---
title: "GPT-6.1 Sol API: facts and benchmarks | Kendr"
canonical: "https://kendr.org/models/kc-gpt-6.1-sol"
date_modified: "2026-10-13"
profile_kind: "hosted"
---

# GPT-6.1 Sol API model profile

GPT-6.1 Sol is a OpenAI model profile with a 1,050,000-token context window. The dated catalog snapshot records file, image, text modalities and interfaces for agentic, coding, file input, prompt caching, reasoning.

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.

GPT-6.1 Sol is worth reaching for when you need a route scoring in the top quarter on the published intelligence index and carrying one of the widest context windows in the catalog. The conditions below are the ones its own numbers support.

GPT-6.1 Sol is available under the Kendr alias kc-gpt-6.1-sol. Current account availability and customer credit quotes come from Kendr's live public model API and applicable account policy.

GPT-6.1 Sol accepts file, image, and text and returns text. The snapshot records agentic, coding, file input, prompt caching, reasoning, reasoning controls, structured output, text generation, tool calling, tools, vision, web search, and web search pricing as capabilities or interfaces.

The dated reference snapshot lists $1 input and $5 output per million tokens. Cached input is $0.05 per million tokens. The separately published provider-route reference is $2 / $10 (Standard global inference, ≤272K input; $0.10/M cache read; live route quote applies).

The 2026-10-13 snapshot includes 1 Artificial Analysis index, 6 Design Arena categories, and AutoExacto results for 6 provider observations. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable.

GPT-6.1 Sol ranked #16 in the cited trailing-7-day third-party catalog usage dataset as of 2026-10-13. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share.

Profile data was reviewed for the 2026-10-13 snapshot. Claims retain their source dates, and unavailable fields are shown as unavailable instead of estimated.

## Profile facts

- **Profile type:** Kendr API model
- **Kendr API alias:** kc-gpt-6.1-sol
- **Model developer:** OpenAI
- **Kendr route provider:** OpenAI
- **Context window:** 1M
- **Snapshot date:** 2026-10-13
- **Knowledge cutoff:** Not disclosed
- **Reference catalog ID:** openai/gpt-6.1-sol

## When to pick GPT-6.1 Sol

GPT-6.1 Sol is worth reaching for when you need a route scoring in the top quarter on the published intelligence index and carrying one of the widest context windows in the catalog. The conditions below are the ones its own numbers support.

Each condition below is derived from this model's own values in the 2026-10-13 snapshot, compared only against models publishing the same field.

- Reach for it when a whole corpus has to fit in one prompt. The 1.05M-token context window is in the top quarter of the 167 models publishing a limit here, so long documents can go in whole rather than chunked.
- Reach for it when answer quality matters more than unit cost. It scores 51.8 on the Artificial Analysis intelligence index, above three quarters of the 119 models carrying that field in the 2026-10-13 snapshot.
- Reach for it when the input includes images. The snapshot records image input, so screenshots, scans, and diagrams can be sent directly instead of described.
- Reach for it when the model has to call tools. Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose.
- Look elsewhere when the request is trivial and latency-sensitive. Reasoning is mandatory on this route and cannot be turned off, so short factual requests still pay reasoning tokens and reasoning latency.

## Context, modalities, and identity

GPT-6.1 Sol accepts file, image, and text and returns text. The snapshot records agentic, coding, file input, prompt caching, reasoning, reasoning controls, structured output, text generation, tool calling, tools, vision, web search, and web search pricing as capabilities or interfaces.

- **Model developer:** OpenAI
- **Kendr route provider:** OpenAI
- **Context window:** 1M
- **Maximum output:** 128,000 tokens
- **Input modalities:** file, image, and text
- **Output modalities:** text
- **Knowledge cutoff:** Not disclosed

## Model overview

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.

- **Reference model ID:** openai/gpt-6.1-sol
- **Canonical version:** openai/gpt-6.1-sol-20260929
- **Hugging Face ID:** Not separately documented

## Capabilities and supported controls

Capabilities and parameters are reported from the dated catalog and source records; their presence does not guarantee identical behavior across every provider route.

- **Supported parameters:** include_reasoning, max_completion_tokens, max_tokens, reasoning, reasoning_effort, response_format, seed, structured_outputs, tool_choice, tools, verbosity

- agentic
- coding
- file input
- prompt caching
- reasoning
- reasoning controls
- structured output
- text generation
- tool calling
- tools
- vision
- web search
- web search pricing

## Dated pricing snapshot

The dated reference snapshot lists $1 input and $5 output per million tokens. Cached input is $0.05 per million tokens. The separately published provider-route reference is $2 / $10 (Standard global inference, ≤272K input; $0.10/M cache read; live route quote applies).

Reference figures are dated 2026-10-13; the live Kendr quote can differ by selected provider route, context tier, caching, tools, region, and current rate card.

- **Price date:** 2026-10-13
- **Input:** $1 per 1M tokens
- **Cached input:** $0.05 per 1M tokens
- **Output:** $5 per 1M tokens

| Prompt threshold | Input | Cached input | Output |
| --- | --- | --- | --- |
| From 272,000 prompt tokens | $4 / 1M | $0.2 / 1M | $15 / 1M |

## Provider routes, performance, and uptime

The snapshot retains 8 provider endpoints. Provider prices, context limits, p50 performance, and uptime can differ by route and are not Kendr guarantees.

- **Active provider endpoints:** 8
- **Best p50 latency:** 1.84 s
- **Best p50 throughput:** 83 tok/s
- **Availability with routing:** 95.16% over the sampled window
- **Availability without routing:** 92.34% over the sampled window
- **Performance date:** 2026-10-13

| Provider | Quantization | Input / 1M | Output / 1M | Cache read / 1M | Context | p50 latency | p50 throughput | Uptime (1d) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| OpenAI | unknown | $1 / 1M | $5 / 1M | $0.05 / 1M | 1,050,000 tokens | 10.38 s | 30 tok/s | 96.03% |
| Azure | unknown | $2 / 1M | $10 / 1M | $0.1 / 1M | 1,050,000 tokens | 11.57 s | 33 tok/s | 100.00% |
| OpenAI | unknown | $2 / 1M | $10 / 1M | $0.1 / 1M | 1,050,000 tokens | 7.32 s | 38 tok/s | 100.00% |
| Amazon Bedrock | unknown | $2.2 / 1M | $11 / 1M | $0.11 / 1M | 1,050,000 tokens | 6.30 s | 44 tok/s | 100.00% |
| Azure | unknown | $2.2 / 1M | $11 / 1M | $0.11 / 1M | 1,050,000 tokens | 5.91 s | 36 tok/s | 100.00% |
| Azure | unknown | $2.2 / 1M | $11 / 1M | $0.11 / 1M | 1,050,000 tokens | 4.68 s | 28 tok/s | 100.00% |
| OpenAI | unknown | $4 / 1M | $20 / 1M | $0.2 / 1M | 1,050,000 tokens | 3.06 s | 65 tok/s | 100.00% |
| OpenAI | unknown | $12 / 1M | $60 / 1M | $0.6 / 1M | 1,050,000 tokens | 1.84 s | 83 tok/s | 100.00% |

## Benchmark evidence and limitations

The 2026-10-13 snapshot includes 1 Artificial Analysis index, 6 Design Arena categories, and AutoExacto results for 6 provider observations. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable.

Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.

- **Intelligence Index:** 51.8
- **AutoExacto coverage:** 6 provider observations over 32 days

| Design Arena category | Elo | Win rate | Rank |
| --- | --- | --- | --- |
| 3d | 1476 | 73.5% | #3 |
| codecategories | 1343 | 58.2% | #5 |
| dataviz | 1322 | 57.4% | #10 |
| gamedev | 1379 | 62.2% | #4 |
| uicomponent | 1352 | 59.7% | #4 |
| website | 1319 | 55.7% | #6 |

## AutoExacto provider benchmarks

Rolling provider observations from the cited third-party benchmark view. The lookback is 32 days; GPQA Diamond and TAU-Bench Airline measure different abilities and should not be blended into one score.

| Provider | GPQA Diamond | TAU-Bench Airline | Runs |
| --- | --- | --- | --- |
| Amazon Bedrock | 94.78% | 72.67% | 1 |
| auto-routing | 94.44% | 70% | 1 |
| Azure | 93.34% | 68.34% | 2 |
| Azure | 93.94% | 67.7% | 2 |
| Azure | 94.2% | 68.98% | 2 |
| OpenAI | 94.44% | 68.25% | 3 |

## Popularity and market context

GPT-6.1 Sol ranked #16 in the cited trailing-7-day third-party catalog usage dataset as of 2026-10-13. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share.

- **Third-party catalog rank:** #16
- **Global market share:** Not inferred
- **Observation date:** 2026-10-13

## OpenAI-compatible API example

```bash
curl https://api.kendr.org/v1/chat/completions \
  -H "Authorization: Bearer $KENDR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"kc-gpt-6.1-sol","messages":[{"role":"user","content":"Hello"}]}'
```

## Frequently asked questions

### When should I use GPT-6.1 Sol?

GPT-6.1 Sol is worth reaching for when you need a route scoring in the top quarter on the published intelligence index and carrying one of the widest context windows in the catalog. The conditions below are the ones its own numbers support. Reach for it when a whole corpus has to fit in one prompt: The 1.05M-token context window is in the top quarter of the 167 models publishing a limit here, so long documents can go in whole rather than chunked. Reach for it when answer quality matters more than unit cost: It scores 51.8 on the Artificial Analysis intelligence index, above three quarters of the 119 models carrying that field in the 2026-10-13 snapshot. Reach for it when the input includes images: The snapshot records image input, so screenshots, scans, and diagrams can be sent directly instead of described. Reach for it when the model has to call tools: Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose. Look elsewhere when the request is trivial and latency-sensitive: Reasoning is mandatory on this route and cannot be turned off, so short factual requests still pay reasoning tokens and reasoning latency.

### What is GPT-6.1 Sol?

GPT-6.1 Sol is a OpenAI model profile with a 1,050,000-token context window. The dated catalog snapshot records file, image, text modalities and interfaces for agentic, coding, file input, prompt caching, reasoning.

### What context window does GPT-6.1 Sol have?

The dated profile lists 1M of context and up to 128,000 output tokens. Provider routes, variants, and runtime configuration can impose lower effective limits.

### What benchmark evidence is available for GPT-6.1 Sol?

The 2026-10-13 snapshot includes 1 Artificial Analysis index, 6 Design Arena categories, and AutoExacto results for 6 provider observations. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable. Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.

### What is the Kendr API alias for GPT-6.1 Sol?

Use kc-gpt-6.1-sol as the model value. The live public model API and signed-in catalog remain authoritative for route availability and customer credit quotes.

### How is GPT-6.1 Sol priced on Kendr?

The dated reference snapshot lists $1 input and $5 output per million tokens. Cached input is $0.05 per million tokens. The separately published provider-route reference is $2 / $10 (Standard global inference, ≤272K input; $0.10/M cache read; live route quote applies). Kendr applies one 5% markup to configured provider model cost; the live quote and settled routing receipt are authoritative for a request.

## Sources and evidence dates

- [GPT-6.1 Sol third-party catalog record](https://openrouter.ai/openai/gpt-6.1-sol) — catalog, checked 2026-10-13
- [Third-party model catalog methodology](https://openrouter.ai/docs/guides/overview/models) — methodology, checked 2026-10-13
- [OpenAI official model documentation](https://developers.openai.com/api/docs/models) — primary, checked 2026-10-13
- [Artificial Analysis capability indices methodology](https://artificialanalysis.ai/methodology/capability-indices) — benchmark, checked 2026-10-13
- [Design Arena leaderboard and methodology](https://www.designarena.ai/leaderboard) — benchmark, checked 2026-10-13
- [GPT-6.1 Sol third-party catalog record](https://openrouter.ai/blog/announcements/auto-exacto/) — benchmark, checked 2026-10-13
- [GPT-6.1 Sol provider or route reference](https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html) — primary, checked 2026-10-13

Live Kendr operational availability is published separately at https://api.kendr.org/api/public/models.