impulse

Spot Deepseek V4 Flash

Open weights
API id spot-deepseek-v4-flash
Input / 1M
$0.105
at Fireworks AI
Output / 1M
$0.21
at Fireworks AI
Context window
1M
tokens
Max output
384K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at Fireworks AI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.105$0.21
Cached input
80% off input
$0.021

What it costs a month

At Fireworks AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$39.69
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$37.80
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$68.04
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$302
Use your own numbers

Where to run it

1 host serve Spot Deepseek V4 Flash. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Fireworks AIInference
spot-deepseek-v4-flash
$0.105 / $0.21

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Features
Prompt caching
Open weights
License: DeepSeek License (MIT code)
Runtimes: SGLang, TGI, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Fireworks AI.

Smaller Independent models

No cheaper Independent model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • MiniMax M3.1 Flash
    MiniMax · on Refuseless
    $0.05 / $0.25
    Has every key capability
    24% less
  • Qwen3.5 9B
    Alibaba Qwen · on EmpirioLabs AI
    $0.09 / $0.13
    Has every key capability
    24% less
  • GLM 5.3 Flash
    Zhipu AI · on CLF AI Gateway
    $0.06 / $0.20
    Has every key capability
    28% less
  • Ling 3.0 Flash
    Independent · on DeepInfra
    $0.06 / $0.18
    Has every key capability
    31% less

Call it

Using Fireworks AI's API.

Python
from litellm import completion

response = completion(
    model="fireworks_ai/spot-deepseek-v4-flash",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Spot Deepseek V4 Flash cost?

On Fireworks AI, Spot Deepseek V4 Flash costs $0.105 per million input tokens and $0.21 per million output tokens. Cached input costs $0.021 per million tokens.

Which APIs offer Spot Deepseek V4 Flash?

Spot Deepseek V4 Flash runs on 1 API: Fireworks AI.

What is Spot Deepseek V4 Flash's context window?

1M tokens, with up to 384K tokens in one reply.

Is Spot Deepseek V4 Flash being retired?

It has been retired: Fireworks AI retired it on 14 Aug 2026.

What are cheaper alternatives to Spot Deepseek V4 Flash?

Models that cost less and keep most of what it can do: MiniMax M3.1 Flash on Refuseless (24% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Spot Deepseek V4 Flash's API model id?

Use spot-deepseek-v4-flash with Fireworks AI.

Sources

Raw catalog entry for spot-deepseek-v4-flash on Fireworks AI
{
  "cache_read_input_token_cost": 2.1e-8,
  "deprecation_date": "2026-08-14",
  "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md",
  "input_cost_per_token": 1.05e-7,
  "litellm_provider": "fireworks_ai",
  "max_input_tokens": 1048576,
  "max_output_tokens": 384000,
  "mode": "chat",
  "output_cost_per_token": 2.1e-7,
  "source": "https://api.fireworks.ai/v1/serverless/models",
  "successor_model": "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash",
  "supports_function_calling": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_tool_choice": true,
  "supports_vision": false
}