Home/Models
Models/OpenAI

GPT-6 Sol

GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost and shares Astra's clearer, more concise communication style in technical and coding conversations.

openai/gpt-6-sol
Organization
OpenAI
Family
gpt-sol
Providers
34
Context
1,050,000
Output limit
128,000
Knowledge
2026-04-20
Release
2026-09-22
Updated
—
Weights
Closed
Input
text, image/jpeg, image/png, image/gif, image/webp, application/pdf
Output
text
Capabilities
—

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

45 offers · USD per million tokens
ProviderModel IDContextOutputInput / output · 1MReasoningToolsStructuredDetails
302.AI
gpt-6-sol
1,050,000128,000— / ————
View
AIHubMix
gpt-6-sol
1,050,000128,000— / ————
View
AI/ML API
openai/gpt-6-sol
1,050,000128,000— / ————
View
Aixy
openai/gpt-6-sol
1,050,000128,000— / ————
View
Amazon Bedrock
us.openai.gpt-6-sol
1,050,000128,000— / ————
View
Amazon Bedrock
openai.gpt-6-sol
1,050,000128,000— / ————
View
Amazon Bedrock
global.openai.gpt-6-sol
1,050,000128,000— / ————
View
Azure
gpt-6-sol
1,050,000128,000— / ————
View
Boundless
gpt-6-sol
1,050,000128,000— / ————
View
Cloudflare AI Gateway
openai/gpt-6-sol
1,050,000128,000— / ————
View
CommandCode
gpt-6-sol
1,050,000128,000— / ————
View
Cortecs
gpt-6-sol
1,050,000128,000— / ————
View
CrossModel
openai/gpt-6-sol
1,050,000128,000— / ————
View
DevPass (LLM Gateway)
gpt-6-sol
1,050,000128,000— / ————
View
DigitalOcean
openai-gpt-6-sol
1,050,000128,000— / ————
View
Eden AI
openai/gpt-6-sol
1,050,000128,000— / ————
View
GitHub Copilot
gpt-6-sol
1,050,000128,000— / ————
View
GitLab Duo
duo-chat-gpt-6-sol
1,050,000128,000— / ————
View
Kilo Gateway
openai/gpt-6-sol
1,050,000128,000— / ————
View
LLM Gateway
openai/gpt-6-sol
1,050,000128,000— / ————
View
LLM Gateway
azure/gpt-6-sol
1,050,000128,000— / ————
View
LowRouter
auto/openai/gpt-6-sol
1,050,000128,000— / ————
View
Merge Gateway
openai/gpt-6-sol
1,050,000128,000— / ————
View
NanoGPT
openai/gpt-6-sol
1,050,000128,000— / ————
View
NEAR AI Cloud
openai/gpt-6-sol
1,050,000128,000— / ————
View
Neon
gpt-6-sol
1,050,000128,000— / ————
View
Ofox
openai/gpt-6-sol
1,050,000128,000— / ————
View
OpenAI
gpt-6-sol
1,050,000128,000— / ————
View
OpenCode
gpt-6-sol
1,050,000128,000— / ————
View
Amazon Bedrockvia OpenRouter
openai/gpt-6-sol
unknown		1,050,000128,000$2.20 / $11.00YesYesYes
View
Azurevia OpenRouter
openai/gpt-6-sol
unknown		1,050,000128,000$2.00 / $10.00YesYesYes
View
Azurevia OpenRouter
openai/gpt-6-sol
unknown		1,050,000128,000$2.20 / $11.00YesYesYes
View
Azurevia OpenRouter
openai/gpt-6-sol
unknown		1,050,000128,000$2.20 / $11.00YesYesYes
View
OpenAIvia OpenRouter
openai/gpt-6-sol
unknown		1,050,000128,000$1.00 / $5.00YesYesYes
View
OpenAIvia OpenRouter
openai/gpt-6-sol
unknown		1,050,000128,000$4.00 / $20.00YesYesYes
View
OpenAIvia OpenRouter
openai/gpt-6-sol
unknown		1,050,000128,000$2.00 / $10.00YesYesYes
View
Perplexity Agent
openai/gpt-6-sol
1,050,000128,000— / ————
View
Prime Inference
openai/gpt-6-sol
1,050,000128,000— / ————
View
Requesty
gpt-6-sol
1,050,000128,000— / ————
View
Requesty
gpt-6-sol@eu
1,050,000128,000— / ————
View
Venice AI
openai-gpt-6-sol
1,050,000128,000— / ————
View
Vercel AI Gateway
openai/gpt-6-sol
1,050,000128,000— / ————
View
Vercel AI Gateway
openai/gpt-6-sol-fast
1,050,000128,000— / ————
View
Vivgrid
gpt-6-sol
1,050,000128,000— / ————
View
ZenMux
openai/gpt-6-sol
1,050,000128,000— / ————
View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens
Input from$1.00Per 1M input tokens
Output from$5.00Per 1M output tokens
Available offers45Across 34 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 7 lowest-priced configurations
InputOutput
OpenAIopenai/flex
$1.00$5.00
Azureazure
$2.00$10.00
OpenAIopenai
$2.00$10.00
Amazon Bedrockamazon-bedrock/us-east-1
$2.20$11.00
Azureazure/eu
$2.20$11.00
Azureazure/us
$2.20$11.00
OpenAIopenai/fast
$4.00$20.00
openai/gpt-6-solObserved
Input
$2.00
Output
$10.00
Cache read
$0.20
Cache write
$2.50
Additional fees and pricing conditions
web search
$0.01 / search

overrides · USD per token for token prices; time windows use UTC.

[
  {
    "prompt": "0.000004",
    "completion": "0.000015",
    "input_cache_read": "0.0000004",
    "input_cache_write": "0.000005",
    "min_prompt_tokens": 272000
  }
]
Hosting prices through OpenRouter All endpoints and cache rates
EndpointInput / 1MOutput / 1MCache read / 1MCache write / 1M
Amazon Bedrockamazon-bedrock/us-east-1$2.20$11.00$0.22$2.75
Azureazure$2.00$10.00$0.20$2.50
Azureazure/eu$2.20$11.00$0.22$2.75
Azureazure/us$2.20$11.00$0.22$2.75
OpenAIopenai/flex$1.00$5.00$0.10$1.25
OpenAIopenai/fast$4.00$20.00$0.40$5.00
OpenAIopenai$2.00$10.00$0.20$2.50

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 6 endpoints
P50P75P90P99
Amazon Bedrockamazon-bedrock/us-east-1
1,605–8,858.5 ms
Azureazure
2,497–15,355 ms
Azureazure/eu
3,174–8,569.84 ms
OpenAIopenai/flex
2,937–23,304.3 ms
OpenAIopenai/fast
1,816–11,870.14 ms
OpenAIopenai
1,873–30,672.85 ms
All latency percentiles 6 endpoints
EndpointP50P75P90P99
Amazon Bedrockamazon-bedrock/us-east-11,605 ms3,129.5 ms5,214 ms8,858.5 ms
Azureazure2,497 ms3,551 ms4,915 ms15,355 ms
Azureazure/eu3,174 ms4,246.5 ms6,245.6 ms8,569.84 ms
OpenAIopenai/flex2,937 ms4,382.5 ms7,018.2 ms23,304.3 ms
OpenAIopenai/fast1,816 ms3,005 ms4,703.6 ms11,870.14 ms
OpenAIopenai1,873 ms2,910.25 ms4,989.7 ms30,672.85 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints
P50P75P90P99
Amazon Bedrockamazon-bedrock/us-east-1
71–213.68 t/s
Azureazure
30–129 t/s
Azureazure/eu
86–161.52 t/s
OpenAIopenai/flex
78–144 t/s
OpenAIopenai/fast
105.5–179.43 t/s
OpenAIopenai
81–130 t/s
All throughput percentiles 6 endpoints
EndpointP50P75P90P99
Amazon Bedrockamazon-bedrock/us-east-171 t/s98 t/s117 t/s213.68 t/s
Azureazure30 t/s46 t/s73.9 t/s129 t/s
Azureazure/eu86 t/s128 t/s153.8 t/s161.52 t/s
OpenAIopenai/flex78 t/s97 t/s114 t/s144 t/s
OpenAIopenai/fast105.5 t/s132.75 t/s150 t/s179.43 t/s
OpenAIopenai81 t/s92 t/s101 t/s130 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window
Availability by endpointCurrent overlapping windows · 7 endpoints
Endpoint5 minutes30 minutes24 hours
Amazon Bedrockamazon-bedrock/us-east-1
Azureazure
Azureazure/eu
Azureazure/us
OpenAIopenai/flex
OpenAIopenai/fast
OpenAIopenai

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations
openai/gpt-6-solObserved
Benchmark profileArtificial Analysis · shared source scale from 0 to 50
Intelligence47.6

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better
gpqa diamondOpenAI: GPT-6 Sol
91.919%
tau bench verified airlineOpenAI: GPT-6 Sol
69.333%
EvaluationConfigurationSourceResultsDetails
gpqa diamondOpenAI: GPT-6 Solopenai/gpt-6-sol-20260922OpenRouter91.919%
Details
tau bench verified airlineOpenAI: GPT-6 Solopenai/gpt-6-sol-20260922OpenRouter69.333%
Details
Composite indicesGPT-6 Sol (Max)openai/gpt-6-sol-20260922Artificial AnalysisIntelligence 44.2 · Coding — · Agentic —
Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Nov 7, 2026.

Apps & session costs

Compare observed median session costs for applications using this model, grouped by conversation length.

30-day sample · through Nov 1, 2026
ApplicationModel routeTurnsMedian cost / sessionDetails
Hermes Agentopenai/gpt-6-sol-202609222–9 turns
$0.064565
Details
Hermes Agentopenai/gpt-6-sol-202609221 turn
$0.007263
Details
Codexopenai/gpt-6-sol-202609222–9 turns
$0.109515
Details
Hermes Agentopenai/gpt-6-sol-2026092250+ turns
$2.820681
Details
Codexopenai/gpt-6-sol-202609221 turn
$0.027228
Details
Codexopenai/gpt-6-sol-2026092250+ turns
$3.455206
Details
Hermes Agentopenai/gpt-6-sol-2026092210–49 turns
$0.44637
Details
Codexopenai/gpt-6-sol-2026092210–49 turns
$0.530172
Details

Source: OpenRouter, as of Nov 2, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.

Activity

Daily prompt and completion tokens reported for this model's routes in OpenRouter's top 50. Missing days have no published value.

Last 90 complete UTC days
Daily token usage3,418,937,710,816 reported tokens · 29 days with observations
Aug 9, 2026Nov 6, 2026
Daily observations · 29 days
Date (UTC)Reported tokensReported routes
Oct 26, 202657,471,723,8211
Oct 21, 202656,785,260,7151
Oct 20, 202666,286,978,3241
Oct 19, 202662,783,474,7291
Oct 18, 202657,120,379,7661
Oct 16, 202665,258,179,7361
Oct 15, 202699,853,157,3671
Oct 14, 202678,116,060,2231
Oct 13, 202667,518,774,1601
Oct 12, 202660,264,756,8001
Oct 11, 202662,628,633,0091
Oct 10, 202688,992,928,4381
Oct 9, 2026132,760,812,3891
Oct 8, 2026156,453,835,8151
Oct 7, 2026139,030,660,9301
Oct 6, 2026112,425,819,6931
Oct 5, 2026144,048,667,2341
Oct 4, 202679,301,127,4911
Oct 3, 2026157,344,216,2451
Oct 2, 2026172,659,428,8181
Oct 1, 2026125,047,551,3571
Sep 30, 2026163,697,921,3111
Sep 29, 2026221,474,173,9481
Sep 28, 2026236,333,919,1341
Sep 27, 2026139,728,899,7941
Sep 26, 2026119,384,901,2121
Sep 25, 2026166,816,404,7161
Sep 24, 2026193,889,714,2291
Sep 23, 2026135,459,349,4121

Source: OpenRouter (openrouter.ai/rankings), as of Nov 7, 2026. CC BY 4.0. Totals include only individually published routes. Tokenizers differ by provider; the aggregated “other” category is never assigned to a model.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications
openai/gpt-6-solObserved
Context
1,050,000
Maximum output
128,000
Tokenizer
GPT
Input
file, image, text
Output
text
Moderation
Yes
Added to OpenRouter
2026-09-22
Base URLhttps://openrouter.ai/api/v1
Model IDopenai/gpt-6-sol
Version IDopenai/gpt-6-sol-20260922

Reasoning

Required
No
Enabled by default
Yes
Default effort
medium
Supported efforts
max, xhigh, high, medium, low, none

Supported parameters

  • include_reasoning
  • max_completion_tokens
  • max_tokens
  • reasoning
  • reasoning_effort
  • response_format
  • seed
  • structured_outputs
  • tool_choice
  • tools
  • verbosity

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does GPT-6 Sol cost?

Listed rates start at $1.00 per million input tokens and $5.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer GPT-6 Sol?

There are 45 cataloged offers across 34 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 1,050,000 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Not reported. Structured output: Not reported. Support can vary by endpoint.

Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

  • · d98c9a5591d8
  • · 504437a71fa6