Api.Airforce
28 model routes currently listed at zero price.
https://api.airforce/v1Models mentioned
codestral-2508codestral-latestgemma3-270m:freeglm-4.7-flashgpt-oss-20bkimi-k2.7-codellama-instantministral-14b-2512ministral-14b-latestministral-3b-2512ministral-3b-latestministral-8b-2512ministral-8b-latestmistral-code-fim-latestmistral-code-latestmistral-large-2512mistral-large-latestmistral-tiny-2407mistral-tiny-latestopen-mistral-nemoopen-mistral-nemo-2407rnj-1suno-v4.5suno-v5suno-v5.5unmoderated-gptvoxtral-small-2507voxtral-small-latestEquivalent paid value
How this was valued: Documented free-plan envelope of 1 request/minute and 1,000 requests/day multiplied by the 4,096-token per-request completion cap that the live catalog documents for every free-tier chat model, priced at Api.Airforce's own paid per-token USD rates (customer_price_table, micro-USD, snapshot 2026-09-13). The headline assigns the shared request pool to rnj-1, the most expensive chat model carrying the catalog's free-tier marker (tier "free", 31 models); model rows are alternative maxima for the same shared pool and are not additive. Assumes uninterrupted saturation with no latency, concurrency, availability, or fair-use loss, and counts completion tokens only because no per-request input ceiling is documented. The provider's confirmed but unpublished per-model daily token cap can only reduce the realizable value, so the figures are strict upper bounds. Free-tier markers in the rotating catalog are volatile, and authenticated runtime verification of premium-looking free-tier entries such as rnj-1 and mistral-large-2512 has not been performed.
Limits and terms
- Requests Per Minute
- 1
- Requests Per Day
- 1,000
- Per Model Daily Token Cap
- Yes
- Per Model Daily Token Cap Amount
- unpublished
What happens to your prompts?
Content can be retained for safety without a fixed TTL, while training and upstream handling are not fully documented.
- Plan Scope
- Api.Airforce website, dashboard, and inference gateway; downstream model-provider policies also apply.
- Prompt Retention
- Submitted content is retained as needed for abuse, fraud, illegal-activity detection, and service safety, but no fixed content-retention period is published.
- Response Retention
- Responses may be processed by third-party model providers; a gateway-specific output-retention period is not documented.
- Ordinary Logging
- Request counts, IP addresses, model usage, request logs, subscription data, and authentication information are collected for operations, analytics, security, rate limits, abuse prevention, and improvement.
- Model Training
- not documented
- Product Improvement
- Analytics and request logs may be used to improve and maintain the platform; whether prompt content itself is used for model or product improvement is not clearly stated.
- Human Or Operator Access
- Content can be processed for abuse, fraud, illegal-activity detection, and safety; the policy does not define operator roles or access limitations.
- Subprocessors And Routing
- Requests and outputs may be handled by changing third-party model providers under their own terms and policies.
- Deletion Controls
- Closing an account disables access and releases identifiers but is described as a reversible soft deletion. EU/EEA and equivalent-region users may request erasure, subject to legal-retention exceptions.
- Caveat
- The policy acknowledges content retention without a duration and does not publish a no-training commitment. Do not infer privacy from the service's proxy role.
Governing documents
- Terms Of Service
- https://api.airforce/terms/
- Privacy Policy
- https://api.airforce/privacy/
Eligibility
- Account Required
- Yes
- Payment Method Required
- No
Primary sources
Before you build with Api.Airforce
Read the classification narrowly
This record has current first-party evidence for some zero-cost hosted inference. The label describes the bounded offer supported by evidence on 2026-09-19; it does not guarantee permanence, production suitability, uptime, latency, model quality, or access from every region.
Resolve the live model route
This snapshot records 28 model IDs. Match the exact ID against the provider's live catalog before using it in code; zero-price routes and aliases can rotate while an older documentation page remains online. The recorded base endpoint is https://api.airforce/v1, but the provider's current API reference remains authoritative for paths, authentication, and request shape.
Confirm account and billing boundaries
An account is required, so public catalog evidence cannot by itself prove the limits, balance, or billing behavior attached to your workspace. The reviewed evidence explicitly says no payment card is required. Re-check the signup flow because eligibility and billing controls can change after the snapshot. The equivalent paid value shown here prices a documented allowance where possible; it is not cash, guaranteed savings, or protection from overage.
Re-read the prompt policy for your plan
This record classifies the reviewed handling as “Partially private”: Content can be retained for safety without a fixed TTL, while training and upstream handling are not fully documented. Provider policies can distinguish free, paid, enterprise, opted-in, and feature-specific traffic, so verify the governing terms for the exact account and route that will receive your data.
Follow the evidence, then re-check it
The record links 7 first-party sources covering the offer, catalog, limits, pricing, terms, privacy, or adoption evidence available to the audit. Prefer the newest governing document or live catalog when sources disagree, and submit a correction when a provider changes a material term.
Match the quota to the workload shape
Translate the published allowance into the traffic pattern you actually expect instead of comparing headline totals alone. A daily token pool can look generous while a low requests-per-minute or concurrency ceiling blocks interactive bursts; a high request limit can still fail a long-context job when input, output, or per-request tokens are capped. Separate prompt tokens from generated tokens, include retries and tool calls, and test the largest realistic payload. If the provider documents more than one limit window, the tightest window at your peak load is the practical ceiling. Research, experimental, and community access can also carry eligibility or fair-use constraints that cannot be modeled as a simple number.
Plan fallback without changing the rules
A fallback should preserve more than API syntax. Confirm that the substitute route supports the required modality, context length, streaming behavior, structured output, tools, and safety controls, then compare its prompt-retention and training terms. An OpenAI-compatible request shape does not make providers operationally or contractually equivalent. Decide which errors may trigger a retry, cap retry storms, and prevent an exhausted free route from silently switching to a billable model. If deterministic output matters, record the model revision and sampling settings; rotating aliases and free-model pools can change behavior even when the endpoint remains available.
Monitor the offer as a dependency
Capture the model ID, response model field, rate-limit headers, usage fields, latency, HTTP status, and any provider request identifier for each test. Watch for authorization failures, quota exhaustion, catalog removal, policy revisions, and dashboard balance changes as separate failure modes. Re-check the provider’s live catalog and governing pages on a schedule proportionate to the workload’s importance, and keep the dated sources that supported your decision. Free capacity is especially suitable for prototypes, evaluations, fallbacks, and bounded workloads when the application can tolerate change; a production dependency still needs observability, an exit path, and an owner responsible for re-verification.
Test one complete request before scaling
Start with the smallest permitted request using the exact credential, model ID, endpoint, and account type you intend to deploy. Record the HTTP status, response headers, usage fields, latency, and any dashboard balance change. Then exercise the failure path: an invalid model, an exhausted quota, or a rate-limit response should fail clearly without silently switching to a paid route. If the provider supports streaming or tool calls, validate those features separately because a free model can expose a narrower capability set than its paid counterpart. Keep a budget ceiling outside the application whenever billing is possible, and avoid sending sensitive data until the observed route matches the reviewed data agreement.