ai.canshu.com
中文
VRAM Calculator Advisor & TCO API Pricing Compare Models Leaderboard GPUs

Search models, GPUs, and tools

↑↓ Navigate · Enter Open · ★ Watchlist prioritized ai.canshu.com
OpenAI
Proprietary API OpenAI · gpt-6.1-terra · Text+Image+PDF

GPT-6.1 Terra Official Specifications, Pricing & Benchmarks

Cost-efficient 1.05M-context OpenAI workhorse at half the price of GPT-6.1 Sol ($1/$5, $0.05 cached).

📋 GPT-6.1 Terra Official API & System Card Specifications

Verified against official OpenAI developer documentation & pricing

API Model ID: gpt-6.1-terra

1. Identity & Capabilities

API Spec
API Model ID
gpt-6.1-terra
Release Date
2026-10-26
Weight License
Proprietary (Undisclosed)
Native Reasoning
✅ Supported
Function Calling & JSON Schema
✅ 原生支持
Batch API 异步批处理
✅ Supported (50% off)

2. Context, Output & Modalities

Limits
Max Context Window
1,050,000 tokens (1050K)
Max Output Tokens
128,000 tokens
Input Modalities
Text + Image + PDF
Output Modalities
Text
Direct China Access
🌐 Global / OpenRouter
Deployment Mode
Cloud API only (Proprietary)

3. Official Pricing & Cache

USD / 1M
Input / 1M Tokens
$ 1
Cached Input / 1M
$ 0.05 -95%
Output / 1M Tokens
$ 5
Tiered Pricing Notes
Base rate ≤272K ($1/$5, $0.05 cache read); >272K ($2/$7.5)

🏆 Official Benchmark Results

Sourced from official System Card / Model Card & technical reports

Arena Elo ~1496 AA Index 51
📚 Knowledge
MMLU-Pro 87 %

A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks.

🧠 Reasoning
GPQA Diamond 89.5 %

PhD-level Google-proof science reasoning questions

💻 Coding
SWE-bench Verified 76.5 %

A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.

🤖 Agentic
Terminal Bench 2.0 64 %

🎛️ Official Sampling & Reasoning Parameters

Recommended generation settings & API parameter constraints

Production Agent Balanced Mode
temperature=1 top_p=1 max_tokens=32,768

💡 Keep static system/tool schemas at prompt prefix to trigger $0.05/1M cached reads.

📊 GPT-6.1 Terra Full Benchmark Scorecard

7 public benchmarks · ranks among 154 models · synced 2026-11-20

⚔️ Compare head-to-head

Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).

Closest Self-Hostable Open-Weight Alternatives to GPT-6.1 Terra

Open-weight models with full HuggingFace weights for private GPU / Mac deployment

Compare with these →

Frequently Asked Questions

Is GPT-6.1 Terra open-source or proprietary?

GPT-6.1 Terra (gpt-6.1-terra) is a proprietary commercial model by OpenAI. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.

What are the context limit and API pricing of GPT-6.1 Terra?

GPT-6.1 Terra supports 1050K input context and 128,000 max output tokens, priced at $1/1M input ($0.05/1M cached) and $5/1M output.