Jina AI Search Foundation logo

Jina AI Search Foundation

Embeddings 2.7/10

Jina AI provides best-in-class multilingual embeddings and rerankers through a unified Search Foundation API, with free tokens auto-granted to every new key and no credit card required.

Jina AI Search Foundation scores 2.7/10 for free value in Embeddings. The main constraint: 10 million free tokens per new API key (shared across Embeddings, Reranker, Reader, Classifier and DeepSeek/segment APIs), no credit card. Free tier: 100 RPM & 100K TPM for embeddings/rerank. jina-embeddings-v4 is additionally free (throttled).

Category Embeddings Kind Hosted embeddings + reranker API (free tokens) Caveats 10M tokens is a one-time grant shared across all Jina APIs (not monthly-refilling); throughput on the free tier is capped at 100 RPM; some models (v4) are CC-BY-NC / noncom. Card required No Eligibility anyone

Free value score

2.7 / 10
Show the math
Overall 2.7/10
value = 2.7/100
weighted_components_v1
Free value 1/10
value = 0 $/mo
fixed_log_v1
Search fit 4.1/10
value = 4.1/100
policy_score_v1
Access 4.8/10
value = 4.8/100
policy_score_v1

Key metrics

10M tokens Token grant one-time grant; kept separate from monthly scoring value
1 tokens/mo Monthly tokens policy_default: Conservative scoring fallback: no renewable monthly token allowance is published in this item.
100K tokens/min Tokens/min
0.001 GB Storage policy_default: Conservative scoring fallback: no comparable included storage allowance is published in this item.
No daily cap Requests/day 100 RPM
Yes Commercial use v4 noncom

What you get

Confirmed on official site: 10M free tokens per key, no credit card

Single key covers embeddings, reranker, reader, and classifier

OpenAI-compatible embeddings schema (api.jina.ai/v1/embeddings)

Strong multilingual + multimodal models (v3, v4, clip-v2)

Limitations

  • 10M one-time token grant

    Every new API key receives exactly 10 million free tokens shared across all Jina APIs (Embeddings, Reranker, Reader, Classifier, DeepSearch); once exhausted, paid top-up is required.

  • 100 RPM / 100K TPM (Embeddings & Reranker)

    Free API keys are capped at 100 requests per minute and 100,000 tokens per minute on the Embedding and Reranker APIs.

  • 2 concurrent requests on free tier

    Free keys allow only 2 concurrent in-flight requests across all Jina APIs, limiting parallelism in batch workloads.

  • 25 RPM / 25K TPM (Classifier API)

    The Classifier train and classify endpoints are limited to 25 RPM and 25,000 TPM on free keys.

  • 50 RPM (DeepSearch)

    Free keys are limited to 50 requests per minute on the DeepSearch endpoint.

  • jina-embeddings-v4 noncom only

    The jina-embeddings-v4 model is released under the Qwen Research License (CC BY-NC), which prohibits commercial or production use; only v3 and older models can be used commercially via the API.

  • jina-embeddings-v4 intentionally throttled

    Because Jina cannot monetize v4, they intentionally cap its API throughput to control infrastructure costs; high-volume use is explicitly unsupported and callers are directed to self-host.

  • Cold starts on serverless models

    Low-traffic models are offloaded during idle periods; the first request after inactivity triggers a warm-up delay of several seconds.

  • Token pool shared across all APIs

    The 10M free tokens are shared across Reader, Embeddings, Reranker, Classifier, and DeepSearch — Reader searches alone cost 10,000 tokens per request, so heavy multi-product use can drain the pool quickly.

Sources

  • "We offer a welcoming free trial to new users, which includes ten millions tokens for use with any of our models, facilitated by an auto-generated API key."

    https://jina.ai/embeddings/

  • "Free: 100 RPM, 100K TPM, 2 concurrent requests ... Premium: 5,000 RPM, 50M TPM, 500 concurrent requests ... Additionally, there is an IP-based rate limit of 10,000 requests per 60 seconds"

    https://jina.ai/embeddings/

  • "On English MTEB, it achieves 71.7 average, outperforming Qwen3-0.6B with instructions (70.5) and jina-embeddings-v3 (65.7)."

    https://jina.ai/models/jina-embeddings-v5-text-small/

  • "Jina AI successfully raised a total of $39 million over two funding rounds. This included a Series A round of $30 million in November 2021, led by Canaan"

    https://app.dealroom.co/companies/jina_ai
embeddings reranker rag free-tokens multilingual
Open service Source ← All Embeddings