Where is the GPT-5.6 Terra documentation?

The GPT-5.6 Terra documentation on OpenRouter includes the GPT-5.6 Migration Guide cookbook and the GPT 5.6 Discounts & Jevons Paradox blog post. The quickstart covers API keys and your first request, and the API reference lists every parameter.

How much does GPT-5.6 Terra cost?

GPT-5.6 Terra costs $2.00/M input tokens and $12.00/M output tokens, with separate rates for Cache Read at $0.20/M tokens, Cache Write at $2.50/M tokens, and Web Search at $10.00/1K calls.

What is the context length of GPT-5.6 Terra?

GPT-5.6 Terra has a 1,050,000 token context window. It supports up to 128,000 completion tokens.

Does GPT-5.6 Terra support tool calling and structured outputs?

Yes. GPT-5.6 Terra accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Can I disable prompt caching for GPT-5.6 Terra?

Yes. OpenAI caches prompts of 1024 tokens or more automatically, and GPT-5.6 Terra bills a cache write on each cached prompt whether or not the cached prefix is read again. To turn caching off for a request, set prompt_cache_options.mode to "explicit" at the request root and do not mark any content block with prompt_cache_breakpoint. Explicit mode disables OpenAI-managed breakpoints, so a request with none of your own has no cacheable prefix and is billed at the plain input rate. See the prompt caching guide.

What inputs and outputs does GPT-5.6 Terra support?

GPT-5.6 Terra accepts files such as PDFs, images, and text as input and returns text.

Which providers serve GPT-5.6 Terra?

GPT-5.6 Terra is served by 3 providers on OpenRouter: OpenAI, Azure, and Amazon Bedrock. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

When was GPT-5.6 Terra released?

GPT-5.6 Terra was released on July 9, 2026. Its knowledge cutoff is February 16, 2026.

OpenAI: GPT-5.6 Terra

openai/gpt-5.6-terra

Compare

GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced, offering strong performance at roughly half the cost of Sol.

Modalities

In / out price

$2 / $12per 1M

Context

1.1M

Released

Jul 9, 2026

Knowledge cutoff

Feb 2026

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput


	$2.00	$12.00	$0.20	1.79s	53 tok/s	100.00%
	$2.00	$12.00	$0.20	3.15s	71 tok/s	100.00%
Not used in Standard routing:Why these endpoints are not used
Flex	$1.00	$6.00	$0.10	2.49s	78 tok/s	100.00%
	$2.20	$13.20	$0.22	3.28s	96 tok/s	100.00%
	$2.20	$13.20	$0.22	1.83s	74 tok/s	100.00%
	$2.20	$13.20	$0.22	1.30s	75 tok/s	100.00%
Fast	$4.00	$24.00	$0.40	0.90s	95 tok/s	100.00%

Input $2.00Output $12.00
53 tok/s100.00% uptime
Input $2.00Output $12.00
71 tok/s100.00% uptime
Not used in Standard routing:Why these endpoints are not used
Input $1.00Output $6.00
Flex
78 tok/s100.00% uptime
Input $2.20Output $13.20
96 tok/s100.00% uptime
Input $2.20Output $13.20
74 tok/s100.00% uptime
Input $2.20Output $13.20
75 tok/s100.00% uptime
Input $4.00Output $24.00
Fast
95 tok/s100.00% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.8513/M tokens

Output

$11.80/M tokens

GPT-5.6 Terra — Price history

Price history

No effective price data for this selection

		$0.607	$12.06	84.0%	13.7%
		$0.887	$12.02	71.8%	82.6%
Not used in Standard routing:Why these endpoints are not used
	Flex	$0.799	$6.00	31.2%	1.5%
		$0.800	$13.20	76.9%	1.0%
		$1.102	$13.20	67.8%	0.6%
	Fast	$1.424	$24.00	77.5%	0.6%
		$1.590	$13.20	45.6%	0.0%

Effective in $0.607Effective out $12.06
Token share
13.7%
Effective in $0.887Effective out $12.02
Token share
82.6%
Not used in Standard routing:Why these endpoints are not used
Effective in $0.799Effective out $6.00
FlexToken share
1.5%
Effective in $0.800Effective out $13.20
Token share
1.0%
Effective in $1.102Effective out $13.20
Token share
0.6%
Effective in $1.424Effective out $24.00
FastToken share
0.6%
Effective in $1.590Effective out $13.20
Token share
0.0%

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

99.82%

Availability over the last 3 days

Last 72 hours

Availability 99.82%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.83%

Without Routing

98.85%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for OpenAI: GPT-5.6 Terra (Artificial Analysis and Vals AI)
Source	Benchmark	Score
Artificial Analysis	GPT-5.6 Terra (Max) Intelligence Index	32.3
Artificial Analysis	GPT-5.6 Terra (Max) Coding Index	76.7
Artificial Analysis	GPT-5.6 Terra (Max) Agentic Index	43.2
Artificial Analysis	GPT-5.6 Terra (Max) GPQA Diamond	92.5%
Artificial Analysis	GPT-5.6 Terra (Max) HLE	42.9%
Artificial Analysis	GPT-5.6 Terra (Max) IFBench	71.2%
Artificial Analysis	GPT-5.6 Terra (Max) τ²-Bench Telecom	86.3%
Artificial Analysis	GPT-5.6 Terra (Max) AA-LCR	83.0%
Artificial Analysis	GPT-5.6 Terra (Max) τ-Bench Banking	40.2%
Artificial Analysis	GPT-5.6 Terra (Max) GDPval-AA	48.1%
Artificial Analysis	GPT-5.6 Terra (Max) CritPt	30.0%
Artificial Analysis	GPT-5.6 Terra (Max) SciCode	55.0%
Artificial Analysis	GPT-5.6 Terra (Max) Terminal-Bench Hard	57.6%
Artificial Analysis	GPT-5.6 Terra (Max) Terminal-Bench 4.0	35.4%
Artificial Analysis	GPT-5.6 Terra (Max) Terminal-Bench 2.1	88.0%
Artificial Analysis	GPT-5.6 Terra (Max) AA-Omniscience Accuracy	42.3%
Artificial Analysis	GPT-5.6 Terra (Max) AA-Omniscience Non-Hallucination Rate	10.6%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) Coding Index	52.3
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) Agentic Index	23.5
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) GPQA Diamond	74.6%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) HLE	11.4%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) AA-LCR	58.7%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) τ-Bench Banking	15.7%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) GDPval-AA	30.2%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) CritPt	2.0%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) SciCode	45.1%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) Terminal-Bench 4.0	0.5%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) Terminal-Bench 2.1	56.2%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) AA-Omniscience Accuracy	32.6%
Artificial Analysis	GPT-5.6 Terra (Non-reasoning) AA-Omniscience Non-Hallucination Rate	4.4%
Artificial Analysis	GPT-5.6 Terra (Low) Coding Index	58.1
Artificial Analysis	GPT-5.6 Terra (Low) Agentic Index	25.9
Artificial Analysis	GPT-5.6 Terra (Low) GPQA Diamond	84.3%
Artificial Analysis	GPT-5.6 Terra (Low) HLE	29.2%
Artificial Analysis	GPT-5.6 Terra (Low) IFBench	59.7%
Artificial Analysis	GPT-5.6 Terra (Low) τ²-Bench Telecom	60.5%
Artificial Analysis	GPT-5.6 Terra (Low) AA-LCR	71.3%
Artificial Analysis	GPT-5.6 Terra (Low) τ-Bench Banking	18.8%
Artificial Analysis	GPT-5.6 Terra (Low) GDPval-AA	30.9%
Artificial Analysis	GPT-5.6 Terra (Low) CritPt	9.4%
Artificial Analysis	GPT-5.6 Terra (Low) SciCode	49.9%
Artificial Analysis	GPT-5.6 Terra (Low) Terminal-Bench Hard	43.9%
Artificial Analysis	GPT-5.6 Terra (Low) Terminal-Bench 4.0	1.5%
Artificial Analysis	GPT-5.6 Terra (Low) Terminal-Bench 2.1	62.5%
Artificial Analysis	GPT-5.6 Terra (Low) AA-Omniscience Accuracy	39.8%
Artificial Analysis	GPT-5.6 Terra (Low) AA-Omniscience Non-Hallucination Rate	8.7%
Artificial Analysis	GPT-5.6 Terra (Xhigh) Coding Index	70.6
Artificial Analysis	GPT-5.6 Terra (Xhigh) Agentic Index	41.4
Artificial Analysis	GPT-5.6 Terra (Xhigh) GPQA Diamond	90.8%
Artificial Analysis	GPT-5.6 Terra (Xhigh) HLE	41.9%
Artificial Analysis	GPT-5.6 Terra (Xhigh) IFBench	66.3%
Artificial Analysis	GPT-5.6 Terra (Xhigh) τ²-Bench Telecom	80.4%
Artificial Analysis	GPT-5.6 Terra (Xhigh) AA-LCR	79.0%
Artificial Analysis	GPT-5.6 Terra (Xhigh) τ-Bench Banking	29.7%
Artificial Analysis	GPT-5.6 Terra (Xhigh) GDPval-AA	47.8%
Artificial Analysis	GPT-5.6 Terra (Xhigh) CritPt	27.1%
Artificial Analysis	GPT-5.6 Terra (Xhigh) SciCode	52.3%
Artificial Analysis	GPT-5.6 Terra (Xhigh) Terminal-Bench Hard	62.9%
Artificial Analysis	GPT-5.6 Terra (Xhigh) Terminal-Bench 4.0	10.1%
Artificial Analysis	GPT-5.6 Terra (Xhigh) Terminal-Bench 2.1	80.1%
Artificial Analysis	GPT-5.6 Terra (Xhigh) AA-Omniscience Accuracy	41.3%
Artificial Analysis	GPT-5.6 Terra (Xhigh) AA-Omniscience Non-Hallucination Rate	9.9%
Artificial Analysis	GPT-5.6 Terra (High) Coding Index	67.1
Artificial Analysis	GPT-5.6 Terra (High) Agentic Index	36.7
Artificial Analysis	GPT-5.6 Terra (High) GPQA Diamond	89.6%
Artificial Analysis	GPT-5.6 Terra (High) HLE	38.5%
Artificial Analysis	GPT-5.6 Terra (High) IFBench	64.4%
Artificial Analysis	GPT-5.6 Terra (High) τ²-Bench Telecom	78.4%
Artificial Analysis	GPT-5.6 Terra (High) AA-LCR	77.7%
Artificial Analysis	GPT-5.6 Terra (High) τ-Bench Banking	28.7%
Artificial Analysis	GPT-5.6 Terra (High) GDPval-AA	44.4%
Artificial Analysis	GPT-5.6 Terra (High) CritPt	22.9%
Artificial Analysis	GPT-5.6 Terra (High) SciCode	52.4%
Artificial Analysis	GPT-5.6 Terra (High) Terminal-Bench Hard	57.6%
Artificial Analysis	GPT-5.6 Terra (High) Terminal-Bench 4.0	1.5%
Artificial Analysis	GPT-5.6 Terra (High) Terminal-Bench 2.1	75.7%
Artificial Analysis	GPT-5.6 Terra (High) AA-Omniscience Accuracy	41.2%
Artificial Analysis	GPT-5.6 Terra (High) AA-Omniscience Non-Hallucination Rate	9.0%
Artificial Analysis	GPT-5.6 Terra (Medium) Coding Index	64.7
Artificial Analysis	GPT-5.6 Terra (Medium) Agentic Index	30.4
Artificial Analysis	GPT-5.6 Terra (Medium) GPQA Diamond	87.2%
Artificial Analysis	GPT-5.6 Terra (Medium) HLE	33.3%
Artificial Analysis	GPT-5.6 Terra (Medium) IFBench	62.2%
Artificial Analysis	GPT-5.6 Terra (Medium) τ²-Bench Telecom	72.8%
Artificial Analysis	GPT-5.6 Terra (Medium) AA-LCR	74.0%
Artificial Analysis	GPT-5.6 Terra (Medium) τ-Bench Banking	25.6%
Artificial Analysis	GPT-5.6 Terra (Medium) GDPval-AA	38.7%
Artificial Analysis	GPT-5.6 Terra (Medium) CritPt	17.4%
Artificial Analysis	GPT-5.6 Terra (Medium) SciCode	50.5%
Artificial Analysis	GPT-5.6 Terra (Medium) Terminal-Bench 4.0	1.0%
Artificial Analysis	GPT-5.6 Terra (Medium) Terminal-Bench 2.1	72.3%
Artificial Analysis	GPT-5.6 Terra (Medium) AA-Omniscience Accuracy	40.5%
Artificial Analysis	GPT-5.6 Terra (Medium) AA-Omniscience Non-Hallucination Rate	8.7%
Vals AI	GPT-5.6 Terra Code Migration	47.8%
Vals AI	GPT-5.6 Terra CorpFin v2	65.3%
Vals AI	GPT-5.6 Terra CyberBench v1.1	72.1%
Vals AI	GPT-5.6 Terra EMB	66.2%
Vals AI	GPT-5.6 Terra Finance Agent (v2)	54.4%
Vals AI	GPT-5.6 Terra Financial Coaching Bench	71.0%
Vals AI	GPT-5.6 Terra GPQA Diamond	90.9%
Vals AI	GPT-5.6 Terra Harvey's Legal Agent Benchmark v1	0.8%
Vals AI	GPT-5.6 Terra IOI	87.6%
Vals AI	GPT-5.6 Terra LiveCodeBench	85.9%
Vals AI	GPT-5.6 Terra LegalBench	85.1%
Vals AI	GPT-5.6 Terra Legal Research Bench	41.3%
Vals AI	GPT-5.6 Terra MedCode	43.4%
Vals AI	GPT-5.6 Terra MedScribe	82.9%
Vals AI	GPT-5.6 Terra MMLU Pro	86.7%
Vals AI	GPT-5.6 Terra MMMU Pro	86.5%
Vals AI	GPT-5.6 Terra MortgageTax	67.3%
Vals AI	GPT-5.6 Terra ProgramBench	0.5%
Vals AI	GPT-5.6 Terra ProofBench v1.1	74.0%
Vals AI	GPT-5.6 Terra Public Benefits Bench v1.1	62.4%
Vals AI	GPT-5.6 Terra SAGE	87.0%
Vals AI	GPT-5.6 Terra SkillsBench	58.9%
Vals AI	GPT-5.6 Terra SRE Bench	9.5%
Vals AI	GPT-5.6 Terra SWE-bench	95.4%
Vals AI	GPT-5.6 Terra Tax Agent Bench	30.0%
Vals AI	GPT-5.6 Terra TaxEval v2	76.2%
Vals AI	GPT-5.6 Terra Terminal-Bench 4.0	22.7%
Vals AI	GPT-5.6 Terra Terminal-Bench-Science	10.0%
Vals AI	GPT-5.6 Terra Vals Index	53.1%
Vals AI	GPT-5.6 Terra Vals Multimodal Index	65.1%
Vals AI	GPT-5.6 Terra Vibe Code Bench 1-100	14.8%
Vals AI	GPT-5.6 Terra Vibe Code Bench v1.1	74.6%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Framer

Create a professional website with Framer’s no-code AI website builder. Design freely, manage CMS content, optimize SEO, collaborate, and publish fast.

49Btokens

Claude Code

Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.

35.2Btokens

Codex

A coding agent that helps you build and ship with AI

29.1Btokens

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

19Btokens

Oneport-Agent

new

16.6Btokens

Rest of OpenRouter

11.6B

Top 5 Apps

2.17B

OpenAI: GPT Terra versions

Available through EU in-region routing

OpenAI: GPT-5.6 Terra is available through EU in-region routing. Requests sent to eu.openrouter.ai are decrypted in the EU and routed only to shared provider endpoints in Europe (the EU/EEA, the UK, and Switzerland).

Providers in Europe

Azure

Prices in Europe

Azure: $2.20/M tokens input, $13.20/M tokens output

Base URL

https://eu.openrouter.ai/api/v1

Plan

Requires Business or Enterprise. Self-serve on Business: no contract, no monthly minimum. OpenRouter Business for EU in-region routing

Fails closed: if no shared provider endpoint in Europe is available, the request errors instead of leaving the region. Requests served by your own BYOK key go to your deployment’s region, which you control. In-region routing docs

More models from OpenAI

GPT Image 2.6 Sunburst

GPT Image 2.6 Sunburst is OpenAI's image generation and editing model optimized for detail: dense compositions, text-heavy layouts, and edits that keep details consistent from one edit to the next at medium or high quality, generating about 50% faster than GPT Image 2.5. It takes text and image inputs and produces images, with quality tiers from low to max, transparent backgrounds, and custom sizes in multiples of 16 pixels at aspect ratios from 1:3 to 3:1. GPT Image 2.6 introduces a complexity setting for how much the model plans before rendering, markup-guided edits, animated GIF output, and SVG output. Choose Flare instead when speed matters more than fine detail.

Image$8 / $30

GPT Image 2.6 Flare

GPT Image 2.6 Flare is OpenAI's image generation and editing model optimized for speed: fast iteration and interactive text-to-image and image-to-image workflows, generating about 50% faster than GPT Image 2.5. It takes text and image inputs and produces images, with quality tiers from low to max, transparent backgrounds, and custom sizes in multiples of 16 pixels at aspect ratios from 1:3 to 3:1. GPT Image 2.6 introduces a complexity setting for how much the model plans before rendering, markup-guided edits, animated GIF output, and SVG output. Choose Sunburst instead when detail and edit-to-edit consistency matter more than latency.

Image$8 / $30

GPT-6.1 Terra Pro

GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Terra and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6.1 Terra instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$1 / $5

GPT-6.1 Terra Pro (batch)

GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$0.50 / $2.50

GPT-6.1 Terra

GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots and on-screen content, and is efficient enough for high-volume workloads.

Text1.1M context$1 / $5

GPT-6.1 Terra (batch)

Text1.1M context$0.50 / $2.50

GPT-6 Luna Decisions

GPT-6 Luna Decisions is GPT-6 Luna served through OpenAI's Decisions API. Instead of generating text, it reads the content passed as state (text, JSON, or images) and returns typed, probabilistic answers to named questions in a single request: the probability of yes for a yes/no question (noul), a probability for every option plus the most likely one (choice), or a probability for every level of an ordered rubric plus the expected score (score).

It is built for classification, routing, moderation, and rubric grading where application code thresholds the returned numbers rather than parsing a chat reply. A request can carry up to 200 questions about the same content.

Decisions$0.10 / $0

GPT-6.1 Sol Pro

GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6.1 Sol instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$2 / $10

GPT-6.1 Sol Pro (batch)

GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$1 / $5

GPT-6.1 Sol

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.

Text1.1M context$2 / $10

GPT-6.1 Sol (batch)

Text1.1M context$1 / $5

GPT-6 Luna Pro

GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6 Luna and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6 Luna instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$0.10 / $0.50

GPT-6 Luna Pro (batch)

GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$0.05 / $0.25

GPT-6 Luna

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model. It shares the GPT-6 family's gains in factual reliability and its clearer, more concise communication style.

Text1.1M context$0.10 / $0.50

GPT-6 Luna (batch)

Text1.1M context$0.05 / $0.25

GPT-6 Sol Pro

GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6 Sol instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$2 / $10

GPT-6 Sol Pro (batch)

GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$1 / $5

GPT-6 Sol

GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost and shares Astra's clearer, more concise communication style in technical and coding conversations.

Text1.1M context$2 / $10

GPT-6 Sol (batch)

Text1.1M context$1 / $5

GPT Astra Latest

This model always redirects to the latest model in the GPT Astra family.

Text1.1M context

OpenAI: GPT-5.6 Terra

Providers