Muse Spark 1.3

Muse Spark 1.3 is Meta's multimodal reasoning model for long-running agentic, multi-agent, and coding workflows, taking text, image, and PDF input.

start building →
compare models

input · usd / 1m tok

$1.25

output · usd / 1m tok

$4.25

context window

1.05mtokens

modalities · in → out

takes text and image in, gives text out

pricing

base api ratesusd per 1m tokens

input
$1.25
output
$4.25
cache read
$0.15

providers

Meta hosts Muse Spark 1.3. Impossibl routes your request intelligently and handles failover automatically when a provider is down.

  • Meta

specifications

takes text and image in, gives text outmeta/muse-spark-1.3

  • creatorMeta
  • model typeText generation
  • context window1,048,576 tokens
  • maximum outputnot published
  • input

    takes text and image in, gives text out

  • outputtext
  • tool callingnot verified
  • releasedsep 2, 2026
  • endpoint/v1/chat/completions

unknown means the public catalog does not establish that fact. a model's documented capabilities can differ from what a particular api supports. see the model documentation for integration details.

try it · your prompt, this model, live

# responses API
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["IMPOSSIBL_API_KEY"],
    base_url="https://api.impossibl.com/v1",
)

resp = client.responses.create(
    model="meta/muse-spark-1.3",
    input="",
)
print(resp.output_text)

edit the prompt, then run

benchmarks

intelligence index

48.1#10 of 108 models on the gateway

  1. coding index75.8#12 of 64
  2. agentic index55.5#4 of 53
  • Intelligence Index48.09
  • legal index (API)50.9
  • coding index (API)75.8
  • agentic index (API)55.5
  • economics index (API)56.3
  • engineering index (API)49.4
  • intelligence index (API)48.1
  • strategy and ops index (API)51.2
  • finance and accounting index (API)49.8
  • healthcare and medical index (API)49.7

view source ↗all source data and breakdowns (json) ↗

each configuration is listed separately; these evaluations describe the tested model configuration, and performance and costs can differ on impossibl. unmeasured scores are omitted and api values keep their source units. last checked 2026-10-14.

compare Muse Spark 1.3 with other models

frontier labs and open weights, best-ranked firstusd / 1m tok · in / out

impossibl models --all →

frequently asked questions

What is Muse Spark 1.3?

Muse Spark 1.3 is Meta's multimodal reasoning model for long-running agentic, multi-agent, and coding workflows, taking text, image, and PDF input. Compared with Muse Spark 1.2 it takes fewer turns and is less verbose, uses fewer tool calls, and adds stronger resistance to adversarial inputs and prompt injections.

How much does Muse Spark 1.3 cost?

Muse Spark 1.3 costs $1.25 per million input tokens and $4.25 per million output tokens through the Impossibl API. Cache reads cost $0.15 per million tokens. All rates are in USD.

view the pricing table ↑

What is the context length of Muse Spark 1.3?

Muse Spark 1.3 has a 1,048,576-token context window through the Impossibl API.

What inputs and outputs does Muse Spark 1.3 support?

Muse Spark 1.3 accepts text and image as input. Muse Spark 1.3 returns text.

How do I use Muse Spark 1.3 through an API?

Muse Spark 1.3 is available through the Impossibl API. Use meta/muse-spark-1.3 as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.

follow the api quickstart →

When was Muse Spark 1.3 released?

Meta released Muse Spark 1.3 on September 2, 2026.

this page describes Muse Spark 1.3 as listed by the impossibl public api. prices and availability come from that catalog, refreshed here every five minutes. this is an impossibl offering, not a comparison of independent hosting-provider quotes. model descriptions and release dates, where available, use the creator sources linked under the answers above.

view the source catalog ↗model as markdown ↗report a correction →