How much does GPT-6.1 Terra cost?

GPT-6.1 Terra costs $1.00/M input tokens and $5.00/M output tokens, with separate rates for Cache Read at $0.05/M tokens, Cache Write at $1.25/M tokens, and Web Search at $10.00/1K calls.

What is the context length of GPT-6.1 Terra?

GPT-6.1 Terra has a 1,050,000 token context window. It supports up to 128,000 completion tokens.

Does GPT-6.1 Terra support tool calling and structured outputs?

Yes. GPT-6.1 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-6.1 Terra?

Yes. OpenAI caches prompts of 1024 tokens or more automatically, and GPT-6.1 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-6.1 Terra support?

GPT-6.1 Terra accepts files such as PDFs, images, and text as input and returns text.

Which providers serve GPT-6.1 Terra?

GPT-6.1 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-6.1 Terra released?

GPT-6.1 Terra was released on October 26, 2026.

OpenAI: GPT-6.1 Terra

openai/gpt-6.1-terra

Compare

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.

Modalities

In / out price

$1 / $5per 1M

Context

1.1M

Released

Oct 26, 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


	$1.00	$5.00	$0.05	4.01s	77 tok/s	100.00%
	$1.00	$5.00	$0.05	2.04s	48 tok/s	100.00%
Not used in Standard routing:Why these endpoints are not used
Flex	$0.50	$2.50	$0.025	6.82s	31 tok/s	100.00%
	$1.10	$5.50	$0.055	3.73s	46 tok/s	99.96%
	$1.10	$5.50	$0.055	2.66s	64 tok/s	100.00%
	$1.20	$6.00	$0.06	1.53s	68 tok/s	99.97%
Fast	$2.00	$10.00	$0.10	1.30s	64 tok/s	100.00%

Input $1.00Output $5.00
77 tok/s100.00% uptime
Input $1.00Output $5.00
48 tok/s100.00% uptime
Not used in Standard routing:Why these endpoints are not used
Input $0.50Output $2.50
Flex
31 tok/s100.00% uptime
Input $1.10Output $5.50
46 tok/s99.96% uptime
Input $1.10Output $5.50
64 tok/s100.00% uptime
Input $1.20Output $6.00
68 tok/s99.97% uptime
Input $2.00Output $10.00
Fast
64 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

$0.2161/M tokens

Output

$4.978/M tokens

GPT-6.1 Terra — Price history

Price history

No effective price data for this selection

		$0.1628	$5.01	91.5%	30.0%
		$0.2323	$5.05	86.8%	56.6%
Not used in Standard routing:Why these endpoints are not used
	Flex	$0.0799	$2.52	91.0%	7.2%
		$0.3216	$5.59	82.8%	1.4%
		$0.4280	$6.05	76.1%	2.1%
		$0.5030	$5.50	64.3%	1.0%
	Fast	$0.6703	$10.00	72.3%	1.7%

Effective in $0.1628Effective out $5.01
Token share
30.0%
Effective in $0.2323Effective out $5.05
Token share
56.6%
Not used in Standard routing:Why these endpoints are not used
Effective in $0.0799Effective out $2.52
FlexToken share
7.2%
Effective in $0.3216Effective out $5.59
Token share
1.4%
Effective in $0.4280Effective out $6.05
Token share
2.1%
Effective in $0.5030Effective out $5.50
Token share
1.0%
Effective in $0.6703Effective out $10.00
FastToken share
1.7%

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

77tok/s

P50, best across providers

Latency

1.30s

P50, best provider

Reasoning effortLatency / throughput

AutoExacto benchmarks

GPQA DiamondTAU-BenchOpenAI91.1%70.0%Azure (EU)91.9%68.7%Amazon Bedrock91.9%68.4%Azure90.9%69.3%Azure (US)90.1%65.3%

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)

99.68%

Availability over the last 3 days

Last 72 hours

Availability 99.68%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.67%

Without Routing

99.22%

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-6.1 Terra (Artificial Analysis and Vals AI)
Source	Benchmark	Score
Artificial Analysis	GPT-6.1 Terra (Max) Intelligence Index	51.3
Artificial Analysis	GPT-6.1 Terra (Max) HLE	46.2%
Artificial Analysis	GPT-6.1 Terra (Max) AA-LCR	82.7%
Artificial Analysis	GPT-6.1 Terra (Max) GDPval-AA	48.8%
Artificial Analysis	GPT-6.1 Terra (Max) CritPt	28.0%
Artificial Analysis	GPT-6.1 Terra (Max) SciCode	55.1%
Artificial Analysis	GPT-6.1 Terra (Max) Terminal-Bench 4.0	55.6%
Artificial Analysis	GPT-6.1 Terra (Max) AA-Omniscience Accuracy	47.6%
Artificial Analysis	GPT-6.1 Terra (Max) AA-Omniscience Non-Hallucination Rate	65.5%
Artificial Analysis	GPT-6.1 Terra (Xhigh) Intelligence Index	45.3
Artificial Analysis	GPT-6.1 Terra (Xhigh) HLE	43.7%
Artificial Analysis	GPT-6.1 Terra (Xhigh) AA-LCR	81.7%
Artificial Analysis	GPT-6.1 Terra (Xhigh) GDPval-AA	45.7%
Artificial Analysis	GPT-6.1 Terra (Xhigh) CritPt	26.6%
Artificial Analysis	GPT-6.1 Terra (Xhigh) SciCode	53.4%
Artificial Analysis	GPT-6.1 Terra (Xhigh) Terminal-Bench 4.0	46.5%
Artificial Analysis	GPT-6.1 Terra (Xhigh) AA-Omniscience Accuracy	48.0%
Artificial Analysis	GPT-6.1 Terra (Xhigh) AA-Omniscience Non-Hallucination Rate	63.2%
Artificial Analysis	GPT-6.1 Terra (High) Intelligence Index	42.4
Artificial Analysis	GPT-6.1 Terra (High) HLE	43.3%
Artificial Analysis	GPT-6.1 Terra (High) AA-LCR	82.3%
Artificial Analysis	GPT-6.1 Terra (High) GDPval-AA	42.6%
Artificial Analysis	GPT-6.1 Terra (High) CritPt	25.7%
Artificial Analysis	GPT-6.1 Terra (High) SciCode	51.6%
Artificial Analysis	GPT-6.1 Terra (High) Terminal-Bench 4.0	41.9%
Artificial Analysis	GPT-6.1 Terra (High) AA-Omniscience Accuracy	47.3%
Artificial Analysis	GPT-6.1 Terra (High) AA-Omniscience Non-Hallucination Rate	63.0%
Artificial Analysis	GPT-6.1 Terra (Medium) Intelligence Index	38.2
Artificial Analysis	GPT-6.1 Terra (Medium) HLE	40.2%
Artificial Analysis	GPT-6.1 Terra (Medium) AA-LCR	80.7%
Artificial Analysis	GPT-6.1 Terra (Medium) GDPval-AA	41.2%
Artificial Analysis	GPT-6.1 Terra (Medium) CritPt	21.4%
Artificial Analysis	GPT-6.1 Terra (Medium) SciCode	51.6%
Artificial Analysis	GPT-6.1 Terra (Medium) Terminal-Bench 4.0	32.3%
Artificial Analysis	GPT-6.1 Terra (Medium) AA-Omniscience Accuracy	47.4%
Artificial Analysis	GPT-6.1 Terra (Medium) AA-Omniscience Non-Hallucination Rate	60.4%
Artificial Analysis	GPT-6.1 Terra (Low) Intelligence Index	29.4
Artificial Analysis	GPT-6.1 Terra (Low) HLE	35.8%
Artificial Analysis	GPT-6.1 Terra (Low) AA-LCR	81.0%
Artificial Analysis	GPT-6.1 Terra (Low) GDPval-AA	35.2%
Artificial Analysis	GPT-6.1 Terra (Low) CritPt	15.1%
Artificial Analysis	GPT-6.1 Terra (Low) SciCode	52.4%
Artificial Analysis	GPT-6.1 Terra (Low) Terminal-Bench 4.0	15.2%
Artificial Analysis	GPT-6.1 Terra (Low) AA-Omniscience Accuracy	45.6%
Artificial Analysis	GPT-6.1 Terra (Low) AA-Omniscience Non-Hallucination Rate	58.4%
Artificial Analysis	GPT-6.1 Terra (Non-reasoning) Intelligence Index	30.5
Artificial Analysis	GPT-6.1 Terra (Non-reasoning) HLE	21.1%
Artificial Analysis	GPT-6.1 Terra (Non-reasoning) AA-LCR	67.7%
Artificial Analysis	GPT-6.1 Terra (Non-reasoning) GDPval-AA	39.3%
Artificial Analysis	GPT-6.1 Terra (Non-reasoning) CritPt	4.9%
Artificial Analysis	GPT-6.1 Terra (Non-reasoning) SciCode	47.8%
Artificial Analysis	GPT-6.1 Terra (Non-reasoning) Terminal-Bench 4.0	26.8%
Artificial Analysis	GPT-6.1 Terra (Non-reasoning) AA-Omniscience Accuracy	40.7%
Artificial Analysis	GPT-6.1 Terra (Non-reasoning) AA-Omniscience Non-Hallucination Rate	22.9%
Vals AI	GPT-6.1 Terra EMB v1.1	73.3%
Vals AI	GPT-6.1 Terra Finance Agent v2.1	56.0%
Vals AI	GPT-6.1 Terra Vals Finance Index	53.3%
Vals AI	GPT-6.1 Terra HLAB-Vals-1.1	1.7%
Vals AI	GPT-6.1 Terra Vals Legal Index	58.8%
Vals AI	GPT-6.1 Terra Legal Research Bench	26.0%
Vals AI	GPT-6.1 Terra Tax Agent Bench	17.1%
Vals AI	GPT-6.1 Terra Terminal-Bench 4.0	49.5%
Vals AI	GPT-6.1 Terra Vals Index	60.5%
Vals AI	GPT-6.1 Terra Vibe Code Bench v1.1	84.0%

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.

Codex

A coding agent that helps you build and ship with AI

284Btokens

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.

197Btokens

omp

new

114Btokens

There are many coding agents, but this one is yours.

92Btokens

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.

23.5Btokens

Rest of OpenRouter

129B

Top 5 Apps

29.2B

OpenAI: GPT Terra versions

Available through EU in-region routing

OpenAI: GPT-6.1 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: $1.20/M tokens input, $6/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 (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

GPT Sol Latest

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

Text1.1M context

OpenAI: GPT-6.1 Terra

Providers