Singularity Logs

THE MODEL, IN DETAIL / OpenAI

GPT-6.1 Sol (max)

openai/gpt-6.1-solProprietaryReasoningmax configuration

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...

OpenRouter
Source-linked model intelligenceCatalog added 29 Sept 2026Specifications observed 28 Oct 2026

Specifications and providers describe OpenAI: GPT-6.1 Sol. Evaluation scores retain the exact max configuration.

GPQA Diamond

95.4%

Source-reported

Context window

1.1M

128K max output tokens

Input price

$2

USD / million input tokens

Output price

$10

USD / million output tokens

Inference providers

3

8 provider routes observed

Measured output speed

—

No model-level measurement

01 / PERFORMANCE

A clearer view of capability.

Read the score, understand the context, and explore where this model sits among its peers.

Performance fingerprint

Individual published accuracy scores · not a composite index

Individual benchmark accuracy. Axes represent different tasks, not a composite index.FrontierMath Ti…FrontierMath Ti…GPQA DiamondOTIS Mock AIME …SimpleQA VerifiedFrontierMath Tier 4 v2: 100FrontierMath Tiers 1–3 v2: 93.7GPQA Diamond: 95.4OTIS Mock AIME 2024–2025: 100SimpleQA Verified: 73.9Each axis: 0–100% · Individual evaluations

Performance meets price

GPQA Diamond · same published source and version

Higher score · lower cost80$085$8.62590$17.2595$25.875100$34.5Gemini 4 Argon (high) GPQA Diamond: 96.4 Input: $2/M tokensGPT-6 Astra (max) GPQA Diamond: 95.8 Input: $10/M tokensClaude Sonnet 5.5 (max) GPQA Diamond: 95.6 Input: $2/M tokensGPT-6.1 Sol (max) GPQA Diamond: 95.4 Input: $2/M tokensGPT-6.1 Sol (max)Gemini 3.8 Flash (high) GPQA Diamond: 95.4 Input: $0.825/M tokensGemini 3.7 Flash (high) GPQA Diamond: 94.8 Input: $0.75/M tokensGPT-5.4 Pro (xhigh) GPQA Diamond: 94.6 Input: $30/M tokensGemini 3.1 Pro Preview GPQA Diamond: 94.4 Input: $2/M tokensGPT-6 Sol (max) GPQA Diamond: 94.3 Input: $2/M tokensGPT-6.1 Terra (max) GPQA Diamond: 94.3 Input: $1/M tokensGemini 3.6 Flash GPQA Diamond: 94.1 Input: $0.75/M tokensGemini 3.1 Pro Preview GPQA Diamond: 94.1 Input: $2/M tokensInput price · USD / million tokens
Google DeepMindOpenAIAnthropic

In good company

GPQA Diamond · Epoch AI · benchmark data

96.4
Google DeepMind
95.8
OpenAI
95.6
Anthropic
95.4
This model
95.4
Google DeepMind
94.8
Google DeepMind
94.6
OpenAI
94.4
Google DeepMind
94.3
OpenAI
94.3
OpenAI

Rank #4 in this published cohort. 325 models in the source cohort. Showing selected nearby models. Evaluation settings can differ.

Evidence, by task.

Coverage is not a capability score.

5published results
1 evaluation source
Reasoning5 evaluations
CodingAwaiting evidence
Mathematics3 evaluations
VisionAwaiting evidence
AgenticAwaiting evidence
Long contextAwaiting evidence

Documented features, task evaluations, and preference rankings describe different things. Missing coverage does not imply a model cannot perform a task.

Explore our methodology

02 / BENCHMARK EXPLORER

The numbers behind the model.

Original results, exact versions, and a direct path to the evidence behind every score.

5 published results
020406080100FrontierMath Tier 4 v2: 100% · Epoch AI · independent runs · Epoch AI · benchmark data100%FrontierMath Tie…Higher is betterFrontierMath Tiers 1–3 v2: 93.7% · Epoch AI · independent runs · Epoch AI · benchmark data93.7%FrontierMath Tie…Higher is betterGPQA Diamond: 95.4% · Epoch AI · independent runs · Epoch AI · benchmark data95.4%GPQA DiamondHigher is betterOTIS Mock AIME 2024–2025: 100% · Epoch AI · independent runs · Epoch AI · benchmark data100%OTIS Mock AIME 2…Higher is betterSimpleQA Verified: 73.9% · Epoch AI · independent runs · Epoch AI · benchmark data73.9%SimpleQA VerifiedHigher is better

5 percentage-based evaluations. Each benchmark measures a different task; compare results within the same evaluation and protocol.

Published benchmark results for GPT-6.1 Sol (max)
BenchmarkScoreVersion & metricSourcePublishedEvidence
Epoch AI · independent runsAccuracy · Higher is betterEpoch AI · benchmark dataSource-reportedNot available
Epoch AI · independent runsAccuracy · Higher is betterEpoch AI · benchmark dataSource-reportedNot available
Epoch AI · independent runsAccuracy · Higher is betterEpoch AI · benchmark dataSource-reportedNot available
Epoch AI · independent runsAccuracy · Higher is betterEpoch AI · benchmark dataSource-reportedNot available
Epoch AI · independent runsAccuracy · Higher is betterEpoch AI · benchmark dataSource-reportedNot available

03 / COST & VALUE

Know what your workload costs.

Explore token prices, see where the spend goes, and model a workload of your own.

Input$2per million tokens
Output$10per million tokens
Cache read$0.1per million tokens
Cache write$2.5per million tokens
Additional published rates
Additional rates supplied by the model catalog
Billing fieldPublished rateBilling basis
Overrides[{"prompt":"0.000004","completion":"0.000015","input_cache_read":"0.0000002","input_cache_write":"0.000005","min_prompt_tokens":272000}]Source-supplied USD rate; see provider billing terms
Web Search$0.01Source-supplied USD rate; see provider billing terms
Input Cache Write$2.5USD / million tokens

Workload cost calculator

Change the numbers. See the trade-offs.

Token estimate only. Excludes cache writes, tools, and other provider fees. Actual token usage and provider limits vary.

Your estimated spend

1,000 requests · 11M tokens

$30estimated total
Uncached input$20
Cached input$0
Output$10
Per request$0.03
Without cache discount$30
Estimated cache savings$0

04 / INFERENCE NETWORK

One model. Different ways to run it.

Compare inference routes by price, context, quantization, and reported availability.

3 providers · 8 routes
Provider routes for GPT-6.1 Sol (max), observed 28 Oct 2026
Provider / routeInput / MOutput / MCache / MContextOutput limitSpeedLatencyAvailability · 1dRates
OOpenAIQuantization not disclosed · flex$1$5$0.051.1M128K——66.36%
AAzureQuantization not disclosed$2$10$0.11.1M128K——79.58%
OOpenAIQuantization not disclosed$2$10$0.11.1M128K——100%
AAmazon BedrockQuantization not disclosed$2.2$11$0.111.1M128K——100%
AAzureQuantization not disclosed$2.2$11$0.111.1M128K——99.86%
AAzureQuantization not disclosed$2.2$11$0.111.1M128K——99.86%
OOpenAIQuantization not disclosed · priority$4$20$0.21.1M128K——100%
OOpenAIQuantization not disclosed · ultrafast$12$60$0.61.1M128K——100%

Snapshot observed 28 Oct 2026. Speed and latency are the reported 30-minute median when available. This is a dated snapshot, not live monitoring.

Provider price comparison

USD per million tokens · input and output rates

InputOutput
OpenAI · flex
Input
$1
Output
$5
Azure
Input
$2
Output
$10
OpenAI
Input
$2
Output
$10
Amazon Bedrock
Input
$2.2
Output
$11
Azure
Input
$2.2
Output
$11
Azure
Input
$2.2
Output
$11
OpenAI · priority
Input
$4
Output
$20
OpenAI · ultrafast
Input
$12
Output
$60

Reported availability

Provider availability over the selected observation window

OpenAI · flex66.36%
Azure79.58%
OpenAI100%
Amazon Bedrock100%
Azure99.86%
Azure99.86%
OpenAI · priority100%
OpenAI · ultrafast100%

Output speed

Reported 30-minute p50 · tokens per second

No provider throughput measurements were returned in this snapshot.

Response latency

Reported 30-minute p50 · seconds

No provider latency measurements were returned in this snapshot.

Context by provider

Actual route limits can differ from the catalog maximum

OpenAI · flex1.1M
Azure1.1M
OpenAI1.1M
Amazon Bedrock1.1M
Azure1.1M
Azure1.1M
OpenAI · priority1.1M
OpenAI · ultrafast1.1M

05 / CAPABILITIES & MODALITIES

What goes in. What comes out.

A map of documented interfaces and API features, separate from benchmark performance.

INPUT MODALITIES

FileImageText
GPT-6.1 Sol (max)Reasoning supported

OUTPUT MODALITIES

Text

Feature support

Listed catalog API parameters and documented pricing features

ReasoningSupported
Tool callingSupported
Tool choiceSupported
Structured outputsSupported
Response formatSupported
Reasoning detailsSupported
Seed controlSupported
Stop sequencesNot listed
Prompt cachingSupported
TemperatureNot listed

Room to work

Context capacity and completion limits

1.1Mtotal context tokens
Context window
128Kmax output

Output tokens share the total context budget. The maximum completion length is a separate limit, and individual provider routes may have smaller limits.

Catalog context
1,050,000 tokens
Maximum output
128,000 tokens
Top-provider context
1,050,000 tokens

Features vary by route

Check the provider before depending on a specific API feature.

API feature support by provider
Provider routeReasoningToolsStructured outputResponse formatImplicit caching
OpenAI · flexSupportedSupportedSupportedSupportedNot listed
AzureSupportedSupportedSupportedSupportedNot listed
OpenAISupportedSupportedSupportedSupportedNot listed
Amazon BedrockSupportedSupportedNot listedNot listedNot listed
AzureSupportedSupportedSupportedSupportedNot listed
AzureSupportedSupportedSupportedSupportedNot listed
OpenAI · prioritySupportedSupportedSupportedSupportedNot listed
OpenAI · ultrafastSupportedSupportedSupportedSupportedNot listed

06 / UNDER THE HOOD

The complete specification sheet.

Exact identities, model architecture, limits, and the defaults that shape a request.

Identity & architecture

Developer
OpenAI
Exact identity
gpt-6.1-sol_max
Subject
Model Configuration
Access
proprietary
License
Not disclosed
Parameters
Not disclosed
Tokenizer
GPT
Instruction format
Not disclosed

Reasoning & controls

Reasoning
Supported
Mandatory reasoning
Yes
Reasoning by default
Enabled
Published configuration
max
Supported reasoning efforts
max, xhigh, high, medium, low
Default reasoning effort
medium
API parameters
11
Provider moderation
Yes
Quantization variants
Not disclosed

Dates & limits

Catalog added
29 Sept 2026
Knowledge cutoff
Not disclosed
Catalog expiration
Not documented
Specifications observed
28 Oct 2026
Providers observed
28 Oct 2026
Request limits
Provider-specific / not supplied
Canonical catalog ID
openai/gpt-6.1-sol-20260929

API parameters & defaults

Availability is catalog-wide. Defaults can vary across providers.

include_reasoningSupported · default not supplied
max_completion_tokensSupported · default not supplied
max_tokensSupported · default not supplied
reasoningSupported · default not supplied
reasoning_effortSupported · default not supplied
response_formatSupported · default not supplied
seedSupported · default not supplied
structured_outputsSupported · default not supplied
tool_choiceSupported · default not supplied
toolsSupported · default not supplied
verbositySupported · default not supplied

07 / BUILD WITH THIS MODEL

From exploration to your first request.

Use the documented catalog identifier and keep your API key in an environment variable.

Make an API request

const response = await fetch(
  "https://openrouter.ai/api/v1/chat/completions",
  {
    method: "POST",
    headers: {
      Authorization: `Bearer ${process.env.OPENROUTER_API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      "model": "openai/gpt-6.1-sol",
      "messages": [
        {
          "role": "user",
          "content": "Explain the trade-offs in this design."
        }
      ],
      "reasoning": {
        "effort": "max"
      }
    }),
  },
);
if (!response.ok) throw new Error(`HTTP ${response.status}`);
const data = await response.json();
console.log(data.choices[0].message.content);

08 / PROVENANCE & HISTORY

Every number has a story.

Follow the source, check the observation date, and distinguish published results from model specifications.

The observation trail

Recorded events, in chronological order

Added to the model catalog

Catalog creation date, as recorded by OpenRouter.

Provider routes observed

8 inference routes in this snapshot.

Model specifications observed

Catalog pricing, limits, and supported parameters captured.

Observation dates describe when data was captured. They do not represent newly run evaluations or continuous performance monitoring.

Published observation ledger

Historical evidence, with source and version preserved.

Published observation history for GPT-6.1 Sol (max)
ObservedBenchmarkScoreVersionSourceVerification
28 Oct 2026SimpleQA VerifiedEpoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026FrontierMath Tier 4 v2Epoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026FrontierMath Tiers 1–3 v2Epoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026OTIS Mock AIME 2024–2025Epoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026GPQA DiamondEpoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026SimpleQA VerifiedEpoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026FrontierMath Tier 4 v2Epoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026FrontierMath Tiers 1–3 v2Epoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026OTIS Mock AIME 2024–2025Epoch AI · independent runsEpoch AI · benchmark dataSource-reported
28 Oct 2026GPQA DiamondEpoch AI · independent runsEpoch AI · benchmark dataSource-reported

09 / A FEW MORE DETAILS

Questions worth asking.

Quick answers, drawn from this model’s connected specifications.

How much does GPT-6.1 Sol (max) cost?

Catalog starting rates are $2 per million input tokens and $10 per million output tokens. Cache-read pricing is $0.1 per million tokens. Compare provider routes and service tiers above for their specific prices.

How much context can it handle?

1,050,000 tokens in the catalog context window. The catalog lists a maximum of 128,000 completion tokens. Provider limits can differ.

Does it support tools and structured output?

Tool calling: listed as supported. Structured outputs: listed as supported. See the provider feature matrix for route-specific differences.

How should I interpret these benchmark results?

Read the benchmark name, exact version, metric, source, and model configuration together. Different evaluation settings can change the result. Preference ratings and source-defined composite indices remain separate from task accuracy.

Are these prices and provider measurements live?

This page uses dated source snapshots. Catalog data was observed on 28 Oct 2026. Provider routes were observed on 28 Oct 2026. Missing measurements are not estimated or treated as zero.

KEEP EXPLORING

More from OpenAI.

Explore related identities from the same developer, or take them into a side-by-side comparison.

THE RIGHT MODEL STARTS WITH THE RIGHT CONTEXT.

Put the details side by side.

Explore the trade-offs in a direct model comparison.

Compare GPT-6.1 Sol (max)
Source-backed evidence. Different tasks. A clearer picture.
AboutMethodologyBenchmark dashboard