GPT-6.1 Sol: Release Intelligence, Performance & Price

artificialanalysis.ai · 2026-09-29 · by Long Nguyen ·generic
The GPT-6.1 Sol release offers 5 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across the 5 models. For intelligence, the top model of GPT-6.1 Sol is GPT-6.1 Sol (max) at 52. For output speed, the fastest model is GPT-6.1 Sol (low) at 74 t/s. For latency, GPT-6.1 Sol (low) at 1.84s offers the lowest time to first answer token. For pricing, GPT-6.1 Sol (low) at $0.13 offers the lowest cost per task. Prices vary up to 5.5x across models.

GPT-6.1 Sol: Release Intelligence, Performance & Price

Artificial Analysis

[](https://artificialanalysis.ai/login)K

All Releases•

OpenAI logo

OpenAI

•

Proprietary release

•

Released September 2026

GPT-6.1 Sol: Release Intelligence, Performance & Price

CompareTry it out

Available providers

OpenAIOpenAI

#### Intelligence

GPT-6.1 Sol (max)GPT-6.1 Sol (max)52GPT-6.1 Sol (xhigh)GPT-6.1 Sol (xhigh)51GPT-6.1 Sol (high)GPT-6.1 Sol (high)50GPT-6.1 Sol (medium)GPT-6.1 Sol (medium)48GPT-6.1 Sol (low)GPT-6.1 Sol (low)42

Artificial Analysis Intelligence Index

#### Speed

GPT-6.1 Sol (low)GPT-6.1 Sol (low)74 t/sGPT-6.1 Sol (max)GPT-6.1 Sol (max)67 t/sGPT-6.1 Sol (high)GPT-6.1 Sol (high)66 t/sGPT-6.1 Sol (xhigh)GPT-6.1 Sol (xhigh)64 t/sGPT-6.1 Sol (medium)GPT-6.1 Sol (medium)62 t/s

Output speed

#### Cost

GPT-6.1 Sol (low)GPT-6.1 Sol (low)$0.13GPT-6.1 Sol (medium)GPT-6.1 Sol (medium)$0.21GPT-6.1 Sol (high)GPT-6.1 Sol (high)$0.32GPT-6.1 Sol (xhigh)GPT-6.1 Sol (xhigh)$0.39GPT-6.1 Sol (max)GPT-6.1 Sol (max)$0.72

Per Intelligence Index Task

The GPT-6.1 Sol release offers 5 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across the 5 models.

  • For intelligence, the top model of GPT-6.1 Sol is GPT-6.1 Sol (max) at 52.
  • For output speed, the fastest model is GPT-6.1 Sol (low) at 74 t/s.
  • For latency, GPT-6.1 Sol (low) at 1.84s offers the lowest time to first answer token.
  • For pricing, GPT-6.1 Sol (low) at $0.13 offers the lowest cost per task. Prices vary up to 5.5x across models.

    • Technical specifications

    | Reasoning | YesThis page shows the reasoning version of this model.A non-reasoning variant may also exist. | | --------------- | ---------------------------------------------------------------------------------------------- | | Input modality | Supports: text and image | | Output modality | Supports: text | | Context window | 1M\~1500 A4 pages of size 12 Arial font |

    Intelligence

    Artificial Analysis Intelligence Index

    Artificial Analysis Intelligence Index v4.3.2 incorporates 10 evaluations: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1

    28 of 684 models

    ###

    Artificial Analysis Intelligence Index

    Artificial Analysis Intelligence Index v4.3.2 includes: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

    Intelligence Index vs. Cost per TaskIntelligence Index vs. Time per TaskIntelligence Index vs. Output Tokens per Task

    Intelligence Index vs. Cost per Intelligence Index Task

    Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task

    28 of 684 models

    Most attractive quadrant

    GPT-6.1 Sol

    Pareto line

    OpenAIAnthropicMeta

    ###

    Cost per Intelligence Index Task

    Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

    ###

    Artificial Analysis Intelligence Index

    Artificial Analysis Intelligence Index v4.3.2 includes: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

    Cost

    Cost per Intelligence Index Task

    Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better

    28 of 684 models

    AnswerReasoningCache WriteCache HitInput

    ###

    Cost per Intelligence Index Task

    Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

    Speed & Latency

    Output SpeedLatency

    Output Speed

    Output tokens per second · Higher is better

    28 of 684 models

    ###

    Output Speed

    Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

    ###

    Model Performance Representation

    Figures represent performance of the model's first-party API or the median across providers where a first-party API is not available.

    Capability Scores

    Capability Indexes

    Measures the performance of models on specific capabilities and industries

    28 of 684 models

    Finance & Accounting Index

    Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better

    Strategy & Ops Index

    Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better

    Legal Index

    Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better

    Healthcare & Medical Index

    Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better

    Engineering Index

    Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2.1, AA-Briefcase v1.1, Terminal-Bench 4.0 · Higher is better

    Economics Index

    Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2.1, AA-Briefcase v1.1, AA-LCR v1.1 · Higher is better

    More from OpenAI

  • OpenAI logoGPT-6 Astra5 models53Highest Intelligence
  • OpenAI logoGPT-6 Sol6 models48Highest Intelligence
  • OpenAI logoGPT-5.6 Terra6 models42Highest Intelligence
  • OpenAI logoGPT-6 Luna6 models37Highest Intelligence
  • OpenAI logoGPT-5.3 Codex1 model33Highest Intelligence
  • OpenAI logoGPT-5.5 Instant (June 2026)1 model26Highest Intelligence

Further details

| Model Name | Model Creator | Intelligence | Parameters | Context Window | Price | Output SpeedTokens/s | Weights | Providers | Provider Benchmarks | | ------------------------------------------------------------------------------- | ------------------------------------------------------------------------ | ------------ | ---------- | -------------- | ----- | -------------------- | ------------- | ------------------------------------------------------------- | ------------------------------------------------------------------------- | | GPT-6.1 Sol (max) | OpenAI logoOpenAI | 52 | \- | 1M | $1.5 | 67 | Not available | OpenAI | View | | GPT-6.1 Sol (xhigh) | OpenAI logoOpenAI | 51 | \- | 1M | $1.5 | 64 | Not available | OpenAI | View | | GPT-6.1 Sol (high) | OpenAI logoOpenAI | 50 | \- | 1M | $1.5 | 66 | Not available | OpenAI | View | | GPT-6.1 Sol (medium) | OpenAI logoOpenAI | 48 | \- | 1M | $1.5 | 62 | Not available | OpenAI | View | | GPT-6.1 Sol (low) | OpenAI logoOpenAI | 42 | \- | 1M | $1.5 | 74 | Not available | OpenAI | View |

artificialanalysis.ai · 1 images · 52 links

Comments (0)

No comments yet