Fireworks AI

Fireworks AI: DeepSeek V4 Pro 0813 (Fireworks)

stable

DeepSeek V4 Pro 0813 (Fireworks) is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

accounts__fireworks__models__deepseek-v4-pro-0813deepseek-thinkingreleased Aug 12, 2026
ProviderQuick start
Context
1M
tokens
Max output
384K
tokens
Input
$1.32
per 1M
Output
$3.96
per 1M

Activity

Daily period usage
Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.

Providers

ProviderContextInput /MOutput /M
OpenRouter
OpenRouter
1.0M$1.12$3.37
Fireworks AI
Fireworks AI
1M$1.32$3.96
Hugging Face
Hugging Face
1M$1.32$3.96
Together AI
Together AI
1.0M$1.32$3.96

Pricing

ItemPriceUnit
Input$1.32per 1M tokens
Output$3.96per 1M tokens
Cache read$0.044per 1M tokens

Performance

Reliability

Compare

Compare usage and performance
Place this model beside up to three other catalog models.

Capabilities

Capabilities
Modalities
Input
Output
Details
Model ID
accounts__fireworks__models__deepseek-v4-pro-0813
Family
deepseek-thinking
Status
stable
Knowledge
-
Released
Aug 12, 2026
Gateway Config
API
2024-01-01
Auth
FIREWORKS_API_KEY
Discovery
static
Provider type
meta

Quick Start

index.ts
import Everstack from "@everstack/node";const client = new Everstack({  apiKey: process.env.EVERSTACK_API_KEY!,  baseUrl: "https://{instance}.{region}.everstack.ai",});const completion = await client.chat.completions.create({  model: "@fireworks/accounts__fireworks__models__deepseek-v4-pro-0813",  messages: [{ role: "user", content: "Explain vector cache routing." }],});console.log(completion.choices[0]?.message?.content);

Endpoint

Base URL
https://api.fireworks.ai/inference/v1
Chat completions
https://api.fireworks.ai/inference/v1/chat/completions
Model
accounts__fireworks__models__deepseek-v4-pro-0813
Auth env
FIREWORKS_API_KEY

DeepSeek V4 Pro 0813 (Fireworks) FAQ

How much does the DeepSeek V4 Pro 0813 (Fireworks) API cost?

Through Fireworks AI, DeepSeek V4 Pro 0813 (Fireworks) costs $1.32 per 1M input tokens and $3.96 per 1M output tokens. The lowest input price in the catalog is $1.12 per 1M tokens on OpenRouter.

What is the context window of DeepSeek V4 Pro 0813 (Fireworks)?

DeepSeek V4 Pro 0813 (Fireworks) accepts up to 1M tokens of context and returns up to 384K output tokens on Fireworks AI.

Which providers offer DeepSeek V4 Pro 0813 (Fireworks)?

DeepSeek V4 Pro 0813 (Fireworks) is available from OpenRouter, Fireworks AI, Hugging Face and Together AI. Everstack can route between them with automatic fallback when one is unavailable.

What can DeepSeek V4 Pro 0813 (Fireworks) do?

DeepSeek V4 Pro 0813 (Fireworks) supports chat, function calling and reasoning. It accepts text input.

How do I call DeepSeek V4 Pro 0813 (Fireworks) through Everstack?

Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @fireworks/accounts__fireworks__models__deepseek-v4-pro-0813. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.