Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work
82 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows
9 providers
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.
14 providers
Open MoE flagship with million-token context for coding and long agent runs
71 providers
Multimodal Kimi workhorse for agent loops, coding tasks, and visual context
69 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| Kimi K3moonshotai/kimi-k3 | Moonshot AI |
88.3 | 1.04858M | $3 | $15 | 2026-07-16 | ||
| Beam 1.0 501B A23Breflection/beam-1.0-501b-a23b | 80.1 | 1.04858M | $0.24 | $0.98 | 2026-10-05 | |||
| Muse Spark Openmeta/muse-spark-open | Meta |
76.4 | 1.04858M | $1.25 | $4.25 | 2026-10-15 | ||
| DeepSeek V4 Prodeepseek/deepseek-v4-pro | DeepSeek |
64.7 | 1M | $0.66 | $1.98 | 2026-04-24 | ||
| Kimi K2.6moonshotai/kimi-k2.6 | Moonshot AI |
64.3 | 262.144K | $0.95 | $4 | 2026-04-20 |