openai/gpt-6.1-sol

Model release OpenRouter 模型 Source language: Chinese

OpenRouter 于 2026-09-30 收录该模型(收录时间不等于模型正式发布日期);上下文:1,050,000 tokens;输入价:$2.0000/百万 tokens;输出价:$10.0000/百万 tokens;定位(来源描述):GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in…

Full text

OpenAI: GPT-6.1 Sol

openai/gpt-6.1-sol

Compare

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 work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost. Compared with GPT-6 Sol, it makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic tasks.

Modalities

In / out price

$2 / $10per 1M

Context

1.1M

Released

Sep 29, 2026

Compare

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput

$2.00$10.00$0.103.02s60 tok/s

99.96%

$2.00$10.00$0.102.70s43 tok/s

100.00%

$2.00$10.00$0.103.81s36 tok/s

99.72%

Not used in Standard routing:Why these endpoints are not used

Flex

$1.00$5.00$0.0513.15s19 tok/s

100.00%

$2.20$11.00$0.113.83s47 tok/s

100.00%

$2.20$11.00$0.112.40s31 tok/s

99.89%

$2.20$11.00$0.116.18s35 tok/s

100.00%

Fast

$4.00$20.00$0.201.57s65 tok/s

100.00%

Ultrafast

$12.00$60.00$0.601.54s237 tok/s

100.00%

ProviderInput / Output /M

Input $2.00 / Output $10.00

60 tok/s99.96% uptime

Input $2.00 / Output $10.00

43 tok/s100.00% uptime

Input $2.00 / Output $10.00

36 tok/s99.72% uptime

Not used in Standard routing:Why these endpoints are not used

Input $1.00 / Output $5.00

Flex

19 tok/s100.00% uptime

Input $2.20 / Output $11.00

47 tok/s100.00% uptime

Input $2.20 / Output $11.00

31 tok/s99.89% uptime

Input $2.20 / Output $11.00

35 tok/s100.00% uptime

Input $4.00 / Output $20.00

Fast

65 tok/s100.00% uptime

Input $12.00 / Output $60.00

Ultrafast

237 tok/s100.00% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.5611/M tokens

Output

$10.12/M tokens

GPT-6.1 Sol — Price history

Price history

No effective price data for this selection

$0.570$10.0080.4%15.1%

$0.575$10.0280.2%70.3%

$0.781$10.0071.3%6.1%

Not used in Standard routing:Why these endpoints are not used

Flex

$0.220$5.0085.8%7.0%

$0.224$11.0095.6%0.9%

Fast

$0.351$20.0096.9%0.5%

$2.743$11.000.0%0.1%

Ultrafast

$14.998$60.000.0%0.0%

————

ProviderInput / Output /M

Token share

Effective in $0.570 / Effective out $10.00

Token share

15.1%

Effective in $0.575 / Effective out $10.02

Token share

70.3%

Effective in $0.781 / Effective out $10.00

Token share

6.1%

Not used in Standard routing:Why these endpoints are not used

Effective in $0.220 / Effective out $5.00

FlexToken share

7.0%

Effective in $0.224 / Effective out $11.00

Token share

0.9%

Effective in $0.351 / Effective out $20.00

FastToken share

0.5%

Effective in $2.743 / Effective out $11.00

Token share

0.1%

Effective in $14.998 / Effective out $60.00

UltrafastToken share

0.0%

Effective in — / Effective out —

Token share —

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

237tok/s

P50, best across providers

Latency

1.54s

P50, best provider

Reasoning effortLatency / throughput

AutoExacto benchmarks

GPQA DiamondTAU-BenchAmazon Bedrock94.8%68.7%

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)The model was reachable. Request routed to a provider.

99.99%

Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.

98.90%

Availability over the last 3 days

Last 72 hours

Availability 98.90%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.69%

Without Routing

98.74%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for OpenAI: GPT-6.1 Sol (Artificial Analysis, Design Arena and Vals AI)

SourceBenchmarkScore

Artificial AnalysisGPT-6.1 Sol (Xhigh) Intelligence Index52.5

Artificial AnalysisGPT-6.1 Sol (Xhigh) HLE52.6%

Artificial AnalysisGPT-6.1 Sol (Xhigh) AA-LCR79.7%

Artificial AnalysisGPT-6.1 Sol (Xhigh) GDPval-AA53.1%

Artificial AnalysisGPT-6.1 Sol (Xhigh) CritPt31.7%

Artificial AnalysisGPT-6.1 Sol (Xhigh) SciCode55.7%

Artificial AnalysisGPT-6.1 Sol (Xhigh) Terminal-Bench 4.054.0%

Artificial AnalysisGPT-6.1 Sol (Xhigh) AA-Omniscience Accuracy61.1%

Artificial AnalysisGPT-6.1 Sol (Xhigh) AA-Omniscience Non-Hallucination Rate52.0%

Artificial AnalysisGPT-6.1 Sol (Low) Intelligence Index34.8

Artificial AnalysisGPT-6.1 Sol (Low) HLE47.4%

Artificial AnalysisGPT-6.1 Sol (Low) AA-LCR84.0%

Artificial AnalysisGPT-6.1 Sol (Low) GDPval-AA41.1%

Artificial AnalysisGPT-6.1 Sol (Low) CritPt24.9%

Artificial AnalysisGPT-6.1 Sol (Low) SciCode53.2%

Artificial AnalysisGPT-6.1 Sol (Low) Terminal-Bench 4.030.8%

Artificial AnalysisGPT-6.1 Sol (Low) AA-Omniscience Accuracy58.6%

Artificial AnalysisGPT-6.1 Sol (Low) AA-Omniscience Non-Hallucination Rate50.1%

Artificial AnalysisGPT-6.1 Sol (High) Intelligence Index50.3

Artificial AnalysisGPT-6.1 Sol (High) HLE51.4%

Artificial AnalysisGPT-6.1 Sol (High) AA-LCR82.3%

Artificial AnalysisGPT-6.1 Sol (High) GDPval-AA51.1%

Artificial AnalysisGPT-6.1 Sol (High) CritPt30.0%

Artificial AnalysisGPT-6.1 Sol (High) SciCode55.8%

Artificial AnalysisGPT-6.1 Sol (High) Terminal-Bench 4.051.5%

Artificial AnalysisGPT-6.1 Sol (High) AA-Omniscience Accuracy60.4%

Artificial AnalysisGPT-6.1 Sol (High) AA-Omniscience Non-Hallucination Rate51.0%

Artificial AnalysisGPT-6.1 Sol (Max) Intelligence Index54.6

Artificial AnalysisGPT-6.1 Sol (Max) HLE52.9%

Artificial AnalysisGPT-6.1 Sol (Max) AA-LCR83.0%

Artificial AnalysisGPT-6.1 Sol (Max) GDPval-AA55.4%

Artificial AnalysisGPT-6.1 Sol (Max) CritPt31.7%

Artificial AnalysisGPT-6.1 Sol (Max) SciCode54.2%

Artificial AnalysisGPT-6.1 Sol (Max) Terminal-Bench 4.056.1%

Artificial AnalysisGPT-6.1 Sol (Max) AA-Omniscience Accuracy61.8%

Artificial AnalysisGPT-6.1 Sol (Max) AA-Omniscience Non-Hallucination Rate48.1%

Artificial AnalysisGPT-6.1 Sol (Medium) Intelligence Index46.3

Artificial AnalysisGPT-6.1 Sol (Medium) HLE49.9%

Artificial AnalysisGPT-6.1 Sol (Medium) AA-LCR83.3%

Artificial AnalysisGPT-6.1 Sol (Medium) GDPval-AA48.2%

Artificial AnalysisGPT-6.1 Sol (Medium) CritPt27.7%

Artificial AnalysisGPT-6.1 Sol (Medium) SciCode53.2%

Artificial AnalysisGPT-6.1 Sol (Medium) Terminal-Bench 4.048.0%

Artificial AnalysisGPT-6.1 Sol (Medium) AA-Omniscience Accuracy59.6%

Artificial AnalysisGPT-6.1 Sol (Medium) AA-Omniscience Non-Hallucination Rate51.9%

Design ArenaGPT-6.1 Sol Agents Arena Androidnative Elo1195

Design ArenaGPT-6.1 Sol Agents Arena Blender3d Elo1267

Design ArenaGPT-6.1 Sol Agents Arena Codetovideo Elo1195

Design ArenaGPT-6.1 Sol Agents Arena Mobile Apps Elo1227

Design ArenaGPT-6.1 Sol Agents Arena Pdf Elo1133

Design ArenaGPT-6.1 Sol Agents Arena Spreadsheet Elo1223

Design ArenaGPT-6.1 Sol Agents Arena Webapps Elo1279

Design ArenaGPT-6.1 Sol Models Arena 3D Elo1426

Design ArenaGPT-6.1 Sol Models Arena Code Categories Elo1361

Design ArenaGPT-6.1 Sol Models Arena Data Visualization Elo1278

Design ArenaGPT-6.1 Sol Models Arena Game Development Elo1404

Design ArenaGPT-6.1 Sol Models Arena SVG Elo1343

Design ArenaGPT-6.1 Sol Models Arena UI Component Elo1357

Design ArenaGPT-6.1 Sol Models Arena Website Elo1315

Vals AIGPT-6.1 Sol Access to Justice Benchmark65.8%

Vals AIGPT-6.1 Sol BioMysteryBench79.6%

Vals AIGPT-6.1 Sol ClaimBench100.0%

Vals AIGPT-6.1 Sol Code Migration v1.177.3%

Vals AIGPT-6.1 Sol CyberBench v1.139.3%

Vals AIGPT-6.1 Sol EMB v1.171.1%

Vals AIGPT-6.1 Sol Finance Agent v2.161.8%

Vals AIGPT-6.1 Sol Vals Finance Index55.8%

Vals AIGPT-6.1 Sol Financial Coaching Bench68.5%

Vals AIGPT-6.1 Sol HLAB-Vals-1.16.3%

Vals AIGPT-6.1 Sol Immigration67.8%

Vals AIGPT-6.1 Sol IOI96.9%

Vals AIGPT-6.1 Sol Vals Legal Index68.7%

Vals AIGPT-6.1 Sol Legal Research Bench38.5%

Vals AIGPT-6.1 Sol MedCode48.8%

Vals AIGPT-6.1 Sol MedScribe86.5%

Vals AIGPT-6.1 Sol MysteryMechanism46.4%

Vals AIGPT-6.1 Sol ProgramBench3.0%

Vals AIGPT-6.1 Sol ProofBench v1.199.0%

Vals AIGPT-6.1 Sol Public Benefits Bench v1.159.3%

Vals AIGPT-6.1 Sol Robo-bench28.3%

Vals AIGPT-6.1 Sol Vals RSI Index26.6%

Vals AIGPT-6.1 Sol SAGE90.5%

Vals AIGPT-6.1 Sol Vals Science Index59.6%

Vals AIGPT-6.1 Sol SRE Bench50.8%

Vals AIGPT-6.1 Sol SWE-bench Multimodal43.5%

Vals AIGPT-6.1 Sol Tax Agent Bench21.8%

Vals AIGPT-6.1 Sol Terminal-Bench 4.055.1%

Vals AIGPT-6.1 Sol Terminal-Bench-Science52.9%

Vals AIGPT-6.1 Sol Vals Index63.9%

Vals AIGPT-6.1 Sol Vibe Code Bench v1.188.9%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

1.

Codex

A coding agent that helps you build and ship with AI

3.3Ttokens

2.

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

398Btokens

3.

pi

There are many coding agents, but this one is yours.

350Btokens

4.

Descript

AI Video & Podcast Editor

301Btokens

5.

omp

new

256Btokens

Rest of OpenRouter

512M

Top 5 Apps

160M

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

OpenAI: GPT Sol versions

Available through EU in-region routing

OpenAI: GPT-6.1 Sol is available through EU in-region routing. Requests sent to eu.openrouter.ai are decrypted in the EU and routed only to shared provider endpoints in Europe (the EU/EEA, the UK, and Switzerland).

Providers in EuropeAzurePrices in Europe

Azure: $2.20/M tokens input, $11/M tokens output

Base URLhttps://eu.openrouter.ai/api/v1PlanRequires Business or Enterprise. Self-serve on Business: no contract, no monthly minimum. OpenRouter Business for EU in-region routing

Fails closed: if no shared provider endpoint in Europe is available, the request errors instead of leaving the region. Requests served by your own BYOK key go to your deployment’s region, which you control. In-region routing docs

Documentation

Guides, cookbooks, blog posts, and tools for building with OpenAI: GPT-6.1 Sol on OpenRouter.

Reranking in RAG: How to Fix Bad Retrieval with a RerankerBlog post

How to Benchmark LLMsBlog post

Frequently asked questions

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 work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost.

The GPT-6.1 Sol documentation on OpenRouter includes the Reranking in RAG: How to Fix Bad Retrieval with a Reranker blog post and the How to Benchmark LLMs blog post. The quickstart covers API keys and your first request, and the API reference lists every parameter.

GPT-6.1 Sol costs $2.00/M input tokens and $10.00/M output tokens, with separate rates for Cache Read at $0.10/M tokens and Cache Write at $2.50/M tokens.

GPT-6.1 Sol has a 1,050,000 token context window. It supports up to 128,000 completion tokens.

Yes. GPT-6.1 Sol accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Yes. OpenAI caches prompts of 1024 tokens or more automatically, and GPT-6.1 Sol bills a cache write on each cached prompt whether or not the cached prefix is read again. To turn caching off for a request, set prompt_cache_options.mode to "explicit" at the request root and do not mark any content block with prompt_cache_breakpoint. Explicit mode disables OpenAI-managed breakpoints, so a request with none of your own has no cacheable prefix and is billed at the plain input rate. See the prompt caching guide.

GPT-6.1 Sol accepts files such as PDFs, images, and text as input and returns text.

GPT-6.1 Sol is served by 3 providers on OpenRouter: OpenAI, Amazon Bedrock, and Azure. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

GPT-6.1 Sol was released on September 29, 2026.

Sources

← Back to the daily brief