Skip to main content

Muse Spark Open 816B A42B

Muse Spark Open 816B A42B is Meta's coding-optimized open-weight mixture-of-experts model, with 42B active parameters out of 816B total, trained for agentic coding workflows and reliable tool calling.

Input / output price
$1.25 / $4.25 per 1M
Context
1M tokens
Released
Oct 15, 2026
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "muse-spark-open-816b-a42b".

Read docs

Providers

One provider serves this model, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Makoramakora/muse-spark-open-816b-a42b
$1.25/M$4.25/M

Pricing

USD per 1M tokens on Makora, after gateway discounts.

Input
$1.25 per 1M
Output
$4.25 per 1M
Cache read
$0.15 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$1.25/MMakora

Benchmarks

The Respan Index plus 27 published scores from 5 sources, each linked to where it was published.

42.9/ 100

Respan Index#55 of 167

167 ranked models. The shaded band is this model's 95% interval, 35.6 to 51.1. Qwen3.7-Max and GLM-5.2 fall inside it, so the gap is within the margin of error.
Muse Spark Open 816B A42B by category: Coding 21.7, Agents 44.6, Reasoning 50.1, Knowledge & language 56.6, Human preference 54.4
  1. 55Muse Spark Open42.9
  2. 54Qwen3.7-Max43.1
  3. 56GLM-5.242.1

Published scores

BenchmarkScore
DeepSWE 1.1 (preferred harness)huggingface.co60%
SciCodehuggingface.co58.5%
SWE-Atlas-QnA (preferred harness)huggingface.co58%
Terminal-Bench 4.0Vals AI6.6%

Apps

Use Muse Spark Open 816B A42B in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Muse Spark Open 816B A42B FAQ

Short answers, built from the data on this page.

Muse Spark Open 816B A42B is a model from Meta, released on Oct 15, 2026. Muse Spark Open 816B A42B is Meta's coding-optimized open-weight mixture-of-experts model, with 42B active parameters out of 816B total, trained for agentic coding workflows and reliable tool calling.

On the Respan gateway, Muse Spark Open 816B A42B costs $1.25 per 1M input tokens and $4.25 per 1M output tokens on Makora, after gateway discounts.

Muse Spark Open 816B A42B is served by Makora.

Muse Spark Open 816B A42B accepts up to 1M tokens of context.

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "muse-spark-open-816b-a42b". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Muse Spark Open 816B A42B scores 42.9 out of 100 on the Respan Index v1.1, ranking #55 of 167 models. By category: Coding 21.7, Agents 44.6, Reasoning 50.1, Knowledge & language 56.6, and Human preference 54.4. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

Muse Spark Open 816B A42B has 27 published benchmark scores, including DeepSWE 1.1 (preferred harness) 60%, MCP-Atlas 89.2%, and GPQA Diamond 89%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.