DeepSeek language model

DeepSeek V4 Pro

DeepSeek's larger V4 model: 1.6T total parameters (49B active), text-only, with a 1M-token context and selectable thinking effort. previewed in April 2026 and generally available from 2026-08-13, it sits above V4.1 Flash, which costs less and also reads images.

01

price

$1.32/M

input tokens

$3.96/M

output tokens

$0.044/M

cached input

per 1M tokens. octomind bills the listed provider price, with no markup, on every plan, including the free one (pay as you go from credits).

  • since 2026-08-16 16:00 UTC DeepSeek's own api bills peak and off-peak; the listed price is the peak rate, and off-peak is half ($0.66 / $1.98).
  • on DeepSeek's api, peak is 01:00-04:00 and 06:00-10:00 UTC Monday-Friday, excluding Chinese public holidays.

02

what real work costs

workloadcost
one chat reply 3,000 tokens in, 500 out $0.0059
summarise a 100-page report 50,000 tokens in, 1,500 out, one request $0.07
1,000 classification calls 500 tokens in, 20 out, per call $0.74
coding-agent session 2M tokens in across ~60 turns, 60,000 out, no cache $2.88
same session, cached 85% of input read from the prompt cache, the rest written to it $0.71

at the listed rate. token counts are typical sizes, not measurements.

03

specs

provider
DeepSeek
context window
1M tokens — ≈ 1,500 pages of prose or 100,000 lines of code
max output
384k tokens
input
text
output
text
structured output
yes — JSON schema
reasoning mode
yes
prompt caching
yes — cache hits at $0.044/M
weights
open — MIT
released
April 24, 2026
status
live
model id
deepseek-v4-pro

integration notes

  • thinking is on by default at high effort; send thinking type "disabled" to turn it off.
  • in thinking mode temperature, presence_penalty, frequency_penalty and top_p are silently ignored, with no error.
  • with tools, every earlier assistant turn's reasoning_content must be sent back in full, or the api returns a 400 error.

04

benchmarks

as published by the maker; not measured by octomind.

benchmarkscore
HLE (without tools)source42.7
HLE (with tools)source60.0
Terminal Bench 2.1source87.9
Toolathlon-Verifiedsource74.1
DeepSWEsource62.7

05

when to pick it

pick it if

  • want DeepSeek's largest V4 model with MIT-licensed open weights
  • resend long prompts: cache hits bill $0.044 per 1M versus $1.32
  • need low / high / max thinking effort for agent workflows

06

where it sits on price

blended price $1.98/M at 3 input tokens per output token: 25 live language models cost less, 18 cost more.

  1. Kimi 2.7 Code $1.712/M
  2. Inkling $1.762/M
  3. DeepSeek V4 Pro $1.98/M
  4. GPT-6.1 Terra $2/M
  5. Muse Spark 1.3 $2/M

07

use DeepSeek V4 Pro in octomind

one octohub login reaches every model in the catalog. pick this one per run, per session, or as your default.

run it
octomind login
octomind run -m octohub:deepseek-v4-pro
switch mid-session
/model octohub:deepseek-v4-pro
make it the default — config.toml
[model]
name = "octohub:deepseek-v4-pro"

08

compare DeepSeek V4 Pro

all model comparisons →

09

similar models

nearest live models by listed input price.

view all models →

10

DeepSeek V4 Pro faq

how much does DeepSeek V4 Pro cost?

DeepSeek V4 Pro lists at $1.32/M input, $3.96/M output, $0.044/M cached input per 1M tokens. a typical coding-agent session (2M tokens in, 60,000 out) comes to $2.88, or $0.71 when 85% of the input is read from the prompt cache. octomind bills the listed provider price, with no markup, on every plan, including the free one (pay as you go from credits).

what is the context window of DeepSeek V4 Pro?

1M tokens, ≈ 1,500 pages of prose or 100,000 lines of code. a single reply can run to 384k tokens.

does DeepSeek V4 Pro accept images?

no. DeepSeek V4 Pro is text-only; pick a vision model from the DeepSeek lineup or the catalog for screenshots and diagrams.

is DeepSeek V4 Pro open source?

its weights are open under MIT, so it can also be self-hosted.

when was DeepSeek V4 Pro released?

April 24, 2026, by DeepSeek.

is DeepSeek V4 Pro free?

no. DeepSeek V4 Pro bills per token at $1.32/M input, $3.96/M output, $0.044/M cached input per 1M. octomind's free plan reaches it pay as you go from credits, so you pay only for the tokens you use, at the provider price. credits carry a 3% top-up fee.

how do i use DeepSeek V4 Pro in octomind?

run octomind login once, then octomind run -m octohub:deepseek-v4-pro. inside a running session, /model octohub:deepseek-v4-pro switches to it without losing context.

use DeepSeek V4 Pro in octomind

choose a model when you start, then switch mid-session when the work changes.