How much does V3 2 cost per million tokens?
V3 2 costs $0.280/1M input tokens and $0.420/1M output tokens in the gateway catalog snapshot (2026-06-27). Endpoint pricing may differ by fulfillment host.
Sourced from gateway catalog snapshot.
V3 2 costs $0.280/1M input tokens and $0.420/1M output tokens as of 2026-06-27. Deepseek publishes this model with a 128K tokens context window. o10 lists V3 2 on AWS Bedrock and SambaNova at routing band C1.
Last updated: 2026-06-27. Full catalog
V3 2 costs $0.280/1M input tokens and $0.420/1M output tokens in the gateway catalog snapshot (2026-06-27). Endpoint pricing may differ by fulfillment host.
Sourced from gateway catalog snapshot.
V3 2 is configured on AWS Bedrock and SambaNova. Each host maps to an upstream model ID listed in the fulfillment routes table. This model is routable through o10 eval-gated routing.
V3 2 supports a 128K tokens context window in the gateway catalog snapshot. Context limits may vary by fulfillment host endpoint.
Gateway snapshot pricing for V3 2.
| Unit | Price |
|---|---|
| Input | $0.28/1M tokens |
| Output | $0.42/1M tokens |
Upstream venues configured for V3 2.
| Host | Upstream model ID |
|---|---|
| bedrock | bedrock/deepseek.v3.2 |
| bedrock | sambanova/DeepSeek-V3.2 |
Eval-gated model selection for this slug.
o10 slug: deepseek-v3-2. Band: C1. Routable: yes.
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 deepseek and host providers.
V3 2 costs $0.280/1M input tokens and $0.420/1M output tokens in the gateway snapshot (2026-06-27). Verify against your provider's published pricing.
V3 2 supports 128K tokens in the gateway catalog snapshot. Host-specific endpoints may differ.
V3 2 (deepseek-v3-2) is configured on: AWS Bedrock and SambaNova. Upstream model IDs are listed in the fulfillment routes section.
Yes. V3 2 is routable at band C1. Send model: "deepseek-v3-2" or use an o10 smart routing alias.
Use o10 slug "deepseek-v3-2" or gateway ID "deepseek/deepseek-v3.2" depending on your integration. Gateway-compatible endpoints accept OpenAI-style /v1 requests.
o10 routes V3 2 only when per-use-case evals clear at your quality floor. Band C1 indicates cost tier. See /kyi for governance and /models/routing for smart aliases.