Vendor · OpenAI · 16 models

OpenAI API on Crazyrouter

OpenAI's API is card-only and unavailable in several regions. Crazyrouter serves the same models through `/v1/chat/completions` and the native `/v1/responses` endpoint (reasoning items, encrypted reasoning and tool calls pass through unchanged), bills at each model's published rates, and works with compatible SDKs by changing `base_url`. Check the model page before choosing an endpoint; GPT-6.1 Sol currently lists Chat Completions.

Cheapest OpenAI model here: GPT-4o mini at $0.0975 / $0.39 per 1M tokens. Up to 35% below list.

Get an API key →Price comparisonOfficial docs: openai.com
Input price per 1M tokens: list vs Crazyrouter
ListCrazyrouterGPT-6 Astra$10 → $6.50GPT-5.5$5.00 → $3.25GPT-5.6 Sol$4.00 → $2.60GPT-5.4$2.50 → $2.00GPT-4o$2.50 → $2.00GPT-6.1 Sol$2.00 → $2.00GPT-4.1$2.00 → $1.60OpenAI o3$2.00 → $2.00GPT-5.3 Codex$1.75 → $1.40GPT-5$1.25 → $1.00GPT-5 Codex$1.25 → $1.00GPT-5.4 mini$0.750 → $0.600GPT-4.1 mini$0.400 → $0.320GPT-4o mini$0.150 → $0.098
OpenAI on Crazyrouter

Chat and reasoning models

OpenAI
Input / 1M$2.00$2.00
Output / 1M$10$10
Context 922K input tokensCached $0.100Also on Azure · Bedrock
GPT-6.1 Solgpt-6.1-sol
Crazyrouter price: $2.00 / $10.00 per 1M tokens · list $2.00 / $10.00
OpenAI compatibleReasoningCoding
Details, samples and code →Compare prices
OpenAI
−20%
below list
Input / 1M$1.25$1.00
Output / 1M$10$8.00
Context 272K tokensCached $0.104Also on Azure
GPT-5gpt-5
Crazyrouter price: $1.00 / $8.00 per 1M tokens · list $1.25 / $10.00
OpenAI compatibleReasoningCoding
Details, samples and code →Compare prices
OpenAI
−35%
below list
Input / 1M$5.00$3.25
Output / 1M$30$20
Context 1M tokensCached $0.325Also on Azure · Bedrock
GPT-5.5gpt-5.5
Crazyrouter price: $3.25 / $19.50 per 1M tokens · list $5.00 / $30.00
OpenAI compatibleReasoningCoding
Details, samples and code →Compare prices
OpenAI
−20%
below list
Input / 1M$2.50$2.00
Output / 1M$15$12
Context 1M tokensCached $0.200Also on Azure · Bedrock
GPT-5.4gpt-5.4
Crazyrouter price: $2.00 / $12.00 per 1M tokens · list $2.50 / $15.00
OpenAI compatibleReasoningCoding
Details, samples and code →Compare prices
OpenAI
−20%
below list
Input / 1M$0.750$0.600
Output / 1M$4.50$3.60
Context 272K tokensCached $0.060Also on Azure
GPT-5.4 minigpt-5.4-mini
Crazyrouter price: $0.60 / $3.60 per 1M tokens · list $0.75 / $4.50
OpenAI compatibleFastLow cost
Details, samples and code →Compare prices
OpenAI
−35%
below list
Input / 1M$4.00$2.60
Output / 1M$20$13
Context 922K tokensCached $0.260Also on Azure · Bedrock
GPT-5.6 Solgpt-5.6-sol
Crazyrouter price: $2.60 / $13.00 per 1M tokens · list $4.00 / $20.00
OpenAI compatibleReasoningCoding
Details, samples and code →Compare prices
OpenAI
−35%
below list
Input / 1M$10$6.50
Output / 1M$50$33
Context 922K tokensCached $0.650Also on Azure · Bedrock
GPT-6 Astragpt-6-astra
Crazyrouter price: $6.50 / $32.50 per 1M tokens · list $10.00 / $50.00
OpenAI compatibleReasoningCoding
Details, samples and code →Compare prices
OpenAI
−20%
below list
Input / 1M$1.75$1.40
Output / 1M$14$11
Context 272K tokensCached $0.140Also on Azure
GPT-5.3 Codexgpt-5.3-codex
Crazyrouter price: $1.40 / $11.20 per 1M tokens · list $1.75 / $14.00
OpenAI compatibleCoding agentsCodex CLI
Details, samples and code →Compare prices
OpenAI
−20%
below list
Input / 1M$1.25$1.00
Output / 1M$10$8.00
Context 272K tokensCached $0.104Also on Azure
GPT-5 Codexgpt-5-codex
Crazyrouter price: $1.00 / $8.00 per 1M tokens · list $1.25 / $10.00
OpenAI compatibleCoding agentsCodex CLI
Details, samples and code →Compare prices
OpenAI
−20%
below list
Input / 1M$2.00$1.60
Output / 1M$8.00$6.40
Context 1M tokensCached $0.400Also on Azure
GPT-4.1gpt-4.1
Crazyrouter price: $1.60 / $6.40 per 1M tokens · list $2.00 / $8.00
OpenAI compatibleReasoningCoding
Details, samples and code →Compare prices
OpenAI
−20%
below list
Input / 1M$0.400$0.320
Output / 1M$1.60$1.28
Context 1M tokensCached $0.080Also on Azure
GPT-4.1 minigpt-4.1-mini
Crazyrouter price: $0.32 / $1.28 per 1M tokens · list $0.40 / $1.60
OpenAI compatibleFastLow cost
Details, samples and code →Compare prices
OpenAI
−20%
below list
Input / 1M$2.50$2.00
Output / 1M$10$8.00
Context 128K tokensCached $1.00Also on Azure
GPT-4ogpt-4o
Crazyrouter price: $2.00 / $8.00 per 1M tokens · list $2.50 / $10.00
OpenAI compatibleReasoningCoding
Details, samples and code →Compare prices
OpenAI
−35%
below list
Input / 1M$0.150$0.098
Output / 1M$0.600$0.390
Context 128K tokensCached $0.052Also on Azure
GPT-4o minigpt-4o-mini
Crazyrouter price: $0.0975 / $0.39 per 1M tokens · list $0.15 / $0.60
OpenAI compatibleFastLow cost
Details, samples and code →Compare prices
OpenAI
Input / 1M$2.00$2.00
Output / 1M$8.00$8.00
Context 200K tokensCached $0.500Also on Azure
OpenAI o3o3
Crazyrouter price: $2.00 / $8.00 per 1M tokens · list $2.00 / $8.00
OpenAI compatibleReasoningMath
Details, samples and code →Compare prices

Image models

GPT Image 2
GPT Image 2gpt-image-2
Crazyrouter price: $0.0377 / image
Image generationText to imageImage editing
Details, samples and code →
GPT Image 1.5
GPT Image 1.5gpt-image-1.5
Crazyrouter price: $0.165 / image
Image generationText to imageImage editing
Details, samples and code →

Why route OpenAI through Crazyrouter

  • Native Responses API with encrypted reasoning, so Codex CLI and agent frameworks behave as on OpenAI.
  • GPT-6 Astra, GPT-5.6 Sol and GPT-5.5 at 35% below list; GPT-5 and GPT-4.1 for volume work.
  • GPT Image 2 and GPT Image 1.5 behind the same key — see the image samples on each model page.
  • Multiple upstream channels with priority routing; failed requests are retried on another channel before you see an error.

FAQ

Which endpoint should I use?
`/v1/chat/completions` for anything OpenAI-compatible; `/v1/responses` when you need reasoning items, encrypted reasoning or the Codex CLI. Both accept the same key, but endpoint support varies by model. GPT-6.1 Sol currently lists Chat Completions only.
Is GPT-6 Astra available?
Yes, at $3.25 / $16.25 per 1M tokens against OpenAI's $10 / $50. It is the most-routed model on the platform.
Does Codex CLI work?
Yes — set the provider base URL to `https://api.crazyrouter.com/v1` in `config.toml`; the one-click script on the Codex integration page does it for you.
Are image models billed per token?
GPT Image models are billed per image by size and quality, shown on each model page; text models are per token.

Further reading