OpenAI

GPT 6.1 Terra

OpenAIToken-basedDynamic Pricing
Alias:gpt-6.1-terra
Create API Key

Compare gpt-6.1-terra API pricing, supported endpoints, capabilities and access options on Modelsell.

textimagevisionreasoningstreamingfunction_callingtoolsstructured_outputcachingcontext:1050000new
Starting price
View full pricing
Context
1.1M
Maximum input window
Max output
128K
Maximum tokens per response
Modalities
→
Knowledge cutoff
Jun 2026
Released
Oct 2026

Pricing by Supplier

OpenAI
-40%
Openai官方接口
standardInput ≤ 272K tokens
Input/ 1M tokens
$0.6$1
Output/ 1M tokens
$3$5
Cache Read/ 1M tokens
$0.03$0.05
Cache Write (5m)/ 1M tokens
$0.75$1.25
long_contextInput > 272K tokens
Input/ 1M tokens
$1.2$2
Output/ 1M tokens
$4.5$7.5
Cache Read/ 1M tokens
$0.06$0.1
Cache Write (5m)/ 1M tokens
$1.5$2.5
GPT官+AZ 混合
-40%
适合生产环境,az 和官 key 混合渠道
standardInput ≤ 272K tokens
Input/ 1M tokens
$0.6$1
Output/ 1M tokens
$3$5
Cache Read/ 1M tokens
$0.03$0.05
Cache Write (5m)/ 1M tokens
$0.75$1.25
long_contextInput > 272K tokens
Input/ 1M tokens
$1.2$2
Output/ 1M tokens
$4.5$7.5
Cache Read/ 1M tokens
$0.06$0.1
Cache Write (5m)/ 1M tokens
$1.5$2.5
GPT特价
-90%
适合vibe coding自用,gpt pro 号池
standardInput ≤ 272K tokens
Input/ 1M tokens
$0.1$1
Output/ 1M tokens
$0.5$5
Cache Read/ 1M tokens
$0.005$0.05
Cache Write (5m)/ 1M tokens
$0.125$1.25
long_contextInput > 272K tokens
Input/ 1M tokens
$0.2$2
Output/ 1M tokens
$0.75$7.5
Cache Read/ 1M tokens
$0.01$0.1
Cache Write (5m)/ 1M tokens
$0.25$2.5

Capabilities / Supported modalities

StreamingFunction callingToolsStructured outputVisionWeb searchPrompt cachingReasoningCode interpreter
Input
Output

Provider & data privacy

Provider
OpenAIDocs
Tokenizer
o200k_base
License
Proprietary (commercial)Proprietary
Data retention30 daysNot used for upstream training by default

Performance

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows

Metrics sourced fromArtificial Analysis 2026-09-30·GPT 6.1 Terra

This model is not included in the current benchmark snapshot.

Missing models or measurements are not zero scores.

Benchmark charts preserve the source model selection and reasoning settings. Missing models or measurements are not zero scores, and benchmark cost or speed is not this site’s service commitment.

About GPT 6.1 Terra

用图片和屏幕信息推进日常工作

GPT-6.1 Terra 适合需要兼顾速度与成本的视觉任务:对照商品照片挑选目录条目,解释技术图纸中的结构,理解应用截图中的操作步骤,或把初稿改写成清楚自然的文字。它支持文本和图像输入、文本输出;模型本身不直接生成音频或视频。

接入与能力

可通过 Chat Completions 或 Responses API 调用;函数调用和其他工具调用需要使用 Responses API。官方支持流式响应、结构化输出,以及在 Responses API 中使用网页搜索、文件搜索、代码解释器和计算机操作等工具;工具是否可用取决于所选渠道与应用接入。

推理强度支持 none、low、medium(默认)、high、xhigh、max。上下文窗口为 1,050,000 tokens,最大输出 128,000 tokens;知识截止时间为 2026 年 6 月 1 日,正式发布于 2026 年 10 月 26 日。

标准价格与长上下文

以下为 OpenAI Standard 官方基准价,单位为美元 / 百万 tokens。本站报价和结算继续应用所选分组倍率。

计费项输入不超过 272,000 tokens输入超过 272,000 tokens
普通输入$1.00$2.00
输出$5.00$7.50
缓存读取$0.05$0.10
缓存写入(30 分钟)$1.25$2.50

长上下文档按完整输入长度判断,包括缓存部分;超过门槛时,整次请求适用对应费率。

价格表中的“缓存写入 (5m)”为通用界面标签;本模型实际按 30 分钟缓存写入费率计价。

官方另提供 12 小时缓存写入,基准价为 $2.50,长上下文为 $5.00。本站当前缓存写入统一按上表的 30 分钟写入费率计价,尚未区分 12 小时或混合缓存时长;12 小时价格仅作官方参考。

资料核对日期:2026-10-29。参考 官方模型说明、官方价格、缓存说明 与 发布记录。

Use cases and prompting

商品图片匹配示例

“请对照这张商品图与给定目录,只从目录中选择匹配项。输出 candidate_id、matching_features、uncertain_features 和 needs_review;若图片不足以区分型号,请说明还需要哪种角度或标签,不要补写看不见的规格。”

将商品图、可选条目和匹配标准放在同一请求中;需要程序读取结果时,可使用结构化输出并校验字段。

截图分析与界面操作

提供清晰截图,说明当前页面、要完成的目标和成功条件。仅分析截图时,普通图文对话即可;需要执行点击、输入或其他工具操作时,使用 Responses API 并由应用接入工具。工具调用需要应用执行并回传结果。

接口与推理设置

模型名称为 gpt-6.1-terra。Responses API 使用 reasoning.effort;Chat Completions 使用 reasoning_effort。可选 none、low、medium、high、xhigh、max,默认 medium。工具调用请使用 /v1/responses。

本模型的标准缓存时长为 30 分钟。官方 Responses API 通过 prompt_cache_options.ttl 选择 30m 或 12h;本站当前尚未按缓存时长细分计费,相关官方参考价见上方说明。

API access

API documentation

Code samples

RequestPOST/v1/chat/completions
Example request
Parameters
ParameterTypeDefault / rangeDescription
temperature
number
=10 ~ 2
Sampling temperature; lower is more deterministic
top_p
number
=10 ~ 1
Nucleus sampling probability mass
max_tokens
integer>= 1Maximum number of tokens in the response
frequency_penalty
number
=0-2 ~ 2
Penalises repetition of frequent tokens
presence_penalty
number
=0-2 ~ 2
Encourages introducing new topics
stop
array—Up to 4 strings that stop generation
seed
integer—Deterministic sampling seed (best-effort)
n
integer
=1>= 1
Number of completions to generate
stream
boolean
=false
Stream tokens via Server-Sent Events
response_format
object—Force JSON object or schema-conforming output
tools
array—Tool / function declarations the model may call
tool_choice
string
autononerequired
Tool-choice policy or specific tool name
logprobs
boolean
=false
Return per-token log probabilities
top_logprobs
integer0 ~ 20Number of top log probabilities returned per token
logit_bias
object—Per-token logit bias map
user
string—End-user identifier for abuse monitoring

Replace <YOUR_API_KEY> with the API key from your token settings.

Authentication

All requests must include Authorization: Bearer <TOKEN> header. Anthropic-formatted endpoints accept the x-api-key header instead.

Generate tokens from the Tokens page; you can scope them to specific models, groups, IPs, and rate-limits.

Supported parameters

Generation parameters
ParameterTypeDefault / rangeDescription
temperature
number
=10 ~ 2
Sampling temperature; lower is more deterministic
top_p
number
=10 ~ 1
Nucleus sampling probability mass
max_tokens
integer>= 1Maximum number of tokens in the response
frequency_penalty
number
=0-2 ~ 2
Penalises repetition of frequent tokens
presence_penalty
number
=0-2 ~ 2
Encourages introducing new topics
stop
array—Up to 4 strings that stop generation
seed
integer—Deterministic sampling seed (best-effort)
n
integer
=1>= 1
Number of completions to generate
stream
boolean
=false
Stream tokens via Server-Sent Events
response_format
object—Force JSON object or schema-conforming output
tools
array—Tool / function declarations the model may call
tool_choice
string
autononerequired
Tool-choice policy or specific tool name
logprobs
boolean
=false
Return per-token log probabilities
top_logprobs
integer0 ~ 20Number of top log probabilities returned per token
logit_bias
object—Per-token logit bias map
user
string—End-user identifier for abuse monitoring

Rate limits

SupplierRPMTPMRPD
defaultUnlimitedUnlimitedUnlimited
GPT官+AZ 混合UnlimitedUnlimitedUnlimited
GPT特价UnlimitedUnlimitedUnlimited
OpenAIUnlimitedUnlimitedUnlimited

No restriction

Frequently asked questions about gpt-6.1-terra

What is gpt-6.1-terra?

Compare gpt-6.1-terra API pricing, supported endpoints, capabilities and access options on Modelsell.

How do I call gpt-6.1-terra?

Create an API key with access to gpt-6.1-terra, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.

How is gpt-6.1-terra priced?

Pricing depends on the selected provider group and the model billing unit. The current input, output, request, or media prices are shown on this page before sign-up.

What is the context window of gpt-6.1-terra?

The model catalog lists a context window of 1050000 tokens. Check the selected endpoint for request limits.

What is the maximum output of gpt-6.1-terra?

The model catalog lists a maximum output of 128000 tokens. Your request settings may set a lower limit.

How should I evaluate gpt-6.1-terra for my project?

Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.