Makora: Models Intelligence, Performance & Price
This analysis is intended to support you in choosing the best model provided by Makora for your use-case.
Most Intelligent
GLM-5.3 (max)
Kimi K3 (max)GLM-5.3-Flash
DeepSeek V4.1 Flash (max)
Muse Spark Open (xhigh) (NVFP4)Intelligence Index
Total 8 models
Fastest
Muse Spark Open (xhigh) (NVFP4)
Gemma 4 26B A4BGemma 4 26B A4B (non-reasoning)GLM-5.3-FlashDeepSeek V4.1 Flash (max)Output speed
Total 8 models
Lowest Price
MiMo-V2.6-FlashGemma 4 26B A4BGemma 4 26B A4B (non-reasoning)GLM-5.3-FlashDeepSeek V4.1 Flash (max)Blended price (per 1M tokens)
Total 8 models
Makora offers 8 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across models.
- For intelligence, the top models on Makora are GLM-5.3 (max) (45), Kimi K3 (max) (44), and GLM-5.3-Flash (42).
- For output speed, the fastest models are Muse Spark Open (xhigh) (NVFP4) (497 t/s), Gemma 4 26B A4B (290 t/s), and Gemma 4 26B A4B (non-reasoning) (274 t/s). Speed varies significantly across models, with a 123% difference between the fastest and slowest.
- For latency, Gemma 4 26B A4B (non-reasoning) (0.58s), Muse Spark Open (xhigh) (NVFP4) (4.89s), and Gemma 4 26B A4B (7.48s) offer the lowest time to first answer token.
- For pricing, MiMo-V2.6-Flash ($0.06), Gemma 4 26B A4B ($0.08), and Gemma 4 26B A4B (non-reasoning) ($0.08) offer the lowest blended prices per 1M tokens. Prices vary up to 3.2x across models.
- For context window size, GLM-5.3 (max) (1M), Kimi K3 (max) (1M), and GLM-5.3-Flash (1M) support the largest context windows on Makora.
Intelligence Evaluations
Artificial Analysis Intelligence Index
Evaluations
Agentic knowledge work, (Elo-500)/2000
Knowledge
1 - hallucination rate
Agentic SaaS workflows
Agentic real-world work tasks, (Elo-500)/2000
Reasoning & knowledge
Professional document reasoning, All-pass
Agentic coding & terminal use
Long context reasoning
Coding
Physics reasoning
Agentic scientific research workflows in a terminal
Agentic software engineering in open-source repositories
Quantitative analysis on spreadsheets & documents
Legal agentic work, Hallucination-Gated All-Pass Rate
Agentic business operations
Agentic interactive 3D experiences, (Elo-500)/2000
Kubernetes incident root-cause analysis
Medical long context reasoning
Visual reasoning
Intelligence Index vs. Price
Context Window
Context Window
Pricing
Intelligence Index vs. Price
Performance Summary
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed
Latency
Measured by Time (seconds) to First Token
Latency: Time To First Answer Token
Cache Behaviour
Cache Hit Rate
Cost per Task vs. Cache Hit Rate
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time vs. Price
Further Analysis | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
GLM-5.3 (max) | 1.05M | Open | 45 | $0.92 | 184 | 0.85 | 14.40 | 10.84 | |||
Kimi K3 (max) | 1.05M | Open | 44 | $1.18 | 64 | 1.19 | 40.11 | 31.14 | |||
GLM-5.3-Flash | 1.05M | Open | 42 | $0.54 | 212 | 1.22 | 13.02 | 9.44 | |||
DeepSeek V4.1 Flash (max) | 1.05M | Open | 39 | $1.01 | 219 | 0.63 | 12.03 | 9.12 | |||
Muse Spark Open (xhigh) (NVFP4) | 1.05M | Open | 39 | $0.72 | 519 | 0.88 | 5.70 | 3.85 | |||
MiMo-V2.6-Flash | 1.05M | Open | 38 | $0.22 | 111 | 1.24 | 23.76 | 18.02 | |||
Gemma 4 26B A4B | 1M | Open | 17* | -- | 335 | 0.57 | 8.02 | 5.96 | |||
Gemma 4 26B A4B (non-reasoning) | 1M | Open | 13* | -- | 486 | 0.58 | 1.61 | -- | |||
Key definitions
Frequently Asked Questions
Common questions about Makora
Makora offers 8 models that we track: GLM-5.3 (max), Kimi K3 (max), GLM-5.3-Flash, DeepSeek V4.1 Flash (max), Muse Spark Open (xhigh) (NVFP4), MiMo-V2.6-Flash, Gemma 4 26B A4B, and Gemma 4 26B A4B (non-reasoning).
The most intelligent model available on Makora is GLM-5.3 (max) with an Intelligence Index score of 45.
The fastest model on Makora by output speed is Muse Spark Open (xhigh) (NVFP4) at 497.4 tokens per second.
The model with the lowest time to first answer token on Makora is Gemma 4 26B A4B (non-reasoning) at 0.58s. Lower latency means faster initial response time.
The most affordable model on Makora by blended price is MiMo-V2.6-Flash at $0.06 per 1M tokens (7:2:1 cache hit/input/output ratio).
Prices on Makora vary up to 31x across models, from $0.06 per 1M tokens for MiMo-V2.6-Flash to $1.72 per 1M tokens for Kimi K3 (max).
Yes, Makora offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
Yes, all 8 models on Makora support JSON mode for structured output.
Yes, all 8 models on Makora support function calling (tool use).
Yes, Makora offers 7 reasoning models: GLM-5.3 (max), Kimi K3 (max), GLM-5.3-Flash, DeepSeek V4.1 Flash (max), Muse Spark Open (xhigh) (NVFP4), MiMo-V2.6-Flash, and Gemma 4 26B A4B. Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, all 8 models on Makora are open weight models.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
When choosing a model on Makora, consider: intelligence (for quality-sensitive tasks), output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and features like context window size, JSON mode, or function calling support.