OpenAI Releases GPT-6.1 Sol: Mid-Tier Model with 1.1M Context at $2/$10 per Million Tokens
OpenAI has released GPT-6.1 Sol, an incremental upgrade to GPT-6 Sol positioned below flagship GPT-6 Astra in its GPT-6 lineup. The model features a 1.1M token context window, priced at $2 per 1M input tokens and $10 per 1M output tokens, with claimed improvements in factual accuracy and instruction-following on agentic tasks.
GPT-6.1 Sol — Quick Specs
OpenAI has released GPT-6.1 Sol, an updated version of GPT-6 Sol that sits below the flagship GPT-6 Astra in the company's GPT-6 model series. The model became available September 29, 2026, according to OpenRouter listings.
GPT-6.1 Sol offers a 1.1 million token context window and is priced at $2 per 1M input tokens and $10 per 1M output tokens through standard OpenAI routing. A "Flex" tier is available at $1/$5 per 1M tokens with higher latency, while a "Fast" tier costs $4/$20 per 1M tokens for lower-latency responses. Cached input tokens are priced at $0.10 per 1M across most endpoints.
According to OpenAI, the model is designed for agentic coding, computer use, document-heavy professional work, and multi-step business workflow automation. The company claims GPT-6.1 Sol approaches the performance of the higher-tier GPT-6 Astra on these tasks at substantially lower cost. Compared to its predecessor GPT-6 Sol, OpenAI states the new version makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic operations. No independent benchmark scores were disclosed alongside the release.
A "Pro" variant, GPT-6.1 Sol Pro, is also available, using the same underlying weights but with reasoning.mode set to "pro" for higher-quality outputs on complex problems. OpenAI notes this mode consumes significantly more reasoning tokens per request, making typical costs several times higher than standard GPT-6.1 Sol, with correspondingly longer completion times. OpenAI recommends the Pro mode only for hard, high-stakes problems, directing everyday coding and chat workloads to the standard model.
Performance data from OpenRouter shows median latency of 1.96 seconds and throughput of 42 tokens per second on OpenAI's own infrastructure for standard requests, with the Fast tier reaching 95 tokens per second at 0.81 seconds median latency. Uptime across providers was reported at 100% for OpenAI-hosted endpoints over the measurement window, with overall OpenRouter availability at 99.71% over the trailing 24 hours.
GPT-6.1 Sol fits into a broader GPT-6 family that includes the flagship GPT-6 Astra, the mid-tier GPT-6 Sol, and the fast, lower-cost GPT-6 Luna, priced at $0.10/$0.50 per 1M tokens. All models in the family share a 1.1M token context window and reportedly carry over gains in factual reliability and communication clarity that OpenAI attributes to the GPT-6 architecture generally.
What this means: GPT-6.1 Sol represents an incremental version bump rather than a new architecture, targeting the same use cases as GPT-6 Sol with claimed reliability improvements rather than headline capability jumps. The pricing structure — offering Flex, Standard, and Fast tiers at different cost/latency tradeoffs — signals OpenAI's continued push toward flexible serving options for agentic and enterprise workloads where cost sensitivity varies by task. Without independently verified benchmark scores, buyers evaluating this model against GPT-6 Sol or competing mid-tier models will need to run their own evaluations to confirm the claimed accuracy and instruction-following gains before migrating production workloads.
Related Articles
OpenAI publishes startup guide for GPT-6 family covering model choice, reasoning effort and tool coordination
OpenAI has published "A model guide for the GPT-6 family," a practical guide aimed at startups. It covers choosing GPT-6 models, tuning reasoning effort, improving prompts and skills, coordinating tools, and preparing workflows for production. The summary gives no pricing, context window or benchmark figures.
OpenAI publishes startup guide to choosing and deploying GPT-6 models, with reasoning-effort tuning
OpenAI has published a practical guide for startups building on the GPT-6 family. It covers model selection, reasoning effort, prompts and skills, tool coordination, and production workflows. The available summary discloses no pricing, context window, or benchmark figures.
GPT-6 Astra Ultrafast Claims Up to 8x Faster Token Generation on NVIDIA Blackwell GPUs
GPT-6 Astra Ultrafast, running on NVIDIA Blackwell GPUs, is available now in the OpenAI API and to eligible ChatGPT Work and Codex users. NVIDIA says it generates tokens up to 8x faster than Astra Standard mode. Pricing and context window details were not disclosed in the source.
Google unveils Gemini 4 Argon at $2/$10 per 1M tokens, but access is limited to select users
Google unveiled Gemini 4 Argon on Wednesday with introductory pricing of $2 per 1M input tokens and $10 per 1M output tokens, matching OpenAI's discounted GPT-6.1 Sol. Access is restricted to select cybersecurity defenders and enterprise cloud customers, and Google says published rates will double later.
Comments
Loading...