GPT-6.1 Sol
GPT-6.1 Sol is OpenAI's current Sol model, positioned as near-Astra performance for complex work at a lower cost than Astra.
Provider
OpenAI
Model family
OpenAI GPT
Multimodal LLM
Cost tier
Sol
Status
Current
Why teams choose it
OpenAI's latest-model guide says to start with Astra
GPT-6.1 Sol, or Luna, and to review the migration notes before switching an existing gpt-6-sol integration.
Reasoning effort is low, medium (default), high, xhigh, or max
none and minimal are not supported. Tool calling requires the Responses API; Chat Completions is supported without tool calling.
Cached input is 5% of uncached input, and cache writes are 1.25× uncached input
Prompts above 272K input tokens are billed at 2× input and cache and 1.5× output for the full request.
Fast mode is 2× Standard. Batch and Flex are 50% of Standard. Regional processing is a
10% premium where available. Fast mode is unavailable with EU data residency.
Tradeoffs to know
- Standard input and output list prices match GPT-6 Sol at $2 and $10. The documented savings versus Sol are on cached input ($0.10 versus $0.20), not a lower uncached sticker price.
- Audio and video are not supported. The free API tier is not supported. Fine-tuning is not supported.
When not to use this
- No independent benchmark scores are published on the model card. Do not copy Astra or GPT-6 Sol scores onto GPT-6.1 Sol.
Technical specs
- Inputs
- text, image
- Outputs
- text
- Capabilities
- complex work, reasoning, tool use, vision, code interpreter, computer use
- License
- Proprietary API
- API ID
gpt-6.1-sol- Source
- https://developers.openai.com/api/docs/models/gpt-6.1-sol
- Context tokens
- 1,050,000
- Knowledge Cutoff
- 2026-04-30
- Max output tokens
- 128,000
- Input Usd Per Million
- 2
- Output Usd Per Million
- 10
- Cache Write Usd Per Million
- 2.5
- Cached Input Usd Per Million
- 0.1
Benchmarks
No independent or vendor benchmark scores in this catalog entry.
OpenAI GPT family lineup
Current models
Previous versions
Related models
GPT-6.1 Sol FAQ
What is GPT-6.1 Sol?
GPT-6.1 Sol is OpenAI's current Sol model, positioned as near-Astra performance for complex work at a lower cost than Astra. The API ID is gpt-6.1-sol. It accepts text and image input, returns text, and has a 1,050,000-token context window, 128,000 max output, and a knowledge cutoff of April 30, 2026. Standard price is $2 input, $0.10 cached input, $2.50 cache writes, and $10 output per million tokens.
When does GPT-6.1 Sol fit best?
Complex coding and agent work below Astra's list price
What should teams watch out for with GPT-6.1 Sol?
Standard input and output list prices match GPT-6 Sol at $2 and $10. The documented savings versus Sol are on cached input ($0.10 versus $0.20), not a lower uncached sticker price.
Explore next
Models, tools, and comparisons that connect to this reference.