Перейти к основному содержанию

Deepseek-V4-Flash

Deepseek-V4-Flash is a LLM model. Fast DeepSeek model for efficient chat, coding help, and agent loops
Vision
Audio
Tool Use
Reasoning
Citations

Key Specs

Context
1M
Max Output
1M
Best Price (Input / Output)
$0.07 / $0.17 per 1M tokens
Chat with Model
Try on OpenRouter

Pricing Comparison

Provider Input (1M) Output (1M) Image (1k)
kenari (Free Tier) Free Free -
opencode (Free Tier) Free Free -
umans-ai-coding-plan Free Free -
digitalocean $0.07 $0.17 -
kilo $0.08 $0.25 -
openrouter $0.08 $0.25 -
openrouter (Ver 0731) $0.08 $0.18 -
neuralwatt $0.10 $0.21 -
baseten (Ver 0731) $0.13 $0.26 -
venice (Ver 0423) $0.14 $0.28 -
chutes (TEE / Ver 0731) $0.14 $0.28 -
deepseek $0.14 $0.28 -
nano-gpt (Ver 0731) $0.14 $0.28 -
nano-gpt $0.14 $0.28 -
opencode $0.14 $0.28 -
umans-ai $0.14 $0.28 -
vivgrid $0.15 $0.30 -
azure $0.19 $0.51 -
nano-gpt (TEE) $0.20 $0.40 -
venice (Ver 0731) $0.35 $0.70 -

Prices are per 1 million tokens unless otherwise noted. Image pricing is per 1000 images if applicable.

Price History

Prompt Price
Completion Price
$0.00$0.25$0.50$0.75$1.00Aug 13

Price trend per 1 million tokens over time.

Supported Parameters

frequency_penalty
reasoning
parallel_tool_calls
min_p
structured_outputs
response_format
include_reasoning
stop
top_k
max_tokens
top_logprobs
temperature
presence_penalty
tools
seed
tool_choice
logit_bias
reasoning_effort
logprobs
repetition_penalty
top_p
top_a

Похожие модели