ModelsDeepSeekDeepSeek V3.1 Terminus
DeepSeek V3.1 Terminus
deepseek/deepseek-v3.1-terminus164k context Compare →- MedianThe median blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
- $0.453
- Most expensiveThe highest blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
- $0.464
- Offers
- 10
- Providers
- 8
Cheapest right now
DeepInfra
via Hugging FaceThe provider's published policy: prompts are not used for training.$0.44 blended / 1M tokens
No change7D- in
- $0.27
- out
- $0.95
- Cached input
- –
Public leaderboards
- Text Arena, style controlThe series the source publishes by default for text since 16 May 2025: ranks corrected for the style of the answers (style control).Thinking setting #116 of 419Best rank in the source's rank spread, 116th to 166th, given the confidence intervals of all ranked models. 140th by score. 1,416 1,406 to 1,426Arena Score · 3,379 votes
- Text Arena, style controlThe series the source publishes by default for text since 16 May 2025: ranks corrected for the style of the answers (style control). #118 of 419Best rank in the source's rank spread, 118th to 166th, given the confidence intervals of all ranked models. 143rd by score. 1,415 1,405 to 1,424Arena Score · 3,609 votes
Source: Arena (opens in a new tab) · Data under the CC BY 4.0 license (creativecommons.org/licenses/by/4.0) · CC BY 4.0 (opens in a new tab) · scores and ranks as published on 28 Oct 2026; the presentation is ours
DeepSeek V3.1 Terminus costs from $0.44 per million tokens (at a 3:1 input:output mix): the cheapest of 3 comparable offers, at DeepInfra, checked on ; 10 offers are listed.
Listed offers, by price
Comparable offersOther offersSolid steps are comparable offers; dashed steps are the other offers, which are not counted in cheapest, median or most expensive.Offers not counted in cheapest, median or most expensive (7)
- $0.363 · NanoGPT via NanoGPT · cannot be designated the cheapest
- $0.44 · DeepInfra via Eden AI · cannot be designated the cheapest
- $0.453 · SiliconFlow via Kilo Gateway · cannot be designated the cheapest
- $0.453 · Glama via Glama · cannot be designated the cheapest
- $0.453 · Martian via Martian · cannot be designated the cheapest
- $0.453 · Nous Portal via Nous Portal · cannot be designated the cheapest
- $0.713 · AtlasCloud via LMRouter · cannot be designated the cheapest
Price historyThe cheapest offer each day, against the lab's official list price when it publishes one. Each day at 00:00 UTC, the offer the API would have selected as the cheapest, with the same exclusions as /cheapest. Blended price, promotions included.
| Day | Cheapest offer | Official list price |
|---|---|---|
| 2026-10-25 | $0.44, DeepInfra | – |
| 2026-10-26 | $0.44, DeepInfra | – |
| 2026-10-27 | $0.44, DeepInfra | – |
| 2026-10-28 | $0.44, DeepInfra | – |
| 2026-10-29 | $0.44, DeepInfra | – |
| 2026-10-30 | $0.44, DeepInfra | – |
| 2026-10-31 | $0.44, DeepInfra | – |
| Day | Cheapest offer | Official list price |
|---|---|---|
| 2026-10-02 | $0.363, NanoGPT | – |
| 2026-10-03 | $0.363, NanoGPT | – |
| 2026-10-04 | $0.363, NanoGPT | – |
| 2026-10-05 | $0.363, NanoGPT | – |
| 2026-10-06 | $0.363, NanoGPT | – |
| 2026-10-07 | $0.363, NanoGPT | – |
| 2026-10-08 | $0.363, NanoGPT | – |
| 2026-10-09 | $0.363, NanoGPT | – |
| 2026-10-10 | $0.363, NanoGPT | – |
| 2026-10-11 | $0.363, NanoGPT | – |
| 2026-10-12 | $0.363, NanoGPT | – |
| 2026-10-13 | $0.363, NanoGPT | – |
| 2026-10-14 | $0.363, NanoGPT | – |
| 2026-10-15 | $0.363, NanoGPT | – |
| 2026-10-16 | $0.363, NanoGPT | – |
| 2026-10-17 | $0.363, NanoGPT | – |
| 2026-10-18 | $0.363, NanoGPT | – |
| 2026-10-19 | $0.44, DeepInfra | – |
| 2026-10-20 | $0.44, DeepInfra | – |
| 2026-10-21 | $0.44, DeepInfra | – |
| 2026-10-22 | $0.44, DeepInfra | – |
| 2026-10-23 | $0.44, DeepInfra | – |
| 2026-10-24 | $0.44, DeepInfra | – |
| 2026-10-25 | $0.44, DeepInfra | – |
| 2026-10-26 | $0.44, DeepInfra | – |
| 2026-10-27 | $0.44, DeepInfra | – |
| 2026-10-28 | $0.44, DeepInfra | – |
| 2026-10-29 | $0.44, DeepInfra | – |
| 2026-10-30 | $0.44, DeepInfra | – |
| 2026-10-31 | $0.44, DeepInfra | – |
| Day | Cheapest offer | Official list price |
|---|---|---|
| 2026-10-01 | $0.363, NanoGPT | – |
| 2026-10-02 | $0.363, NanoGPT | – |
| 2026-10-03 | $0.363, NanoGPT | – |
| 2026-10-04 | $0.363, NanoGPT | – |
| 2026-10-05 | $0.363, NanoGPT | – |
| 2026-10-06 | $0.363, NanoGPT | – |
| 2026-10-07 | $0.363, NanoGPT | – |
| 2026-10-08 | $0.363, NanoGPT | – |
| 2026-10-09 | $0.363, NanoGPT | – |
| 2026-10-10 | $0.363, NanoGPT | – |
| 2026-10-11 | $0.363, NanoGPT | – |
| 2026-10-12 | $0.363, NanoGPT | – |
| 2026-10-13 | $0.363, NanoGPT | – |
| 2026-10-14 | $0.363, NanoGPT | – |
| 2026-10-15 | $0.363, NanoGPT | – |
| 2026-10-16 | $0.363, NanoGPT | – |
| 2026-10-17 | $0.363, NanoGPT | – |
| 2026-10-18 | $0.363, NanoGPT | – |
| 2026-10-19 | $0.44, DeepInfra | – |
| 2026-10-20 | $0.44, DeepInfra | – |
| 2026-10-21 | $0.44, DeepInfra | – |
| 2026-10-22 | $0.44, DeepInfra | – |
| 2026-10-23 | $0.44, DeepInfra | – |
| 2026-10-24 | $0.44, DeepInfra | – |
| 2026-10-25 | $0.44, DeepInfra | – |
| 2026-10-26 | $0.44, DeepInfra | – |
| 2026-10-27 | $0.44, DeepInfra | – |
| 2026-10-28 | $0.44, DeepInfra | – |
| 2026-10-29 | $0.44, DeepInfra | – |
| 2026-10-30 | $0.44, DeepInfra | – |
| 2026-10-31 | $0.44, DeepInfra | – |
Cheapest offer
| Rank | Provider · viaYou buy access through an aggregator: one account and one API that forward your requests to other providers. "Via" names the aggregator; the price is the one it charges you. When "via" says "hosted API", no aggregator is involved: the model belongs to a lab and another provider sells it. | Input $/1M | Output $/1M | Blended $/1MA single price that mixes input and output: 3 input tokens for 1 output token, per million tokens. It makes offers easy to rank; your real cost depends on your own mix. | PrecisionHow finely the model's numbers are stored on the provider's servers. Lower precision (fp8, fp4) is cheaper to run and can slightly change answer quality; "unknown" means the provider doesn't say. | ContextThe maximum amount of text, counted in tokens, the model can take in and write in a single request. Past this limit, the request is refused or cut. | ConditionsWhat a provider says about how it handles your data and who can sign up: training on prompts, processing region, sign-up requirements. Each comes from the provider's published documents; when nothing is published, it stays unknown. | Signals | Offer |
|---|---|---|---|---|---|---|---|---|---|
| 1 | 0.25 | 0.70 | 0.363 | – | 128k | Thinking: Thinking: a mode of the model, not its standard offer. Never designated cheapest while a standard offer exists | |||
| 2 | 0.27 | 0.95 | 0.44 | – | 164k | United States | |||
| 3 | 0.27 | 0.95 | 0.44 | – | 164k | United States | Unverified. No public page for this offer: listed, not designated cheapest | ||
| 4 | 0.27 | 1.00 | 0.453 | fp8 | 164k | Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest | |||
| 5 | 0.27 | 1.00 | 0.453 | – | 164k | Unverified. No public page for this offer: listed, not designated cheapest | |||
| 6 | 0.27 | 1.00 | 0.453 | – | – | worldwide | Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest | ||
| 7 | 0.27 | 1.00 | 0.453 | – | 164k | Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest | |||
| 8 | 0.27 | 1.00 | 0.453 | fp8 | 164k | Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included. | |||
| 9 | 0.285 | 1.00 | 0.464 | – | 131k | ||||
| 10 | 0.45 | 1.50 | 0.713 | fp8 | 131k | Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest |
No training on promptsPrompts may be used for trainingTraining terms not published
backend not named. The router bills this price itself without naming who serves the model.
-
$0.363NanoGPT
NanoGPT
- in
- $0.25
- out
- $0.70
- Precision
- –
- Context
- 128k
No training on promptsThinking: Thinking: a mode of the model, not its standard offer. Never designated cheapest while a standard offer exists
-
$0.44DeepInfra
Hugging Face
- in
- $0.27
- out
- $0.95
- Precision
- –
- Context
- 164k
No training on promptsUnited States
See pricing See pricing at Hugging Face (opens in a new tab)via Hugging Face -
$0.44DeepInfra
Eden AI
- in
- $0.27
- out
- $0.95
- Precision
- –
- Context
- 164k
Prompts may be used for trainingUnited StatesUnverified. No public page for this offer: listed, not designated cheapest
Seller's site: Eden AI (opens in a new tab)No public price page for this model -
$0.453SiliconFlow
Kilo Gateway
- in
- $0.27
- out
- $1.00
- Precision
- fp8
- Context
- 164k
Training terms not publishedUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
Go to offer Go to offer at Kilo Gateway (opens in a new tab)via Kilo Gateway -
$0.453Glama
Glama
- in
- $0.27
- out
- $1.00
- Precision
- –
- Context
- 164k
No training on promptsUnverified. No public page for this offer: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.
Seller's site: Glama (opens in a new tab)No public price page for this model -
$0.453Martian
Martian
- in
- $0.27
- out
- $1.00
- Precision
- –
- Context
- –
Training terms not publishedworldwideUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.
-
$0.453Nous Portal
Nous Portal
- in
- $0.27
- out
- $1.00
- Precision
- –
- Context
- 164k
Prompts may be used for trainingUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.
See pricing See pricing at Nous Portal (opens in a new tab)via Nous Portal -
$0.453SiliconFlow
OpenRouter
- in
- $0.27
- out
- $1.00
- Precision
- fp8
- Context
- 164k
Training terms not publishedFee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
-
$0.464Featherless
direct
- in
- $0.285
- out
- $1.00
- Precision
- –
- Context
- 131k
Training terms not published
-
$0.713AtlasCloud
LMRouter
- in
- $0.45
- out
- $1.50
- Precision
- fp8
- Context
- 131k
Training terms not publishedUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
No offer matches these filters.
Blended = (3 × input + output) / 4, per million tokens. Prices in USD, converted at the ECB rate when the provider bills in another currency.
Monthly cost for your workload
Computed by the API for the three cheapest offers, per 30-day month.- DeepInfra$30.45per month
- Featherless$32.10per month+$1.65 vs the cheapest
- SiliconFlow$31.20per month+$0.75 vs the cheapest
The estimate could not be updated. Try again in a moment.
Compare DeepSeek V3.1 Terminus with
Related models
More from DeepSeek
- DeepSeek V4.1 Flash
- DeepSeek V4.1 Flash 1017
- DeepSeek V4 Flash 0731
- DeepSeek V4 Pro 0813
- DeepSeek V3.2
- DeepSeek V3.1
Same index family
Use this data
The index is queryable. The API is free to use.curl https://api.inferindex.dev/cheapest?model=deepseek/deepseek-v3.1-terminusclaude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp