LLM Reference

GPT-5.6 Terra

Released
2026-06-26
Last refreshed
2026-06-26
Status
Researched today
Limited previewProprietaryCommercial use: conditionalMultimodalAgentsVisionJSON / Tool use

GPT-5.6 Terra is in limited preview with a tracked OpenAI API route; evaluate it only if you have access, and wait for broader availability plus fuller context and benchmark evidence before migrating production.

Use it for

  • Teams that already qualify for GPT-5.6 Terra's limited preview
  • Teams evaluating the sourced OpenAI API route
  • Architecture watchlists waiting for broad availability

Do not use it for

  • Production launches that need broad self-serve access
  • Migrations that require confirmed context and output limits
  • Benchmark-led selections that need independent public scores
Specifications
Availability
Limited preview
Family
GPT-5.6
Released
2026-06-26
Architecture
Decoder Only
Specialization
general
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Created by

Cutting-edge research and development.

San Francisco, California, United States
Founded 2015
Website
Pricing
Output / 1M
$15.00
Input / 1M
$2.50

Cheapest of 1 route · OpenAI API · cache read $0.250

About

OpenAI's balanced mid-tier GPT-5.6 model. Terra delivers performance competitive with GPT-5.5 at about 2x lower cost, suited for high-volume production workloads such as customer support, document analysis, and internal tooling. It introduces the GPT-5.6 family preview tiering and is available only to select trusted partners until broad API access launches.

GPT-5.6 Terra is a proprietary model in the GPT-5.6 family. The structured metadata tracks multimodal input, reasoning, function calling, and tool use. This page tracks provider routes through OpenAI API, with the cheapest tracked route listed at $2.5 input and $15 output per 1M tokens. Headline tracked benchmarks include HealthBench Professional 57.7, HealthBench 57.0, and HealthBench Hard 32.7.

Top use-case fit: coding, agents, and build tasks

Agents

Included by capability and metadata signals in the decision map.

Vision

Included by capability and metadata signals in the decision map.

JSON / Tool use

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MCacheRoute
OpenAI API$2.50$15.00read $0.250
Serverless

Available via routers & gateways(15)

Capabilities

VisionMultimodalReasoningFunction CallingTool UsePrompt Caching

Benchmark peer barsfor Agents

No task-mapped benchmark peers are available for this model yet.

Benchmark scores(4)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
HealthBench Professional57.7length-adjusted; raw 62.4; mean response 3618 charshttps://deploymentsafety.openai.com/gpt-5-6-preview
HealthBench57.0length-adjusted; raw 58.7; mean response 2285 charshttps://deploymentsafety.openai.com/gpt-5-6-preview
HealthBench Hard32.7length-adjusted; raw 34.3; mean response 2199 charshttps://deploymentsafety.openai.com/gpt-5-6-preview
HealthBench Consensus95.1length-adjusted; raw 95.2; mean response 2247 charshttps://deploymentsafety.openai.com/gpt-5-6-preview

Migration checks

No linked migration route is available for this model yet.