Fireworks: Models Intelligence, Performance & Price
Analysis of Fireworks's models across key metrics including quality, price, output speed, latency, context window & more. This analysis is intended to support you in choosing the best model provided by Fireworks for your use-case.
Most Intelligent
Intelligence index
Total 10 models
Fastest
Output speed
Total 10 models
Lowest Price
Blended price (per 1M tokens)
Total 10 models
Fireworks offers 10 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 Fireworks are Kimi K3 (max) (57), GLM-5.2 (max) (51), and DeepSeek V4 Flash 0731 (max) (50).
- For output speed, the fastest models are GLM-5.2 (max) (300 t/s), MiniMax-M2.7 (220 t/s), and Kimi K3 (max) (175 t/s). Speed varies significantly across models, with a 188% difference between the fastest and slowest.
- For latency, Kimi K2.6 (1.22s), GLM-5.2 (max) (8.25s), and MiniMax-M2.7 (11.99s) offer the lowest time to first answer token.
- For pricing, DeepSeek V4 Flash 0731 (max) ($0.08), gpt-oss-120b (high) ($0.20), and gpt-oss-120b (low) ($0.20) offer the lowest blended prices per 1M tokens. Prices vary up to 9.3x across models.
- For context window size, DeepSeek V4 Pro (max) (1M), Kimi K3 (max) (1M), and DeepSeek V4 Flash 0731 (max) (1M) support the largest context windows on Fireworks.
Highlights
Intelligence Evaluations
Artificial Analysis Intelligence Index
Intelligence Evaluations
Agentic real-world work tasks, (Elo-500)/2000
Agentic tool use
Agentic coding & terminal use
Coding
Reasoning & knowledge
Scientific reasoning
Physics reasoning
Knowledge
1 - hallucination rate
Long context reasoning
Agentic knowledge work, Elo
Agentic SaaS workflows
Legal agentic work, criterion pass rate
Agentic business operations
Instruction following
Long-horizon agentic tasks
Kubernetes incident root-cause analysis
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
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 | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
Kimi K3 (max) | 1.05M | Open | 57 | $0.91 | 175 | 1.14 | 15.39 | 11.40 | |||
GLM-5.2 (max) | 1M | Open | 51 | $0.48 | 300 | 1.58 | 9.91 | 6.67 | |||
DeepSeek V4 Flash 0731 (max) | 1.05M | Open | 50 | $0.08 | 83 | 0.91 | 31.12 | 24.17 | |||
DeepSeek V4 Pro (max) | 1.05M | Open | 44 | $0.38 | 86 | 1.58 | 58.06 | 50.69 | |||
Kimi K2.6 | 262k | Open | 44 | $0.30 | 65 | 1.23 | 77.77 | 68.81 | |||
DeepSeek V4 Pro (high) | 1.05M | Open | 43 | $0.36 | 88 | 1.56 | 29.85 | 22.62 | |||
GLM-5 | 203k | Open | 40* | -- | -- | -- | -- | -- | |||
MiniMax-M2.7 | 197k | Open | 38 | $0.09 | 220 | 0.80 | 14.27 | 11.20 | |||
Kimi K2.6 | 262k | Open | 35* | -- | 60 | 1.22 | 9.62 | -- | |||
GLM-5 | 203k | Open | 32* | -- | -- | -- | -- | -- | |||
DeepSeek V3.2 | 164k | Open | 32 | -- | -- | -- | -- | -- | |||
DeepSeek V3.2 | 164k | Open | 25* | -- | -- | -- | -- | -- | |||
gpt-oss-120b (high) | 131k | Open | 24 | $0.08 | 125 | 0.75 | 20.72 | 15.97 | |||
DeepSeek V3.1 | 164k | Open | 21* | -- | -- | -- | -- | -- | |||
gpt-oss-120b (low) | 131k | Open | 15 | $0.02 | 104 | 0.79 | 24.80 | 19.21 | |||
 Qwen3 VL 235B A22B | 262k | Open | 14* | -- | -- | -- | -- | -- | |||
Qwen3 VL 30B A3B | 262k | Open | 13* | -- | -- | -- | -- | -- | |||
Qwen3 VL 30B A3B | 262k | Open | 10* | -- | -- | -- | -- | -- | |||
 Llama 3.3 70B | 131k | Open | 9 | $0.14 | -- | -- | -- | -- | |||
Qwen3 30B | 262k | Open | 9* | -- | -- | -- | -- | -- | |||
Qwen3 8B | 41k | Open | 5* | -- | -- | -- | -- | -- | |||
Key definitions
Frequently Asked Questions
Common questions about Fireworks
Fireworks offers 10 models that we track: Kimi K3 (max), GLM-5.2 (max), DeepSeek V4 Flash 0731 (max), DeepSeek V4 Pro (max), Kimi K2.6, DeepSeek V4 Pro (high), MiniMax-M2.7, Kimi K2.6, gpt-oss-120b (high), and gpt-oss-120b (low).
The most intelligent model available on Fireworks is Kimi K3 (max) with an Intelligence Index score of 57.
The fastest model on Fireworks by output speed is GLM-5.2 (max) at 300.1 tokens per second.
The model with the lowest time to first answer token on Fireworks is Kimi K2.6 at 1.22s. Lower latency means faster initial response time.
The most affordable model on Fireworks by blended price is DeepSeek V4 Flash 0731 (max) at $0.08 per 1M tokens (7:2:1 cache hit/input/output ratio).
Prices on Fireworks vary up to 31x across models, from $0.08 per 1M tokens for DeepSeek V4 Flash 0731 (max) to $2.31 per 1M tokens for Kimi K3 (max).
Yes, Fireworks offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
Yes, all 10 models on Fireworks support JSON mode for structured output.
Yes, all 10 models on Fireworks support function calling (tool use).
Yes, Fireworks offers 9 reasoning models: Kimi K3 (max), GLM-5.2 (max), DeepSeek V4 Flash 0731 (max), DeepSeek V4 Pro (max), Kimi K2.6, DeepSeek V4 Pro (high), MiniMax-M2.7, 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 10 models on Fireworks 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 Fireworks, 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.