OpenAI: GPT-5.6
GPT-5.6 is a reasoning model from OpenAI released on Jul 9, 2026. It reads text, images and files and writes text, with a 1.05M token context window and up to 128K tokens per reply.
Show moreShow less
It costs $4 per million input tokens and $20 per million output tokens. Cached input bills at $0.40, 90% less than fresh input.
It supports tool calling, structured JSON output and prompt caching.
41 providers serve it, including Azure, Amazon Bedrock and Databricks. The lowest input price is $1.50 per million tokens at Xpersona.
- Modalities
- In / out price
- $4 / $20 per 1M
- Context
- 1.05M
- Max output
- 128K
- Released
- Jul 9, 2026
- Knowledge cutoff
- Feb 2026
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
GPT-5.6 pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $4 / 1M tokens | |
|---|---|---|
| Output | $20 / 1M tokens | |
| Cached input (read) | $0.40 / 1M tokens | 90% off input |
| Cache write | $5 / 1M tokens | |
| Prompts over 200K | $8 in, $30 out | long context rate |
| Prompts over 272K | $8 in, $30 out | long context rate |
GPT-5.6 providers
41 providers serve it, including Azure, Amazon Bedrock and Databricks. The lowest input price is $1.50 per million tokens at Xpersona. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| OpenAI First party | $4 | $20 | $0.40 | 1.05M | 128K |
| Azure | $4 | $20 | $0.50 | 1.05M | 128K |
| Amazon Bedrock | $4.40 | $22 | $0.44 | 1.05M | 128K |
| Databricks | $5 | $30 | $0.50 | 1.05M | 128K |
| Vercel AI Gateway | $8 | $40 | $0.80 | 1.05M | 128K |
| Snowflake Cortex | n/a | n/a | – | 1.05M | 128K |
| Xpersona | $1.50 | $12 | $0.15 | 372K | 128K |
| Cloudflare AI Gateway | $2 | $10 | $0.25 | 1.05M | 128K |
| NanoGPT | $2 | $10 | $0.20 | 1.05M | 128K |
| Infer by Flow7 | $2.50 | $12.50 | $0.25 | 272K | 128K |
| Ofox | $2.50 | $15 | $0.25 | 1.05M | 128K |
| routing.run | $2.50 | $15 | – | 1M | 128K |
Showing 12 of 41 providers: the lab first, then the major clouds, then the cheapest resellers.
What GPT-5.6 costs per month
Pick a workload close to yours or type your own volumes.
Independent benchmarks
Measured by third parties, not reported by OpenAI. Each links to its source and shows the date I checked it.
Human preference: people compare two anonymous answers and pick the better one. Ratings from the Text Arena overall board, style control on.
Arena (formerly LMArena), checked Oct 10, 2026
Agentic coding in a real terminal: can the model, driving an agent harness, finish multi step software and ops tasks. Resolution rate.
Terminal-Bench, checked Oct 10, 2026
Abstract reasoning on visual puzzles the model has not seen, semi private set. Hard to memorise, so it tracks reasoning more than knowledge.
ARC Prize, checked Oct 10, 2026
Expert level questions across many fields, no tools allowed. The Diamond set is 1,000 questions. Few models are on it yet.
Scale Labs, checked Oct 10, 2026
Benchmarks OpenAI reports (17)
- swe-bench-pro (SWE-Bench Pro)64.6%
- terminal-bench-2-1 (Terminal-Bench 2.1 (single agent))88.8%
- terminal-bench-4 (Terminal-Bench 4.0)37.3%
- deepswe-v1-1 (DeepSWE v1.1)72.7%
- gpqa-diamond (GPQA Diamond)94.6%
- agents-last-exam (Agents' Last Exam (launch table))52.7%
- gdpval-aa-v2 (GDPval-AA v2)1747.8
- osworld-2-0 (OSWorld 2.0 (launch table, July 2026))62.6%
- browsecomp (BrowseComp (single agent))90.4%
- mmmu-pro (MMMU Pro (no tools))83%
- frontiermath-tier-4 (FrontierMath Tier 4 (v2))83%
- arc-agi-3 (ARC-AGI-3)7.78%
- arc-agi-2 (ARC-AGI-2)92.5%
- mrcr-v2 (OpenAI MRCR v2 8-needle 512K-1M)73.8%
- automationbench (AutomationBench)18.1%
- aa-intelligence-index (Artificial Analysis Intelligence Index v4.1, as reported by OpenAI)58.9
- aa-coding-agent-index (Artificial Analysis Coding Agent Index v1.1, max reasoning, as reported by OpenAI)80
Labs pick their own settings and harnesses, so compare these only within one lab.
Supported request parameters
What you can set when you call GPT-5.6 through an OpenAI compatible API.
- Tools
tools - Structured outputs
structured_outputs - Reasoning
reasoning
Alternatives to GPT-5.6
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- Index 57.6
Reads text, images and files. Tool calling, structured output, reasoning. Served by 28 providers.
by anthropicSep 18, 20261M context$4/M input tokens$20/M output tokens28 providers
- 1M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 48 providers.
by anthropicFeb 5, 2026$3/M input tokens$15/M output tokens48 providers
- 200K context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 33 providers.
by anthropicJan 15, 2025$3/M input tokens$15/M output tokens33 providers
- 1.05M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 7 providers.
by metaOct 12, 2026$4/M input tokens$20/M output tokens7 providers
- 1M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 2 providers.
by anthropicMar 29, 2026$4/M input tokens$20/M output tokens2 providers
- 400K context
Reads text, images and files. Tool calling, reasoning.
by openaiNov 12, 2025$2.50/M input tokens$20/M output tokens
More from OpenAI
- Index 51.8
Reads text, images and files. Tool calling, structured output, reasoning. Served by 27 providers.
by openaiSep 29, 20261.05M context$2/M input tokens$10/M output tokens27 providers
- 1.05M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 2 providers.
by openaiSep 29, 2026$2/M input tokens$10/M output tokens2 providers
- Index 38.1
Reads text, images and files. Tool calling, structured output, reasoning. Served by 27 providers.
by openaiSep 22, 20261.05M context$0.10/M input tokens$0.50/M output tokens27 providers
- 1.05M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 2 providers.
by openaiSep 22, 2026$0.10/M input tokens$0.50/M output tokens2 providers
- 1.05M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 27 providers.
by openaiSep 22, 2026$2/M input tokens$10/M output tokens27 providers
- 1.05M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 2 providers.
by openaiSep 22, 2026$2/M input tokens$10/M output tokens2 providers
GPT-5.6 questions
How much does the GPT-5.6 API cost?
$4 per million input tokens and $20 per million output tokens, with cached input at $0.40. Prompts over 200K tokens bill at $8 input and $30 output. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of GPT-5.6?
1,050,000 tokens of input, and it can write up to 128,000 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve GPT-5.6?
41 providers serve it, including Azure, Amazon Bedrock and Databricks. The lowest input price is $1.50 per million tokens at Xpersona. Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does GPT-5.6 support tool calling?
Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.
Is GPT-5.6 open source?
No. OpenAI serves it through an API only, so you cannot download the weights or host it yourself.
When was GPT-5.6 released?
Jul 9, 2026, with training data up to Feb 2026.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. Independent scores from my hand checked rankings, sources linked above. The summary is written from these facts.
Building on GPT-5.6?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting