Deepseek V4 Flash costs $0.140/1M input tokens and $0.280/1M output tokens as of 2026-06-27. Deepseek publishes this model with a 1M tokens context window. o10 lists Deepseek V4 Flash on DeepSeek at routing band C2.
Last updated: 2026-06-27. Full catalog
Deepseek V4 Flash costs $0.140/1M input tokens and $0.280/1M output tokens in the gateway catalog snapshot (2026-06-27). Endpoint pricing may differ by fulfillment host.
Sourced from gateway catalog snapshot.
Deepseek V4 Flash is configured on DeepSeek. Each host maps to an upstream model ID listed in the fulfillment routes table. This model is routable through o10 eval-gated routing.
Deepseek V4 Flash supports a 1M tokens context window in the gateway catalog snapshot. Context limits may vary by fulfillment host endpoint.
Gateway snapshot pricing for Deepseek V4 Flash.
| Unit | Price |
|---|---|
| Input | $0.14/1M tokens |
| Output | $0.28/1M tokens |
Upstream venues configured for Deepseek V4 Flash.
| Host | Upstream model ID |
|---|---|
| deepseek | deepseek/deepseek-v4-flash |
Eval-gated model selection for this slug.
o10 slug: deepseek-v4-flash. Band: C2. 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.
Deepseek V4 Flash costs $0.140/1M input tokens and $0.280/1M output tokens in the gateway snapshot (2026-06-27). Verify against your provider's published pricing.
Deepseek V4 Flash supports 1M tokens in the gateway catalog snapshot. Host-specific endpoints may differ.
Deepseek V4 Flash (deepseek-v4-flash) is configured on: DeepSeek. Upstream model IDs are listed in the fulfillment routes section.
Yes. Deepseek V4 Flash is routable at band C2. Send model: "deepseek-v4-flash" or use an o10 smart routing alias.
Use o10 slug "deepseek-v4-flash" or gateway ID "deepseek/deepseek-v4-flash" depending on your integration. Gateway-compatible endpoints accept OpenAI-style /v1 requests.
o10 routes Deepseek V4 Flash only when per-use-case evals clear at your quality floor. Band C2 indicates cost tier. See /kyi for governance and /models/routing for smart aliases.