OpenRouter 模型 ↗ · 2026-10-27
openai/gpt-6.1-terra
Model release OpenRouter 模型 Source language: Chinese
OpenRouter 于 2026-10-27 收录该模型(收录时间不等于模型正式发布日期);上下文:1,050,000 tokens;输入价:$1.0000/百万 tokens;输出价:$5.0000/百万 tokens;定位(来源描述):GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol.
Full text
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
Compare
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$0.0503.57s81 tok/s
100.00%
$1.00$5.00$0.0502.86s59 tok/s
100.00%
Not used in Standard routing:Why these endpoints are not used
Flex
$0.50$2.50$0.0253.04s43 tok/s
100.00%
$1.10$5.50$0.0552.49s78 tok/s
99.86%
$1.10$5.50$0.0552.68s86 tok/s
100.00%
$1.20$6.00$0.0601.13s69 tok/s
99.81%
Fast
$2.00$10.00$0.1001.14s77 tok/s
100.00%
ProviderInput / Output /M
Input $1.00 / Output $5.00
81 tok/s100.00% uptime
Input $1.00 / Output $5.00
59 tok/s100.00% uptime
Not used in Standard routing:Why these endpoints are not used
Input $0.50 / Output $2.50
Flex
43 tok/s100.00% uptime
Input $1.10 / Output $5.50
78 tok/s99.86% uptime
Input $1.10 / Output $5.50
86 tok/s100.00% uptime
Input $1.20 / Output $6.00
69 tok/s99.81% uptime
Input $2.00 / Output $10.00
Fast
77 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
$0.3123/M tokens
Output
$4.879/M tokens
GPT-6.1 Terra — Price history
Price history
No effective price data for this selection
$0.3088$5.0381.9%16.7%
$0.3247$5.0479.1%61.2%
Not used in Standard routing:Why these endpoints are not used
Flex
$0.0822$2.5290.5%13.6%
$0.2461$6.1188.6%2.4%
$0.2494$5.5486.3%0.7%
Fast
$0.7649$10.0068.5%4.6%
$0.9635$5.5026.2%0.9%
ProviderInput / Output /M
Token share
Effective in $0.3088 / Effective out $5.03
Token share
16.7%
Effective in $0.3247 / Effective out $5.04
Token share
61.2%
Not used in Standard routing:Why these endpoints are not used
Effective in $0.0822 / Effective out $2.52
FlexToken share
13.6%
Effective in $0.2461 / Effective out $6.11
Token share
2.4%
Effective in $0.2494 / Effective out $5.54
Token share
0.7%
Effective in $0.7649 / Effective out $10.00
FastToken share
4.6%
Effective in $0.9635 / Effective out $5.50
Token share
0.9%
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
86tok/s
P50, best across providers
Latency
1.13s
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)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
99.79%
Availability over the last 3 days
Last 72 hours
Availability 99.79%
3 Days Ago2 Days AgoYesterdayNow
Availability over the last 24 hours
OpenRouter Availability
99.91%
Without Routing
97.93%
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)
SourceBenchmarkScore
Artificial AnalysisGPT-6.1 Terra (Xhigh) Intelligence Index45.3
Artificial AnalysisGPT-6.1 Terra (Xhigh) HLE43.7%
Artificial AnalysisGPT-6.1 Terra (Xhigh) AA-LCR81.7%
Artificial AnalysisGPT-6.1 Terra (Xhigh) GDPval-AA45.8%
Artificial AnalysisGPT-6.1 Terra (Xhigh) CritPt26.6%
Artificial AnalysisGPT-6.1 Terra (Xhigh) SciCode53.4%
Artificial AnalysisGPT-6.1 Terra (Xhigh) Terminal-Bench 4.046.5%
Artificial AnalysisGPT-6.1 Terra (Xhigh) AA-Omniscience Accuracy48.0%
Artificial AnalysisGPT-6.1 Terra (Xhigh) AA-Omniscience Non-Hallucination Rate63.2%
Artificial AnalysisGPT-6.1 Terra (High) Intelligence Index42.4
Artificial AnalysisGPT-6.1 Terra (High) HLE43.3%
Artificial AnalysisGPT-6.1 Terra (High) AA-LCR82.3%
Artificial AnalysisGPT-6.1 Terra (High) GDPval-AA42.7%
Artificial AnalysisGPT-6.1 Terra (High) CritPt25.7%
Artificial AnalysisGPT-6.1 Terra (High) SciCode51.6%
Artificial AnalysisGPT-6.1 Terra (High) Terminal-Bench 4.041.9%
Artificial AnalysisGPT-6.1 Terra (High) AA-Omniscience Accuracy47.3%
Artificial AnalysisGPT-6.1 Terra (High) AA-Omniscience Non-Hallucination Rate63.0%
Artificial AnalysisGPT-6.1 Terra (Medium) Intelligence Index38.2
Artificial AnalysisGPT-6.1 Terra (Medium) HLE40.2%
Artificial AnalysisGPT-6.1 Terra (Medium) AA-LCR80.7%
Artificial AnalysisGPT-6.1 Terra (Medium) GDPval-AA41.2%
Artificial AnalysisGPT-6.1 Terra (Medium) CritPt21.4%
Artificial AnalysisGPT-6.1 Terra (Medium) SciCode51.6%
Artificial AnalysisGPT-6.1 Terra (Medium) Terminal-Bench 4.032.3%
Artificial AnalysisGPT-6.1 Terra (Medium) AA-Omniscience Accuracy47.4%
Artificial AnalysisGPT-6.1 Terra (Medium) AA-Omniscience Non-Hallucination Rate60.4%
Artificial AnalysisGPT-6.1 Terra (Non-reasoning) Intelligence Index30.5
Artificial AnalysisGPT-6.1 Terra (Non-reasoning) HLE21.1%
Artificial AnalysisGPT-6.1 Terra (Non-reasoning) AA-LCR67.7%
Artificial AnalysisGPT-6.1 Terra (Non-reasoning) GDPval-AA39.3%
Artificial AnalysisGPT-6.1 Terra (Non-reasoning) CritPt4.9%
Artificial AnalysisGPT-6.1 Terra (Non-reasoning) SciCode47.8%
Artificial AnalysisGPT-6.1 Terra (Non-reasoning) Terminal-Bench 4.026.8%
Artificial AnalysisGPT-6.1 Terra (Non-reasoning) AA-Omniscience Accuracy40.7%
Artificial AnalysisGPT-6.1 Terra (Non-reasoning) AA-Omniscience Non-Hallucination Rate22.9%
Artificial AnalysisGPT-6.1 Terra (Max) Intelligence Index51.3
Artificial AnalysisGPT-6.1 Terra (Max) HLE46.2%
Artificial AnalysisGPT-6.1 Terra (Max) AA-LCR82.7%
Artificial AnalysisGPT-6.1 Terra (Max) GDPval-AA48.8%
Artificial AnalysisGPT-6.1 Terra (Max) CritPt28.0%
Artificial AnalysisGPT-6.1 Terra (Max) SciCode55.1%
Artificial AnalysisGPT-6.1 Terra (Max) Terminal-Bench 4.055.6%
Artificial AnalysisGPT-6.1 Terra (Max) AA-Omniscience Accuracy47.6%
Artificial AnalysisGPT-6.1 Terra (Max) AA-Omniscience Non-Hallucination Rate65.5%
Artificial AnalysisGPT-6.1 Terra (Low) Intelligence Index29.4
Artificial AnalysisGPT-6.1 Terra (Low) HLE35.8%
Artificial AnalysisGPT-6.1 Terra (Low) AA-LCR81.0%
Artificial AnalysisGPT-6.1 Terra (Low) GDPval-AA35.2%
Artificial AnalysisGPT-6.1 Terra (Low) CritPt15.1%
Artificial AnalysisGPT-6.1 Terra (Low) SciCode52.4%
Artificial AnalysisGPT-6.1 Terra (Low) Terminal-Bench 4.015.2%
Artificial AnalysisGPT-6.1 Terra (Low) AA-Omniscience Accuracy45.6%
Artificial AnalysisGPT-6.1 Terra (Low) AA-Omniscience Non-Hallucination Rate58.4%
Vals AIGPT-6.1 Terra EMB v1.173.3%
Vals AIGPT-6.1 Terra Finance Agent v2.156.0%
Vals AIGPT-6.1 Terra Vals Finance Index53.3%
Vals AIGPT-6.1 Terra HLAB-Vals-1.11.7%
Vals AIGPT-6.1 Terra Vals Legal Index58.8%
Vals AIGPT-6.1 Terra Legal Research Bench26.0%
Vals AIGPT-6.1 Terra Tax Agent Bench17.1%
Vals AIGPT-6.1 Terra Terminal-Bench 4.049.5%
Vals AIGPT-6.1 Terra Vals Index60.5%
Vals AIGPT-6.1 Terra Vibe Code Bench v1.184.0%
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.
1.
Codex
A coding agent that helps you build and ship with AI
292Btokens
2.
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.
220Btokens
3.
omp
new
118Btokens
4.
pi
There are many coding agents, but this one is yours.
101Btokens
5.
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.
24.8Btokens
Rest of OpenRouter
59B
Top 5 Apps
17B
Activity
Token volume and request traffic to this model over time.
API
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
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 EuropeAzurePrices in Europe
Azure: $1.20/M tokens input, $6/M tokens output
Base URLhttps://eu.openrouter.ai/api/v1PlanRequires 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
Frequently asked questions
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.
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.
GPT-6.1 Terra has a 1,050,000 token context window. It supports up to 128,000 completion tokens.
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.
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.
GPT-6.1 Terra accepts files such as PDFs, images, and text as input and returns text.
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.
GPT-6.1 Terra was released on October 26, 2026.