NameOfficial MappingOfficial Billing MethodNotes
grok-4.1-thinkinginternal reasoning route; conceptually closest to a Grok 4.1 reasoning configurationbilled using the xAI token-category model: prompt / cached prompt / completion / reasoning, plus tool invocation fees when relevantthe public xAI pricing docs emphasize SKU-style names such as grok-4-1-fast-reasoning; this route name should not be treated as an official standalone public SKU
grok-4.1internal Grok 4.1 route; conceptually closer to a non-thinking Grok 4.1 configurationstill follows the same xAI token-category billing logic, with tools billed separatelyfor production budgeting, rely on the current xAI public token and tool rules, not on the internal route name alone
Official links:

​
Z.AI / GLM

Z.AI GLM-5 pricing is close to the OpenAI pattern, but it adds cache storage as its own line item:
  • Input
  • Cached Input
  • Cached Input Storage
  • Output
Built-in tools such as Web Search are priced separately per use.
Crazyrouter NameOfficial MappingOfficial Billing MethodNotes
glm-5Z.AI GLM-5billed as input / cached input / cached input storage / outputofficial Web Search is charged separately, so token price alone is not the full cost picture
Official links:

​
MiniMax

MiniMax is the one vendor here where two official commercial modes matter:
  • Pay as You Go
  • Token Plan
That means:
  • Pay as You Go is the normal token-priced API path
  • Token Plan is subscription-style and, for M2.7, often described as a requests per 5-hour rolling window capacity product rather than plain token billing
Crazyrouter NameOfficial MappingOfficial Billing MethodNotes
MiniMax-M27should map to MiniMax-M2.7under Pay as You Go, billed as input / output / prompt caching read / prompt caching write; under Token Plan, billed as requests / 5hrs capacityfor production API budgeting, start with Pay as You Go; evaluate Token Plan separately for heavy coding or interactive usage
Official links:

​
Summary

If you only need a quick mental model of how each vendor bills, the shortest version is:
  • Anthropic: base input + cache write/read + output
  • OpenAI: input + cached input + output, with tools billed separately
  • Gemini: multiple processing modes + input/output + caching + search/maps grounding
  • xAI: prompt/cached/completion/reasoning, with server-side tools billed separately
  • Z.AI: input + cached input + cached storage + output
  • MiniMax: token pay-as-you-go or subscription-style capacity plan
This page explains upstream official pricing rules, not Crazyrouter selling prices. For actual recharge, billing, multiplier, and discount behavior, use Crazyrouter pricing pages, the console, and /api/pricing.