FastRouter
20 model routes currently listed at zero price.
https://api.fastrouter.ai/v1Models mentioned
fastrouter/autogoogle/gemini-3.1-flash-image-previewopenai/gpt-oss-120b:freeopenai/gpt-oss-20b:freegoogle/gemini-2.5-flash-imageblack-forest-labs/flux-devblack-forest-labs/flux-kontext-problack-forest-labs/flux-pro-2.0bytedance/seedream-4.0bytedance/seedream-4.5google/gemini-3-pro-image-previewgoogle/gemma-4-26b-a4b-itgoogle/gemma4-26b:freeleonardo-ai/lucid-originleonardo-ai/lucid-realismleonardo-ai/phoenixnvidia/nemotron-3-nano-30b:freenvidia/nemotron-3-super:freeopenai/omni-moderation-latestsarvam/sarvam-105b:freeEquivalent paid value
How this was valued: The published allowance or a defensible paid comparison is not precise enough to calculate.
Model-specific free routes have no published finite quota or like-for-like paid price.
Limits and terms
- Published Numeric Limits
- No
- Caveat
- The free gateway plan alone is BYOK/pass-through; only the model-specific free routes below are zero-priced inference.
What happens to your prompts?
The terms grant broad perpetual rights to store and use inputs and outputs for debugging and service improvement.
- Plan Scope
- FastRouter gateway and chat services; the selected model provider's separate terms govern model-side input and output use.
- Prompt Retention
- FastRouter's terms grant it a perpetual license to host, store, transfer, reproduce, adapt, and otherwise process inputs and outputs for service delivery, debugging, optimization, improvement, and compliance; no fixed deletion deadline is stated.
- Response Retention
- The same license and undefined retention apply to outputs.
- Ordinary Logging
- Account, service, API, technical, and usage information is processed under FastRouter's privacy policy, while downstream provider telemetry is independently governed.
- Model Training
- The terms do not provide a gateway-wide no-training promise. Downstream providers can impose their own training rules, and FastRouter's own broad improvement license is not limited to metadata.
- Product Improvement
- Inputs and outputs may be used to optimize and improve the service and API keys under an express perpetual license.
- Human Or Operator Access
- Content may be processed for chat, debugging, optimization, improvement, and legal compliance; no operator-blind or zero-access commitment is published.
- Subprocessors And Routing
- Requests go to model providers including Amazon, Anthropic, Azure, DeepInfra, DeepSeek, OpenAI, Google, Groq, Perplexity, xAI, Meta, and fal.ai, each under separate terms.
- Deletion Controls
- not documented
- Caveat
- The broad perpetual content license and provider-specific rules make this unsuitable for sensitive prompts absent a separate written agreement.
Governing documents
- Terms Of Service
- https://fastrouter.ai/terms
- Privacy Policy
- https://fastrouter.ai/privacy
- Model Provider Terms
- https://fastrouter.ai/llm-model-terms
Primary sources
Before you build with FastRouter
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 20 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.fastrouter.ai/v1, but the provider's current API reference remains authoritative for paths, authentication, and request shape.
Confirm account and billing boundaries
The public evidence does not settle whether an account is required. Confirm the signed-in flow before treating anonymous or credential-free access as available. The payment-card requirement is conditional or not clearly documented. Treat signup friction and billing exposure as unresolved until the account flow confirms them. 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 “Not private”: The terms grant broad perpetual rights to store and use inputs and outputs for debugging and service improvement. 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 5 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.