V3 1 costs $0.560/1M input tokens and $1.68/1M output tokens as of 2026-06-27. DeepSeek publishes this model with a 164K tokens context window. o10 lists V3 1 on SambaNova at routing band C1. API slug deepseek-v3-1. 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.
V3 1 is a chat model from deepseek (slug: deepseek-v3-1). Pick V3 1 for high-volume DeepSeek chat at aggregator prices. It is the V-line, not R1 reasoning. Published input pricing starts at $0.560/1M tokens. Context window: 164K tokens.
Catalog snapshot 2026-06-27.
When should you pick V3 1?
Pick V3 1 for high-volume DeepSeek chat at aggregator prices. It is the V-line, not R1 reasoning. V3 1 is cheaper than most closed flagships. Escalate to DeepSeek R1 or a closed lab only when evals fail.
How does V3 1 differ from sibling models?
V3 1 is cheaper than most closed flagships. Escalate to DeepSeek R1 or a closed lab only when evals fail.
How much does V3 1 cost per million tokens?
V3 1 costs $0.560/1M input tokens and $1.68/1M output tokens in the gateway catalog snapshot (2026-06-27). Endpoint pricing may differ by fulfillment host.
Sourced from gateway catalog snapshot.
Where can you run V3 1?
V3 1 is configured on SambaNova. Known host IDs: sambanova: sambanova/DeepSeek-V3.1. This model is routable through o10 eval-gated routing.
What is V3 1's context window?
V3 1 supports a 164K tokens context window in the gateway catalog snapshot. Context limits may vary by fulfillment host endpoint.
What o10 routing band is V3 1?
V3 1 is classified at o10 routing band C1. 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.
Who makes V3 1?
V3 1 is attributed to source provider deepseek in the o10 catalog. Fulfillment hosts (SambaNova) supply API access; list pricing may differ by venue.
01Deep dive
Specifications
V3 1 in the o10 unified catalog.
V3 1 specifications
Field
Value
o10 slug
`deepseek-v3-1`
Type
text
Band
C1
Routable
Yes
Source provider
deepseek
Primary host
SambaNova
Gateway ID
`deepseek/deepseek-v3.1`
Context window
163,840 tokens
Released
2025-08-21
02Deep dive
Token pricing
Gateway snapshot pricing for V3 1.
V3 1 token pricing
Unit
Price
Input
$0.56/1M tokens
Output
$1.68/1M tokens
03Deep dive
Fulfillment hosts
Upstream venues configured for V3 1.
V3 1 fulfillment routes
Host
Upstream model ID
sambanova
sambanova/DeepSeek-V3.1
04Deep dive
Gateway provider endpoints
Endpoint-level pricing and latency from the gateway catalog.
V3 1 gateway endpoints
Provider
Input ($/1M)
Latency p50
Uptime 1d
deepinfra
$0.21
837.5ms
9994.5%
fireworks
$0.56
-
-
novita
$0.27
1001.5ms
10000.0%
sambanova
$3
-
0.0%
togetherai
$0.6
-
-
05Deep dive
Routing with o10
Eval-gated model selection for this slug.
o10 slug: deepseek-v3-1. Band: C1. Routable: yes.
See [/models/routing](/models/routing) for smart aliases (o10/auto, o10/frontier, o10/squad) and [/kyi](/kyi) for governance.
SourceMethodology
Fulfillment catalog 2026-06-27. Gateway pricing joined where slug match exists.
V3 1 costs $0.560/1M input tokens and $1.68/1M output tokens in the gateway snapshot (2026-06-27). Verify against your provider's published pricing.
What is V3 1's context window?
V3 1 supports 164K tokens in the gateway catalog snapshot. Host-specific endpoints may differ.
Which hosts serve V3 1?
V3 1 (deepseek-v3-1) is configured on: SambaNova. Upstream model IDs are listed in the fulfillment routes section.
Is V3 1 routable through o10?
Yes. V3 1 is routable at band C1. Send model: "deepseek-v3-1" or use an o10 smart routing alias.
How do I call V3 1 via o10?
Use o10 slug "deepseek-v3-1" or gateway ID "deepseek/deepseek-v3.1" depending on your integration. Gateway-compatible endpoints accept OpenAI-style /v1 requests.
How does o10 route this model?
o10 routes V3 1 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.