DeepSeek R1 costs $1.35/1M input tokens and $5.40/1M output tokens as of 2026-06-27. DeepSeek publishes this model with a 128K tokens context window. o10 lists DeepSeek R1 on DeepSeek at routing band C4. API slug deepseek-r1. Verify list prices against the venue you call.
Last updated: 2026-06-27. Full catalog. Reference prices are dated snapshots. Compare total cost and measured task quality before choosing a route.
DeepSeek R1 is a chat model from deepseek (slug: deepseek-r1). Pick DeepSeek R1 when you want DeepSeek's reasoning model at open-weight prices. It is not a cheap V3 chat default. Published input pricing starts at $1.35/1M tokens. Context window: 128K tokens.
Catalog snapshot 2026-06-27.
Pick DeepSeek R1 when you want DeepSeek's reasoning model at open-weight prices. It is not a cheap V3 chat default. DeepSeek R1 is R1 (reasoning). DeepSeek V3 is the high-volume chat sibling. Do not treat them as interchangeable.
DeepSeek R1 is R1 (reasoning). DeepSeek V3 is the high-volume chat sibling. Do not treat them as interchangeable.
DeepSeek R1 costs $1.35/1M input tokens and $5.40/1M output tokens in the gateway catalog snapshot (2026-06-27). Endpoint pricing may differ by fulfillment host.
Sourced from gateway catalog snapshot.
DeepSeek R1 is configured on DeepSeek. Known host IDs: deepseek: deepseek/deepseek-r1. This model is routable through o10 eval-gated routing.
DeepSeek R1 supports a 128K tokens context window in the gateway catalog snapshot. Context limits may vary by fulfillment host endpoint.
DeepSeek R1 is classified at o10 routing band C4. Bands group models by cost tier and eval profile: C0 (economy), C1 (standard), C2 (capable), C3/C4 (frontier). Production routing is enabled for this slug.
DeepSeek R1 is attributed to source provider deepseek in the o10 catalog. Fulfillment hosts (DeepSeek) supply API access; list pricing may differ by venue.
DeepSeek R1 in the o10 unified catalog.
| Field | Value |
|---|---|
| o10 slug | `deepseek-r1` |
| Type | text |
| Band | C4 |
| Routable | Yes |
| Source provider | deepseek |
| Primary host | DeepSeek |
| Gateway ID | `deepseek/deepseek-r1` |
| Context window | 128,000 tokens |
| Released | 2025-01-20 |
Gateway snapshot pricing for DeepSeek R1.
| Unit | Price |
|---|---|
| Input | $1.35/1M tokens |
| Output | $5.4/1M tokens |
Upstream venues configured for DeepSeek R1.
| Host | Upstream model ID |
|---|---|
| deepseek | deepseek/deepseek-r1 |
Endpoint-level pricing and latency from the gateway catalog.
| Provider | Input ($/1M) | Latency p50 | Uptime 1d |
|---|---|---|---|
| bedrock | $1.35 | 311.5ms | 10000.0% |
| deepinfra | $0.5 | 652ms | 10000.0% |
Eval-gated model selection for this slug.
o10 slug: deepseek-r1. Band: C4. Routable: yes.
See [/models/routing](/models/routing) for smart aliases (o10/auto, o10/frontier, o10/squad) and [/kyi](/kyi) for governance.
Fulfillment catalog 2026-06-27. Gateway pricing joined where slug match exists.
DeepSeek R1 costs $1.35/1M input tokens and $5.40/1M output tokens in the gateway snapshot (2026-06-27). Verify against your provider's published pricing.
DeepSeek R1 supports 128K tokens in the gateway catalog snapshot. Host-specific endpoints may differ.
DeepSeek R1 (deepseek-r1) is configured on: DeepSeek. Upstream model IDs are listed in the fulfillment routes section.
Yes. DeepSeek R1 is routable at band C4. Send model: "deepseek-r1" or use an o10 smart routing alias.
Use o10 slug "deepseek-r1" or gateway ID "deepseek/deepseek-r1" depending on your integration. Gateway-compatible endpoints accept OpenAI-style /v1 requests.
o10 routes DeepSeek R1 only when per-use-case evals clear at your quality floor. Band C4 indicates cost tier. See /kyi for governance and /models/routing for smart aliases.
The o10 slug is "deepseek-r1"; the unified gateway ID is "deepseek/deepseek-r1". Host IDs: deepseek: deepseek/deepseek-r1. Pricing snapshot date: 2026-06-27.
DeepSeek R1 is hosted as deepseek: deepseek/deepseek-r1. o10 maps those upstream IDs to slug "deepseek-r1".