OpenAI
GPT-6.1 Sol
As of 2026-11-15, GPT-6.1 Sol costs $2.00 per 1 million input tokens and $10.00 per 1 million output tokens at the official list price (OpenAI API). Source: AuraMatrix Token Price Index; snapshot SHA-256 cedc40b4f1331a4b….
Official list price · OpenAI API
- Input
- 2.00
- Output
- 10.00
- Cached input
- 0.10
- Cache write
- 2.50
USD per 1M tokens. A dash means the price was not recorded, not that it is free.
Billing rule: Above 272,000 input tokens the source lists higher prices that are not recorded here. The source does not say whether cached tokens count or whether the whole request or only the excess is repriced. VERIFIED
Cache write shown is the 30-minute write.
Same channel, other plans: Batch 1.00 / 5.00 · Flex 1.00 / 5.00 · Priority 4.00 / 20.00 · Ultrafast 12.00 / 60.00.
Observed 2026-11-03 03:28 UTC. The source still stated these prices at the last daily check, 2026-11-15 22:15 UTC.
Cheaper in the same tier
How to read this
Official list prices, blended 3 parts input to 1 part output, against models the vendors place in the same tier. Price only: a cheaper model is not an equal one, and nothing here measures quality.
What this price buys
Estimates from the official list price above: tokens read and written for a typical job of that size, times the price. Your own usage will differ. See how these are worked out, and try other jobs →
All channels
| Channel | Type | Region | Input | Output | Cached in | vs officialinput / output | Status | Source |
|---|---|---|---|---|---|---|---|---|
| OpenAI APIlowest inputOpenAI · observed 2026-11-03 03:28 UTC · confirmed 2026-11-15 22:15 UTCStandard tier. Regional data-residency endpoints carry a 10% uplift per the source page.Cache write shown is the 30-minute write. | Officialone list price worldwide | globalGlobal endpoint | 2.00 | 10.00 | 0.10 | reference | VERIFIED | Source |
| Azure AI Foundry, Global deploymentMicrosoft Azure · observed 2026-11-03 09:46 UTC · confirmed 2026-11-15 22:15 UTCStandard tier, Global deployment: the same price in all 26 listed Azure regions.Read from the Azure Retail Prices API (Standard tier). Flex meters, where Azure lists them, are separate records; Azure publishes no priority (PP) meters for this model. | Cloudfixed price per region | globalGlobal endpoint | 2.00 | 10.00 | 0.10 | 0% / 0% | VERIFIED | Source |
| Azure AI Foundry, Data Zone (US)Microsoft Azure · observed 2026-11-03 09:46 UTC · confirmed 2026-11-15 22:15 UTCStandard tier, Data Zone deployment in the 7 US regions (centralus, eastus, eastus2, northcentralus, southcentralus, westus, westus3).Read from the Azure Retail Prices API (Standard tier). Flex meters, where Azure lists them, are separate records; Azure publishes no priority (PP) meters for this model. | Cloudfixed price per region | 2.20 | 11.00 | 0.11 | +10% / +10% | VERIFIED | Source | |
| Azure AI Foundry, Data Zone (EU)Microsoft Azure · observed 2026-11-03 09:46 UTC · confirmed 2026-11-15 22:15 UTCStandard tier, Data Zone deployment in the 6 EU regions (francecentral, germanywestcentral, polandcentral, spaincentral, swedencentral, westeurope).Read from the Azure Retail Prices API (Standard tier). Flex meters, where Azure lists them, are separate records; Azure publishes no priority (PP) meters for this model. | Cloudfixed price per region | 2.40 | 12.00 | 0.12 | +20% / +20% | VERIFIED | Source | |
| OpenRouterOpenRouter · observed 2026-11-03 03:28 UTC · confirmed 2026-11-15 22:15 UTCPrice listed by OpenRouter's public models API. The billed price can depend on the provider OpenRouter routes to.OpenRouter model id openai/gpt-6.1-sol. Converted from per-token prices. Cache write and context/time overrides as exposed by the models API. | Aggregatormarketplace's own price | globalGlobal endpoint | 2.00 | 10.00 | 0.10 | 0% / 0% | LISTED | Source |
Service plans
| Plan | Channel | Input | Output | Cached in | vs standardinput / output | Status | Source |
|---|---|---|---|---|---|---|---|
| BatchBatch API. Cache write shown is the 30-minute write. | OpenAI APIobserved 2026-11-03 03:28 UTC · confirmed 2026-11-15 22:15 UTC | 1.00 | 5.00 | 0.05 | −50% / −50% | VERIFIED | Source |
| FlexFlex processing; the page lists one Flex/Batch price table. Cache write shown is the 30-minute write. | OpenAI APIobserved 2026-11-03 03:28 UTC · confirmed 2026-11-15 22:15 UTC | 1.00 | 5.00 | 0.05 | −50% / −50% | VERIFIED | Source |
| PriorityFast mode, formerly Priority processing (renamed 2026-07-30 per the page). Cache write shown is the 30-minute write. | OpenAI APIobserved 2026-11-03 03:28 UTC · confirmed 2026-11-15 22:15 UTC | 4.00 | 20.00 | 0.20 | +100% / +100% | VERIFIED | Source |
| UltrafastUltrafast tier. Cache write shown is the 30-minute write. | OpenAI APIobserved 2026-11-03 03:28 UTC · confirmed 2026-11-15 22:15 UTC | 12.00 | 60.00 | 0.60 | +500% / +500% | VERIFIED | Source |
| FlexFlex, read from the Azure Retail Prices API. | Azure AI Foundry, Global deploymentobserved 2026-11-03 09:46 UTC · confirmed 2026-11-15 22:15 UTCLong context (Azure "LongCo" meters): input 2.00, output 7.50 | 1.00 | 5.00 | 0.05 | −50% / −50% | VERIFIED | Source |
Measured
One small request an hour, plus one longer request a day to measure speed, sent from our Los Angeles server over the last 7 days. This does not test model quality; it shows whether the API answered, how soon and how fast. All models →
| Channel | Answered | First tokenmedian | Speedtokens per second | Charged vs list price | Last call |
|---|---|---|---|---|---|
| OpenAI API | 100%106 of 106 calls | 1.8 s | 175 | — | 2026-11-15 22:07 UTC |
| OpenRouterserved by OpenAI | 100%107 of 107 calls | 1.1 s | 160 | as listed111 requests | 2026-11-15 22:07 UTC |
Price history
Input price per 1M tokens on each channel, from the first record to the last daily check. A price holds until the next record that states another one, so the lines are steps; a flat line means the price has not moved since we started recording.
| Channel | Since | First | Course | Now | Moves |
|---|---|---|---|---|---|
| Azure AI Foundry, Data Zone (EU) | 2026-11-03 | 2.40 | 2.40 | · | |
| Azure AI Foundry, Data Zone (US) | 2026-11-03 | 2.20 | 2.20 | · | |
| Azure AI Foundry, Global deployment | 2026-11-03 | 2.00 | 2.00 | · | |
| OpenAI API | 2026-11-03 | 2.00 | 2.00 | · | |
| OpenRouter | 2026-11-03 | 2.00 | 2.00 | · |
Names this model is listed under
- gpt-6.1-sol
- openai/gpt-6.1-sol
Compare with
Check a pricePaying for this model, or holding a quote?See where your price stands →
In your AIAsk your assistant: “Where is GPT-6.1 Sol cheapest right now, and how fast is it?”Connect in one click →
Sources
Each price above was read from one of these snapshots. The hash identifies the exact page content that was seen.
OpenAI API pricing (OpenAI docs)
- URL
- https://developers.openai.com/api/docs/pricing
- Fetched
- 2026-11-03 03:28 UTC
- SHA-256
- cedc40b4f1331a4ba0e1dd22711170496756b30a8bccafc12d2f3c3868c2ab8c
- Size
- 594,966 bytes
- Records
- q-20261103-openai-api-gpt-6.1-sol · OpenAI API · recorded by hand from the page by claude (agent) · reviewed by codex (agent) · Cache write shown is the 30-minute write.
- q-20261103-openai-api-gpt-6.1-sol-batch · OpenAI API (Batch) · recorded by hand from the page by claude (agent) · reviewed by codex (agent) · Batch API. Cache write shown is the 30-minute write.
- q-20261103-openai-api-gpt-6.1-sol-flex · OpenAI API (Flex) · recorded by hand from the page by claude (agent) · reviewed by codex (agent) · Flex processing; the page lists one Flex/Batch price table. Cache write shown is the 30-minute write.
- q-20261103-openai-api-gpt-6.1-sol-priority · OpenAI API (Priority) · recorded by hand from the page by claude (agent) · reviewed by codex (agent) · Fast mode, formerly Priority processing (renamed 2026-07-30 per the page). Cache write shown is the 30-minute write.
- q-20261103-openai-api-gpt-6.1-sol-ultrafast · OpenAI API (Ultrafast) · recorded by hand from the page by claude (agent) · reviewed by codex (agent) · Ultrafast tier. Cache write shown is the 30-minute write.
OpenRouter public models API
- URL
- https://openrouter.ai/api/v1/models
- Fetched
- 2026-11-03 03:28 UTC
- SHA-256
- ed770f5fe898372da83aabd7d809dadb9333da21f66a03ca7258981f303a59bb
- Size
- 805,075 bytes
- Records
- q-20261103-openrouter-gpt-6.1-sol · OpenRouter · read from a machine-readable price list by claude (agent) · reviewed by codex (agent) · OpenRouter model id openai/gpt-6.1-sol. Converted from per-token prices. Cache write and context/time overrides as exposed by the models API.
Azure Retail Prices API: Foundry Models, product Azure OpenAI GPT6
- URL
- https://prices.azure.com/api/retail/prices?api-version=2023-01-01-preview&$filter=productName eq 'Azure OpenAI GPT6' and priceType eq 'Consumption'
- Fetched
- 2026-11-03 09:46 UTC
- SHA-256
- 53d4e7ca69bea52a5a9d41494bf47121fc842cb132436e25b75300f2813aebd3
- Size
- 1,897,305 bytes
- Records
- q-20261103-azure-global-gpt-6.1-sol · Azure AI Foundry, Global deployment · read from a machine-readable price list by claude (agent) · reviewed by codex (agent) · Read from the Azure Retail Prices API (Standard tier). Flex meters, where Azure lists them, are separate records; Azure publishes no priority (PP) meters for this model.
- q-20261103-azure-datazone-us-gpt-6.1-sol · Azure AI Foundry, Data Zone (US) · read from a machine-readable price list by claude (agent) · reviewed by codex (agent) · Read from the Azure Retail Prices API (Standard tier). Flex meters, where Azure lists them, are separate records; Azure publishes no priority (PP) meters for this model.
- q-20261103-azure-datazone-eu-gpt-6.1-sol · Azure AI Foundry, Data Zone (EU) · read from a machine-readable price list by claude (agent) · reviewed by codex (agent) · Read from the Azure Retail Prices API (Standard tier). Flex meters, where Azure lists them, are separate records; Azure publishes no priority (PP) meters for this model.
- q-20261103-azure-global-gpt-6.1-sol-flex · Azure AI Foundry, Global deployment (Flex) · read from a machine-readable price list by claude (agent) · reviewed by codex (agent) · Flex, read from the Azure Retail Prices API.