Together AI: Models Intelligence, Performance & Price
This analysis is intended to support you in choosing the best model provided by Together AI for your use-case.
Most Intelligent
Updated
GLM-5.3 (max)
Kimi K3 (max)GLM-5.3-Flash
Qwen3.8 2.4T A95BGLM-5.2 (max)Intelligence index
Total 15 models
Fastest
GLM-5.3 (max)Qwen3.8 2.4T A95BGLM-5.2 (max)
Muse Glimmer (high)Qwen3.5 9B (FP8)Output speed
Total 15 models
Lowest Price
GLM-5.3-FlashQwen3.5 9B (FP8)Qwen3.5 9B (Non-reasoning) (FP8)
gpt-oss-120b (high)gpt-oss-120b (low)Blended price (per 1M tokens)
Total 15 models
Together AI offers 15 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 Together AI are GLM-5.3 (max) (45), Kimi K3 (max) (44), and GLM-5.3-Flash (42).
- For output speed, the fastest models are GLM-5.3 (max) (188 t/s), Qwen3.8 2.4T A95B (129 t/s), and GLM-5.2 (max) (124 t/s). Speed varies significantly across models, with a 104% difference between the fastest and slowest.
- For latency, Qwen3.5 9B (Non-reasoning) (FP8) (0.74s), Llama 3.3 70B Turbo (1.48s), and Gemma 4 31B (Non-reasoning) (FP8) (4.05s) offer the lowest time to first answer token.
- For pricing, GLM-5.3-Flash ($0.10), Qwen3.5 9B (FP8) ($0.18), and Qwen3.5 9B (Non-reasoning) (FP8) ($0.18) offer the lowest blended prices per 1M tokens.
- For context window size, Kimi K3 (max) (1M), GLM-5.3-Flash (1M), and GLM-5.3 (max) (1M) support the largest context windows on Together AI.
- GLM-5.3 (max) offers the best combination of intelligence and speed. For cost optimization, GLM-5.3-Flash provides the most competitive pricing.
Highlights
Intelligence Evaluations
Artificial Analysis Intelligence Index
Intelligence Evaluations
Agentic knowledge work, (Elo-500)/2000
Agentic real-world work tasks, (Elo-500)/2000
Agentic SaaS workflows
Agentic coding & terminal use
Coding
Reasoning & knowledge
Professional document reasoning, All-pass
Physics reasoning
Knowledge
1 - hallucination rate
Long context reasoning
Legal agentic work, criterion pass rate
Agentic business operations
Quantitative analysis on spreadsheets & documents
Agentic tool use
Kubernetes incident root-cause analysis
Visual reasoning
Medical long context 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
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 | $2.58 | 188 | 0.59 | 13.88 | 10.63 | |||
Kimi K3 (max) | 1.05M | Open | 44 | $4.34 | 71 | 0.78 | 35.83 | 28.04 | |||
GLM-5.3-Flash | 1.05M | Open | 42 | $0.36 | 92 | 0.71 | 28.03 | 21.86 | |||
Qwen3.8 2.4T A95B | 262k | Open | 40 | $2.77 | 129 | 1.10 | 20.41 | 15.45 | |||
GLM-5.2 (max) | 262k | Open | 34 | $1.05 | 124 | 0.86 | 20.96 | 16.08 | |||
 MiniMax-M3 | 1M | Open | 30 | $0.70 | 73 | 0.78 | 34.82 | 27.24 | |||
 Inkling | 524k | Open | 26 | $0.91 | 89 | 0.57 | 28.50 | 22.35 | |||
MiniMax-M2.5 (FP4) | 197k | Open | 23* | -- | -- | -- | -- | -- | |||
GLM-4.7 | 203k | Open | 22* | -- | -- | -- | -- | -- | |||
GLM-4.6 | 203k | Open | 19* | -- | -- | -- | -- | -- | |||
Muse Glimmer (high) | 131k | Open | 18 | $0.09 | 107 | 0.80 | 24.09 | 18.64 | |||
GLM-4.7 (Non-reasoning) | 203k | Open | 17* | -- | -- | -- | -- | -- | |||
 Gemma 4 31B (FP8) | 262k | Open | 15 | $0.29 | 37 | 1.66 | 61.82 | 46.71 | |||
GLM-4.6 (Non-reasoning) | 203k | Open | 15* | -- | -- | -- | -- | -- | |||
Gemma 4 31B (Non-reasoning) (FP8) | 262k | Open | 14* | -- | 61 | 4.05 | 12.22 | -- | |||
 Apriel-v1.5-15B-Thinker | 131k | Open | 14* | -- | -- | -- | -- | -- | |||
 DeepSeek V3.1 (Non-reasoning) | 131k | Open | 14* | -- | -- | -- | -- | -- | |||
Qwen3.5 9B (FP8) | 262k | Open | 14* | -- | 92 | 0.70 | 27.77 | 21.65 | |||
Apriel-v1.6-15B-Thinker | 131k | Open | 13* | -- | -- | -- | -- | -- | |||
Qwen3.5 9B (Non-reasoning) (FP8) | 262k | Open | 13* | -- | 91 | 0.74 | 6.25 | -- | |||
DeepSeek R1 0528 | 164k | Open | 13* | -- | -- | -- | -- | -- | |||
gpt-oss-120b (high) | 131k | Open | 12 | $0.11 | 91 | 0.66 | 28.17 | 22.01 | |||
DeepSeek R1 (Jan) | 164k | Open | 11 | $0.41 | -- | -- | -- | -- | |||
GLM-4.5-Air (FP8) | 131k | Open | 11* | -- | -- | -- | -- | -- | |||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 76 | 0.69 | 33.66 | 26.37 | |||
Qwen3 Coder Next (FP8) | 262k | Open | 10 | $0.78 | -- | -- | -- | -- | |||
Llama 4 Maverick | 1.05M | Open | 9 | $0.04 | -- | -- | -- | -- | |||
Llama 3.3 70B Turbo | 131k | Open | 8* | -- | 60 | 1.48 | 9.85 | -- | |||
 Cogito v2.1 | 164k | Open | -- | -- | -- | -- | -- | -- | |||
Key definitions
Frequently Asked Questions
Common questions about Together AI
Together AI offers 15 models that we track: GLM-5.3 (max), Kimi K3 (max), GLM-5.3-Flash, Qwen3.8 2.4T A95B, GLM-5.2 (max), MiniMax-M3, Inkling, Muse Glimmer (high), Gemma 4 31B (FP8), Gemma 4 31B (Non-reasoning) (FP8), Qwen3.5 9B (FP8), Qwen3.5 9B (Non-reasoning) (FP8), gpt-oss-120b (high), gpt-oss-120b (low), and Llama 3.3 70B Turbo.
The most intelligent model available on Together AI is GLM-5.3 (max) with an Intelligence Index score of 45.
The fastest model on Together AI by output speed is GLM-5.3 (max) at 188.2 tokens per second.
The model with the lowest time to first answer token on Together AI is Qwen3.5 9B (Non-reasoning) (FP8) at 0.74s. Lower latency means faster initial response time.
The most affordable model on Together AI by blended price is GLM-5.3-Flash at $0.10 per 1M tokens (7:2:1 cache hit/input/output ratio).
Prices on Together AI vary up to 23x across models, from $0.10 per 1M tokens for GLM-5.3-Flash to $2.31 per 1M tokens for Kimi K3 (max).
Yes, Together AI offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
Yes, all 15 models on Together AI support JSON mode for structured output.
Yes, all 15 models on Together AI support function calling (tool use).
Yes, Together AI offers 12 reasoning models: GLM-5.3 (max), Kimi K3 (max), GLM-5.3-Flash, Qwen3.8 2.4T A95B, GLM-5.2 (max), MiniMax-M3, Inkling, Muse Glimmer (high), Gemma 4 31B (FP8), Qwen3.5 9B (FP8), gpt-oss-120b (high), and gpt-oss-120b (low). Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, all 15 models on Together AI 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 Together AI, 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.