Inference availability
Providers Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.
Report a price
Providers offering Muse Spark Open
Provider Provider model ID Context Max output Input Output Cache read Capabilities Docs
K Kilo Gateway meta/muse-spark-open1.05M
944K
$1.25
$4.25
$0.15
Reasoning Tools JSON Docs ↗
O OpenRouter meta/muse-spark-open1.05M
944K
$1.25
$4.25
$0.15
Reasoning Tools JSON Docs ↗
O Ollama Cloud muse-spark-open1.05M
131K
$1.25
$4.25
$0.15
Reasoning Tools Docs ↗
N Nebius Token Factory meta-models/muse-spark-open1.05M
1.05M
$1.25
$4.25
$0.15
Reasoning Tools JSON Docs ↗
V Vercel AI Gateway meta/muse-spark-open1.05M
1.05M
$1.25
$4.25
$0.15
Reasoning Tools JSON Docs ↗
F Fireworks AI accounts/fireworks/models/muse-spark-open1.05M
131K
$1.25
$4.25
$0.15
Reasoning Tools JSON Docs ↗
R Requesty muse-spark-open1.05M
131K
$1.25
$4.25
$0.15
Reasoning Tools Docs ↗
M Merge Gateway meta/muse-spark-open1.05M
262K
$1.25
$4.25
$0.15
Reasoning Tools Docs ↗
N NanoGPT meta/muse-spark-open1.05M
131K
$1.25
$4.25
$0.15
Reasoning Tools JSON Docs ↗
P Prime Inference meta/muse-spark-open1.05M
944K
$1.25
$4.25
— Reasoning Tools JSON Docs ↗
T Together AI meta-models/Muse-Spark-Open-816B-A42B1.05M
131K
$1.25
$4.25
$0.15
Reasoning Tools JSON Docs ↗
C Cloudflare AI Gateway meta/muse-spark-open1.04M
131K
$1.25
$4.25
$0.15
Reasoning Tools JSON Docs ↗
M Modal meta-models/Muse-Spark-Open-816B-A42B1.05M
131K
$1.25
$4.25
$0.15
Reasoning Tools JSON Docs ↗
V Venice AI muse-spark-open1.05M
131K
$1.56
$5.31
$0.19
Reasoning Tools JSON Docs ↗
Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.
Listed rates
Price across providers Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.
Lowest input
$1.25/M
Across 14 priced providers
Median input
$1.25/M
Midpoint of listed rates
Highest input
$1.56/M
1.2× the lowest listed rate
Output range
$4.25 – $5.31
Per million output tokens
Kilo Gateway
$1.25/M
OpenRouter
$1.25/M
Ollama Cloud
$1.25/M
Nebius Token Factory
$1.25/M
Vercel AI Gateway
$1.25/M
Fireworks AI
$1.25/M
Requesty
$1.25/M
Merge Gateway
$1.25/M
NanoGPT
$1.25/M
Prime Inference
$1.25/M
Together AI
$1.25/M
Cloudflare AI Gateway
$1.25/M
Modal
$1.25/M
Venice AI
$1.56/M
13 providers list the identical $1.25 input rate, so price alone will not separate them — compare context limits, max output, and capabilities above.
Context limits also differ by provider, from 1.04M to 1.05M tokens. Compare the provider table above before choosing on price alone.
Specification
Capabilities Recorded from the source catalog and provider listings.
✓
Reasoning
Yes
✓
Tool calling
Yes
✓
Structured output
Yes
✓
Attachments
Yes
✓
Vision input
Yes
✓
Open weights
Yes
Model family muse
Knowledge cutoff 2026-01-04
License Muse Model License
Release date 2026-10-15
Model ID meta/muse-spark-open
Weights:
Hugging Face (BF16) ↗ · Hugging Face (NVFP4) ↗
Published evaluations
Benchmarks Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.
Benchmark registry
Benchmark profile
Design Arena: w…Design Arena: website
Design Arena: g…Design Arena: gamedev
Humanity's Last…Humanity's Last Exam
GPQA DiamondGPQA Diamond
JobBenchJobBench
GDPval-AAGDPval-AA 2
MCP AtlasMCP Atlas
SciCodeSciCode
This model — Design Arena: website: 1320 elo (94.8th percentile)
This model — Design Arena: gamedev: 1275 elo (76.2th percentile)
This model — Humanity's Last Exam: 61 score (70.8th percentile)
This model — GPQA Diamond: 89 score (6.2th percentile)
This model — JobBench: 61.8 score (81.2th percentile)
This model — GDPval-AA 2: 1401 Elo (25.0th percentile)
This model — MCP Atlas: 89.2 score (90.0th percentile)
This model — SciCode: 58.5 score (50.0th percentile)
Each axis is this model's percentile among the 8 benchmarks it has published results for, measured against every other model with a score on that same benchmark. Percentiles are used because benchmarks do not share a scale — a 60 on one is not a 60 on another. Hover any point for the raw score.
Design Arena: website
#10 of 200
750.0
median 1196.0
1361.0
Design Arena: gamedev
#46 of 191
773.0
median 1189.0
1445.0
Humanity's Last Exam
#4 of 12
30.8
median 54.2
67.7
GPQA Diamond
#8 of 8
89.0
median 91.2
95.5
JobBench
#2 of 8
25.0
median 54.5
62.0
GDPval-AA
#5 of 6
832.0
median 1657.0
1853.0
MCP Atlas
#1 of 5
56.1
median 76.8
89.2
SciCode
#3 of 5
49.2
median 58.5
60.1
Toolathlon-Verified
#4 of 5
49.1
median 73.6
76.9
OSWorld-Verified
#4 of 4
80.4
median 81.4
84.3
BabyVision
#3 of 3
80.2
median 85.6
92.5
39.0
2 models scored — too few for a distribution
76.4
2 models scored — too few for a distribution
25.0
1 model scored — too few for a distribution
60.0
1 model scored — too few for a distribution
26.1
1 model scored — too few for a distribution
68.3
1 model scored — too few for a distribution
58.0
1 model scored — too few for a distribution
73.6
1 model scored — too few for a distribution
61.5
1 model scored — too few for a distribution
49.4
1 model scored — too few for a distribution
50.0
1 model scored — too few for a distribution
Each strip shows every published score for that benchmark, with this model marked. The lighter shape behind the ticks is the density of results, and the dashed line is the median.
Cost against capability
Price and performance Listed input price plotted against Design Arena: website, the benchmark with the widest published coverage that this model appears in.
0
721
1443
$0.1
$1
$10
Amazon: Nova Premier 1.0 — $2.50/M, score 835.0
Nova Pro 1.0 — $0.80/M, score 796.0
Claude Fable 5 — $10.00/M, score 1294.0
Anthropic: Claude Fable 5.1 — $10.00/M, score 1311.0
Anthropic: Claude Fable 5.1 (batch) — $5.00/M, score 1311.0
Anthropic: Claude Fable 5 (batch) — $5.00/M, score 1294.0
Anthropic: Claude Haiku 4.5 — $1.00/M, score 1122.0
Anthropic: Claude Haiku 4.5 (batch) — $0.50/M, score 1122.0
Anthropic: Claude Haiku 5.5 — $0.10/M, score 1261.0
Anthropic: Claude Haiku 5.5 (batch) — $0.05/M, score 1261.0
Anthropic: Claude Opus 4 — $15.00/M, score 1176.0
Anthropic: Claude Opus 4.1 — $15.00/M, score 1175.0
Anthropic: Claude Opus 4.1 (batch) — $7.50/M, score 1175.0
Anthropic: Claude Opus 4.5 — $5.00/M, score 1245.0
Anthropic: Claude Opus 4.5 (batch) — $2.50/M, score 1245.0
Anthropic: Claude Opus 4.6 — $5.00/M, score 1289.0
Anthropic: Claude Opus 4.6 (batch) — $2.50/M, score 1289.0
Anthropic: Claude Opus 4.7 — $5.00/M, score 1307.0
Anthropic: Claude Opus 4.7 (batch) — $2.50/M, score 1307.0
Anthropic: Claude Opus 4.8 — $5.00/M, score 1257.0
Anthropic: Claude Opus 4.8 (batch) — $2.50/M, score 1257.0
Claude Opus 5 — $5.00/M, score 1308.0
Anthropic: Claude Opus 5.5 — $4.00/M, score 1329.0
Anthropic: Claude Opus 5.5 (batch) — $2.00/M, score 1329.0
Anthropic: Claude Opus 5 (batch) — $2.50/M, score 1308.0
Anthropic: Claude Sonnet 4 — $3.00/M, score 1147.0
Anthropic: Claude Sonnet 4.5 — $3.00/M, score 1188.0
Anthropic: Claude Sonnet 4.5 (batch) — $1.50/M, score 1188.0
Anthropic: Claude Sonnet 4.6 — $3.00/M, score 1283.0
Anthropic: Claude Sonnet 4.6 (batch) — $1.50/M, score 1283.0
Claude Sonnet 5 — $2.00/M, score 1273.0
Anthropic: Claude Sonnet 5.5 — $2.00/M, score 1325.0
Anthropic: Claude Sonnet 5.5 (batch) — $1.00/M, score 1325.0
Anthropic: Claude Sonnet 5 (batch) — $1.00/M, score 1273.0
Trinity Large Thinking — $0.25/M, score 1137.0
DeepSeek Chat — $0.15/M, score 1118.0
DeepSeek V3.1 — $0.19/M, score 1122.0
DeepSeek R1 0528 — $0.20/M, score 1149.0
DeepSeek: DeepSeek V3.1 Terminus — $0.27/M, score 1185.0
DeepSeek V3.2 — $0.21/M, score 1173.0
DeepSeek: DeepSeek V3.2 Exp — $0.27/M, score 1177.0
DeepSeek V4 Flash — $0.15/M, score 1206.0
DeepSeek V4 Flash 0731 — $0.04/M, score 1236.0
DeepSeek: DeepSeek V4 Flash 0731 (batch) — $0.11/M, score 1250.0
DeepSeek V4 Pro — $0.66/M, score 1234.0
DeepSeek V4.1 Flash 1017 — $0.15/M, score 1309.0
Gemini 2.5 Flash — $0.30/M, score 1113.0
Google: Gemini 2.5 Flash (batch) — $0.15/M, score 1115.0
Gemini 2.5 Pro — $1.25/M, score 1165.0
Google: Gemini 2.5 Pro (batch) — $0.62/M, score 1167.0
Gemini 3 Flash Preview — $0.50/M, score 1196.0
Google: Gemini 3 Flash Preview (batch) — $0.25/M, score 1196.0
Gemini 3.1 Flash Lite Preview — $0.25/M, score 1081.0
Gemini 3.1 Pro Preview — $2.00/M, score 1251.0
Google: Gemini 3.1 Pro Preview (batch) — $1.00/M, score 1251.0
Gemini 3.5 Flash — $1.50/M, score 1266.0
Google: Gemini 3.5 Flash (batch) — $0.75/M, score 1266.0
Gemini 3.6 Flash — $0.75/M, score 1299.0
Google: Gemini 3.6 Flash (batch) — $0.38/M, score 1299.0
Gemini 3.7 Flash — $0.75/M, score 1302.0
Google: Gemini 3.7 Flash (batch) — $0.38/M, score 1302.0
Gemini 3.8 Flash — $0.75/M, score 1299.0
Google: Gemini 3.8 Flash (batch) — $0.38/M, score 1299.0
Gemini 4 Argon — $2.00/M, score 1314.0
Google: Gemini 4 Argon (batch) — $1.00/M, score 1314.0
Mercury 2 — $0.25/M, score 1035.0
Mercury 3 — $0.10/M, score 1221.0
Meta: Llama 4 Maverick — $0.19/M, score 869.0
Meta: Llama 4 Scout — $0.10/M, score 750.0
Muse Glimmer 30B — $0.20/M, score 1147.0
Muse Spark 1.1 — $1.25/M, score 1269.0
Muse Spark 1.2 — $1.25/M, score 1311.0
Muse Spark 1.3 — $1.25/M, score 1355.0
Muse Spark Open — $1.25/M, score 1320.0
Meta: Muse Wonder — $4.00/M, score 1361.0
MiniMax: MiniMax M2 — $0.26/M, score 1141.0
MiniMax: MiniMax M2.1 — $0.30/M, score 1201.0
MiniMax: MiniMax M2.5 — $0.30/M, score 1222.0
MiniMax: MiniMax M2.7 — $0.30/M, score 1241.0
MiniMax: MiniMax M3 — $0.30/M, score 1255.0
MiniMax: MiniMax M3 (batch) — $0.30/M, score 1271.0
Mistral: Codestral 2508 — $0.30/M, score 1011.0
Mistral: Codestral 2508 (batch) — $0.15/M, score 1011.0
Mistral: Ministral 3 14B 2512 — $0.20/M, score 1081.0
Mistral: Ministral 3 3B 2512 — $0.10/M, score 1026.0
Mistral: Ministral 3 8B 2512 — $0.15/M, score 1063.0
Mistral: Ministral 3 8B 2512 (batch) — $0.07/M, score 1063.0
Mistral: Mistral Large 3 2512 — $0.50/M, score 1162.0
Mistral: Mistral Large 3 2512 (batch) — $0.25/M, score 1162.0
Mistral: Mistral Large 4 — $1.36/M, score 1257.0
Mistral: Mistral Medium 3 — $0.40/M, score 1077.0
Mistral: Mistral Medium 3.1 — $0.40/M, score 1131.0
Mistral: Mistral Medium 3.1 (batch) — $0.20/M, score 1131.0
Mistral: Mistral Small 3.2 24B — $0.07/M, score 894.0
Kimi K2 0711 — $0.40/M, score 1050.0
Kimi K2 Instruct 0905 — $0.60/M, score 1107.0
Kimi K2 Thinking — $0.40/M, score 1113.0
Kimi K2.5 — $0.38/M, score 1248.0
Kimi K2.6 — $0.95/M, score 1267.0
Kimi K2.7 Code — $0.95/M, score 1262.0
MoonshotAI: Kimi K2.7 Code (batch) — $0.47/M, score 1284.0
Kimi K3 — $3.00/M, score 1334.0
Kimi K3.1 Pro — $2.00/M, score 1328.0
MoonshotAI: Kimi K3 (batch) — $2.28/M, score 1334.0
Nex-N2-Pro — $0.50/M, score 1237.0
Nemotron 3 Ultra 550B A55B — $0.10/M, score 1144.0
NVIDIA: Nemotron 3 Ultra (batch) — $0.60/M, score 1145.0
NVIDIA: Nemotron 3.5 Super VL — $0.15/M, score 1172.0
GPT-4.1 — $2.00/M, score 1037.0
GPT-4.1 mini — $0.40/M, score 997.0
OpenAI: GPT-4.1 Mini (batch) — $0.20/M, score 997.0
GPT-4.1 nano — $0.10/M, score 971.0
OpenAI: GPT-4.1 Nano (batch) — $0.05/M, score 971.0
OpenAI: GPT-4.1 (batch) — $1.00/M, score 1037.0
GPT-4o — $2.50/M, score 831.0
OpenAI: GPT-4o (batch) — $1.25/M, score 831.0
GPT-5 — $1.25/M, score 1184.0
GPT-5 Mini — $0.25/M, score 1125.0
OpenAI: GPT-5 Mini (batch) — $0.12/M, score 1125.0
GPT-5 Nano — $0.05/M, score 1101.0
OpenAI: GPT-5 Nano (batch) — $0.02/M, score 1101.0
GPT-5.1 — $1.25/M, score 1185.0
GPT-5.1 Codex — $1.07/M, score 1160.0
GPT-5.1 Codex mini — $0.22/M, score 1109.0
OpenAI: GPT-5.1 (batch) — $0.62/M, score 1185.0
GPT-5.2 — $1.75/M, score 1193.0
OpenAI: GPT-5.2 (batch) — $0.88/M, score 1193.0
GPT-5.3 Codex — $1.75/M, score 1161.0
GPT-5.4 — $2.50/M, score 1218.0
OpenAI: GPT-5.4 (batch) — $1.25/M, score 1218.0
GPT-5.5 — $5.00/M, score 1255.0
OpenAI: GPT-5.5 (batch) — $2.50/M, score 1255.0
OpenAI: GPT-5 (batch) — $0.62/M, score 1184.0
GPT-6.1 Sol — $2.00/M, score 1320.0
OpenAI: GPT-6.1 Sol (batch) — $1.00/M, score 1320.0
GPT OSS 120B — $0.03/M, score 966.0
OpenAI: gpt-oss-120b (batch) — $0.03/M, score 966.0
GPT OSS 20B — $0.02/M, score 852.0
OpenAI: gpt-oss-20b (batch) — $0.02/M, score 852.0
o3 — $2.00/M, score 1036.0
OpenAI: o3 (batch) — $1.00/M, score 1036.0
o4-mini — $1.10/M, score 985.0
OpenAI: o4 Mini (batch) — $0.55/M, score 985.0
Qwen: Qwen3 235B A22B — $0.45/M, score 1035.0
Qwen: Qwen3 235B A22B Instruct 2507 — $0.09/M, score 1056.0
Qwen: Qwen3 235B A22B Thinking 2507 — $0.45/M, score 1051.0
Qwen: Qwen3 30B A3B — $0.12/M, score 953.0
Qwen: Qwen3 30B A3B Thinking 2507 — $0.20/M, score 935.0
Qwen: Qwen3 Coder 480B A35B — $0.30/M, score 1157.0
Qwen: Qwen3 Coder 30B A3B Instruct — $0.07/M, score 1087.0
Qwen: Qwen3 Max — $0.78/M, score 1123.0
Qwen: Qwen3.5 397B A17B — $0.50/M, score 1189.0
Qwen: Qwen3.5 Plus 2026-02-15 — $0.26/M, score 1187.0
Qwen: Qwen3.6 Plus — $0.33/M, score 1241.0
Qwen: Qwen3.7 Max — $1.48/M, score 1273.0
Qwen: Qwen3.7 Plus — $0.32/M, score 1268.0
Qwen: Qwen3.7 Plus (batch) — $0.23/M, score 1268.0
Qwen: Qwen3.8 Max — $2.00/M, score 1295.0
Beam 1.0 501B A23B — $0.24/M, score 1242.0
Step 3.7 Flash — $0.20/M, score 1195.0
Hy3 — $0.07/M, score 1180.0
Inkling — $1.87/M, score 1223.0
Thinking Machines: Inkling (batch) — $1.00/M, score 1229.0
Solar Mini 4 — $0.10/M, score 1153.0
Solar Pro 4 — $0.30/M, score 1176.0
SpaceXAI: Grok 4.20 — $1.25/M, score 1229.0
SpaceXAI: Grok 4.3 — $1.25/M, score 1194.0
SpaceXAI: Grok 4.3 (batch) — $1.00/M, score 1194.0
SpaceXAI: Grok 4.5 — $2.00/M, score 1279.0
SpaceXAI: Grok 4.6 — $2.00/M, score 1287.0
SpaceXAI: Grok 4.7 — $2.00/M, score 1252.0
MiMo-V2.5 — $0.14/M, score 1264.0
MiMo-V2.5-Pro — $0.43/M, score 1265.0
MiMo-V2.6-Pro — $0.43/M, score 1306.0
Z.ai: GLM 4.5 — $0.60/M, score 1168.0
Z.ai: GLM 4.5 Air — $0.13/M, score 1145.0
Z.ai: GLM 4.6 — $0.55/M, score 1174.0
Z.ai: GLM 4.7 — $0.54/M, score 1224.0
Z.ai: GLM 4.7 Flash — $0.06/M, score 1194.0
Z.ai: GLM 5 — $1.00/M, score 1247.0
Z.ai: GLM 5 Turbo — $1.20/M, score 1260.0
Z.ai: GLM 5.1 — $1.40/M, score 1290.0
Z.ai: GLM 5.2 — $0.03/M, score 1283.0
Z.ai: GLM 5.2 (batch) — $0.70/M, score 1302.0
Z.ai: GLM 5.3 — $0.08/M, score 1292.0
Z.ai: GLM 5.3 Flash — $0.15/M, score 1270.0
Z.ai: GLM 5.3 Flash (batch) — $0.05/M, score 1270.0
Z.ai: GLM 5.3 (batch) — $0.45/M, score 1292.0
Z.ai: GLM 5V Turbo — $1.20/M, score 1228.0
Muse Spark Open
Input price per million tokens (log scale)
Elo
The stepped line is the efficient frontier: at each price, the best score available for that money or less. A model sitting on it is not being beaten by anything cheaper. Price is log-scaled because listed rates span four orders of magnitude. Only models with both a listed price and a score on this benchmark can appear.
Catalog activity
Change log Field-level changes detected between successful source imports.
Full change log
Oct 24, 2026 Max Output Tokens 943718 → 131072
Oct 24, 2026 Max Output Tokens 131072 → 943718
Oct 24, 2026 Max Output Tokens 943718 → 131072
Oct 24, 2026 Max Output Tokens 131072 → 943718
Oct 24, 2026 Max Output Tokens 943718 → 131072
Oct 24, 2026 Max Output Tokens 131072 → 943718
Oct 24, 2026 Max Output Tokens 943718 → 131072
Oct 24, 2026 Max Output Tokens 131072 → 943718
Oct 24, 2026 Max Output Tokens 943718 → 131072
Oct 24, 2026 Max Output Tokens 131072 → 943718
Provenance
Sources & verification Every figure on this page traces back to one of these records.
Methodology
Last verified Oct 24, 2026
Status Source-linked
Confidence Medium
Catalog source Models.dev
Public API
Use this record Fetch the complete source-linked model record. No key, no account, no rate-limited tier.
API documentation
Endpoint Copy
GET https://modelbench.lol/api/v1/models/meta/muse-spark-opencurl Copy
curl "https://modelbench.lol/api/v1/models/meta/muse-spark-open"
Common questions
Frequently asked questions Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.
What is Muse Spark Open?
Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context. It is published by Meta and catalogued here from Models.dev.
How much does Muse Spark Open cost?
Listed input pricing starts at $1.25 per million tokens from Kilo Gateway, rising to $1.56 across 14 listed providers.
What is the context length of Muse Spark Open?
Muse Spark Open accepts up to 1.05M tokens of context and returns up to 131K output tokens.
Does Muse Spark Open support tool calling and structured output?
Provider catalogs list support for tool calling, structured output, reasoning, and image input.
Which providers serve Muse Spark Open?
14 providers list this model: Kilo Gateway, OpenRouter, Ollama Cloud, Nebius Token Factory, Vercel AI Gateway, Fireworks AI and 8 more.
Are the weights for Muse Spark Open open?
Yes. The weights are published and downloadable from Hugging Face (BF16), Hugging Face (NVFP4) under the Muse Model License license.
When was Muse Spark Open released?
The catalog records a release date of 2026-10-15, last verified Oct 24, 2026.
OpenRouter
Ollama Cloud
Fireworks AI
Requesty
Merge Gateway
Together AI
Cloudflare AI Gateway
Modal