GPT-6 Sol vs GPT-6.1 Sol

As of November 10, 2026, GPT-6 Sol and GPT-6.1 Sol cost the same: $2.00 per 1M input tokens and $10.00 per 1M output tokens, and both have a 922K-token context window.

Prices from LiteLLM's price fileChecked November 10, 2026

GPT-6 Sol vs GPT-6.1 Sol side by side

Headline prices in US dollars per 1M tokens: each model's own lab where it sells it, otherwise its cheapest provider. Source: LiteLLM model price file, as of November 10, 2026.
	GPT-6 Sol	GPT-6.1 Sol
Input, per 1M tokens	$2.00	$2.00
Output, per 1M tokens	$10.00	$10.00
Cache read, per 1M tokens	$0.20	$0.10
Cache write, per 1M tokens	$2.50	$2.50
Context window	922,000 tokens	922,000 tokens
Max output	128,000 tokens	128,000 tokens
Image input	Yes	Yes
Tool calling	Yes	Yes
Structured output (JSON)	Yes	Yes
Prompt caching	Yes	Yes
Reasoning	Yes	Yes
Providers on LiteLLM	10	11
Price shown is from	OpenAI	OpenAI
Added to LiteLLM	September 22, 2026	September 29, 2026

Cheapest provider for each

GPT-6 Sol: Databricks at $2.00 input and $10.00 output per 1M tokens (databricks/databricks-gpt-6-sol)
GPT-6.1 Sol: Databricks at $2.00 input and $10.00 output per 1M tokens (databricks/databricks-gpt-6-1-sol)

Benchmark scores

From the Epoch AI Benchmarking Hub (CC BY 4.0), data as of September 29, 2026. Some results were run by Epoch and others collected by Epoch from each benchmark's own leaderboard, linked in the first column. Each model's best reported reasoning setting is shown in brackets. Higher is better. Only benchmarks with a score for both models are shown.
Benchmark	GPT-6 Sol	GPT-6.1 Sol
Overall
Epoch Capabilities Index	164.0	168.9
Coding and agents
FrontierCode	49.3% (max)	50.2% (medium)
APEX-Agents	54.3% (max)	60.0% (max)
Reasoning and knowledge
GPQA Diamond	94.3% (max)	95.4% (max)
ARC-AGI-2	89.6% (max)	94.2% (max)
SimpleQA Verified	60.7% (max)	73.9% (max)
Math
FrontierMath (tiers 1-3)	89.8% (max)	93.7% (max)
FrontierMath (tier 4)	90.0% (max)	100.0% (max)
OTIS Mock AIME 2024-2025	100.0% (max)	100.0% (max)

Call GPT-6 Sol or GPT-6.1 Sol with LiteLLM

Both use the OpenAI format through LiteLLM, so switching is a model name change. Set each provider's API key in the environment first.

Python SDK

from litellm import completion

messages = [{"role": "user", "content": "Hello!"}]

# GPT-6 Sol
response = completion(model="gpt-6-sol", messages=messages)

# GPT-6.1 Sol
response = completion(model="gpt-6.1-sol", messages=messages)

# GPT-6 Sol, falling back to GPT-6.1 Sol if the call fails
response = completion(model="gpt-6-sol", messages=messages, fallbacks=["gpt-6.1-sol"])

FAQ

Which is cheaper, GPT-6 Sol or GPT-6.1 Sol?

They cost the same: $2.00 per 1M input tokens and $10.00 per 1M output tokens, as of November 10, 2026.

Which has the larger context window, GPT-6 Sol or GPT-6.1 Sol?

Both have a 922,000-token context window.

Can I switch from GPT-6 Sol to GPT-6.1 Sol without changing my code?

Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "gpt-6-sol" to "gpt-6.1-sol", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.