Google Travel Impact Model API
Browse all Google APIs41
AI ReadinessFoundational (D-)41/100
Official vendor OpenAPI document · agent-readyData EnrichmentData TransformationapiKey1 EndpointsREST
For Agents
Compute per-passenger CO2e flight emissions for a specific carrier, flight number, and date so an agent can surface sustainability data alongside fare options.
Use for: I need to estimate CO2 emissions for a flight from JFK to LHR, Compare carbon emissions across cabin classes for a specific itinerary, Retrieve the per-passenger emissions for a United Airlines flight tomorrow, Find the lowest-emission option among three candidate flights
Not supported: Does not handle flight booking, fare pricing, or seat selection - use for per-flight CO2e emissions estimates only.
The Travel Impact Model API returns carbon dioxide equivalent (CO2e) emission estimates for individual flight legs based on Google's Travel Impact Model. Given an origin airport, destination airport, operating carrier, flight number, and departure date, the API returns per-passenger emissions broken out by cabin class along with the model version used. It is designed for travel platforms, sustainability dashboards, and reporting systems that need consistent, comparable flight emissions data.
Install Jentic One Beta
Connect the Travel Impact Model API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Travel Impact Model API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fgoogleapis.com%2Ftravelimpactmodel" | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fgoogleapis.com%2Ftravelimpactmodel" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
Capabilities
What an agent can do with Travel Impact Model API.
Compute CO2e emissions per cabin class for a specific flight leg
Return the model version stamp so historical estimates remain reproducible
Score multiple flight options in a single batch request for itinerary comparison
Surface per-passenger emissions to power sustainability badges in booking flows
Provide emissions data for carbon-aware travel policy enforcement
Use Cases
Patterns agents use Travel Impact Model API for, with concrete tasks.
★ Sustainability Badges in Flight Search
Online travel agencies and metasearch engines display per-flight CO2e estimates next to fare cards so travelers can factor sustainability into booking decisions. The Travel Impact Model API returns emissions per cabin class for each carrier, flight number, and date combination, letting the front end render a green-leaf indicator or a numeric kilogram value. Integration is typically a single POST per fare list, and the model version is captured for audit consistency.
Call computeFlightEmissions for AA100 JFK to LAX on 2026-07-15 and return economy CO2e in kilograms
Corporate Travel Carbon Reporting
Corporate travel managers reconcile booked itineraries against an emissions model to produce quarterly Scope 3 disclosures. By passing each leg through the Travel Impact Model API, finance and ESG teams obtain comparable numbers across carriers and routes without maintaining their own emissions model. The model_version field stamped on every response keeps historical reports reproducible even after Google updates the underlying methodology.
Iterate over 412 Q3 booked legs and accumulate total economy-class CO2e per traveler
Carbon-Aware Travel Policy Enforcement
Travel platforms enforce internal sustainability policies by ranking eligible flights by emissions before applying price filters. The API returns a single emissions object per leg with a deterministic model version, enabling the policy engine to apply consistent thresholds (for example, exclude options more than 20 percent above the lowest-emission candidate). The single endpoint design keeps integration time low and avoids the need to mirror Google's underlying datasets.
Score five candidate flights and recommend the option with the lowest economy-class CO2e
AI Agent Sustainability Assistant
An AI travel assistant integrated through Jentic discovers the Travel Impact Model API by intent search, loads the request schema, and submits a flight emissions request as part of a conversational booking flow. Because the API has a single operation and a small input schema, it is well-suited to function-calling workflows where the agent must combine fare data, emissions data, and traveler preferences into one recommendation. Jentic isolates the Google API key in its vault so the agent never receives the raw credential.
Search Jentic for compute flight emissions, load the schema, and call it for the user's selected itinerary
Key Endpoints
1 endpoints — the travel impact model api returns carbon dioxide equivalent (co2e) emission estimates for individual flight legs based on google's travel impact model.
METHOD
PATH
DESCRIPTION
POST
/v1/flights:computeFlightEmissions
Compute CO2e emissions for one or more flight legs
POST
/v1/flights:computeFlightEmissions
Compute CO2e emissions for one or more flight legs
Jentic AI Readiness Score
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
T
Travel Impact Model API
- Foundational (D-)41/100
73
Foundational Compliance56
Developer Experience & Jentic Compatibility18
AI-Readiness & Agent Experience94
Agent Usability100
Security50
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.0
Show dimension breakdown
73
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: A-Signals: 4
94%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
0%
Specification Validity
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
100%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
56
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: CSignals: 4
0%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
25%
Response Coverage
Percentage of operations with complete response definitions (success, client error, server error).
100%
Tooling Readiness
Health of API ingestion, bundling, and resolution within Jentic pipelines.
18
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: FSignals: 4
70%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
0%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
0%
Summary Coverage
Coverage of summaries across operations/tags/info.
94
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: A+Signals: 1
94%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
100
Security
Trust, risk posture, and security compliance.
Grade: A+Signals: 1
100%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
50
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: C-Signals: 1
50%
Descriptive Richness
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Travel Impact Model API by hand means provisioning a Google API key, attaching it to each request for quota, and assembling the per-flight market, carrier, and date fields yourself. Through Jentic you install once, import the Travel Impact Model API from the API Directory, store the API key once, and your agent calls it.
Permission scoping
This API exposes a single emissions operation and the flight details travel in the request body, so scope by operation: limit the agent to the computeFlightEmissions operation it needs. You choose the operations it may call, so nothing beyond that estimate is included unless you add it.
Credential isolation
Your Travel Impact Model API key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'compute flight emissions', and Jentic returns the computeFlightEmissions operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Travel Impact Model API through Jentic.
What authentication does the Travel Impact Model API use?
The Travel Impact Model API uses a Google API key passed as the api_key query parameter on the single POST endpoint. Through Jentic, the API key is stored encrypted in your Jentic One instance and only a scoped reference is exposed to the agent at execution time.
Can I compute emissions for multiple flights in one request with the Travel Impact Model API?
Yes. The /v1/flights:computeFlightEmissions endpoint accepts a flights array, so a single request can score an entire itinerary or candidate fare list and return one emissions object per leg with the model version stamp.
What are the rate limits for the Travel Impact Model API?
Google enforces standard Cloud project quotas on the Travel Impact Model API, defaulting to 60 requests per minute per project. Higher quotas can be requested in the Google Cloud Console; check the Travel Partner documentation for the current default for your project.
How do I get flight emissions through Jentic for the Travel Impact Model API?
Install the Jentic SDK with pip install jentic, search for compute flight emissions, load the schema for the computeFlightEmissions operation, then execute it with origin, destination, operating carrier code, flight number, and departure date. Jentic returns the same emissions and model_version response that the raw API does.
Is the Travel Impact Model API free to use?
Google currently offers the Travel Impact Model API at no cost for travel partners and developers, subject to project quotas and acceptable use terms. Confirm current pricing in the Google Cloud Console before high-volume rollout.
Why might the Travel Impact Model API return no emissions for a flight?
If the operating carrier, flight number, or route is not present in Google's underlying schedule and aircraft data, the API returns an empty emissions object for that leg. Verify the IATA airport codes, two-letter carrier code, and that the flight number exists for the requested departure date.
Can I limit what my agent is allowed to do with the Travel Impact Model API?
Yes. Because you self-host Jentic One, your own rules decide which operations and credentials the agent may use, and this API exposes only a single computeFlightEmissions operation. You scope by operation, granting the agent just that emissions call so it cannot reach anything beyond the per-flight CO2e estimate. The Google API key is injected at execution time and never enters the agent's prompt or context, and the agent only gets what you explicitly allow.
GET STARTED