How much does Gemini Embedding 2 cost per million tokens?
Gemini Embedding 2 costs $0.200/1M input tokens in the gateway catalog snapshot (2026-06-27). Endpoint pricing may differ by fulfillment host.
Sourced from gateway catalog snapshot.
Gemini Embedding 2 costs $0.200/1M input tokens as of 2026-06-27. Google publishes this model. o10 lists Gemini Embedding 2 on Google Gemini at routing band C0.
Last updated: 2026-06-27. Full catalog
Gemini Embedding 2 costs $0.200/1M input tokens in the gateway catalog snapshot (2026-06-27). Endpoint pricing may differ by fulfillment host.
Sourced from gateway catalog snapshot.
Gemini Embedding 2 is configured on Google Gemini. Each host maps to an upstream model ID listed in the fulfillment routes table. This model is cataloged but not marked routable for chat routing.
Gemini Embedding 2 context limits depend on the fulfillment host. Check the specifications table for endpoint-specific limits.
Gateway snapshot pricing for Gemini Embedding 2.
| Unit | Price |
|---|---|
| Input | $0.2/1M tokens |
Upstream venues configured for Gemini Embedding 2.
| Host | Upstream model ID |
|---|---|
| gemini | gemini/gemini-embedding-2 |
Eval-gated model selection for this slug.
o10 slug: gemini-embedding-2. Band: C0. Routable: no.
See [/models/routing](/models/routing) for smart aliases (o10/auto, o10/frontier, o10/squad) and [/kyi](/kyi) for governance.
Gateway catalog snapshot 2026-06-27. Fulfillment catalog synced from o10 control plane. Verify list prices against google and host providers.
Gemini Embedding 2 costs $0.200/1M input tokens in the gateway snapshot (2026-06-27). Verify against your provider's published pricing.
Context limits for Gemini Embedding 2 vary by fulfillment host. See the specifications table on this page.
Gemini Embedding 2 (gemini-embedding-2) is configured on: Google Gemini. Upstream model IDs are listed in the fulfillment routes section.
No. Gemini Embedding 2 is cataloged but not enabled for chat routing in the current fulfillment config.
Use o10 slug "gemini-embedding-2" or gateway ID "google/gemini-embedding-2" depending on your integration. Gateway-compatible endpoints accept OpenAI-style /v1 requests.
o10 routes Gemini Embedding 2 only when per-use-case evals clear at your quality floor. Band C0 indicates cost tier. See /kyi for governance and /models/routing for smart aliases.