Fireworks: Models Intelligence, Performance & Price
This analysis is intended to support you in choosing the best model provided by Fireworks for your use-case.
Most Intelligent
DeepSeek V4.1 Flash 1017 (max)
Kimi K3 (max)
MiniMax-M3.1-Flash
GLM-5.3-Flash
Qwen3.8 2.4T A95BIntelligence Index
Total 12 models
Fastest
DeepSeek V4.1 Flash (non-reasoning)
Nemotron 3.5 Lightning (BF16)DeepSeek V4.1 Flash 1017 (max)
Inkling (xhigh)MiniMax-M3.1-FlashOutput speed
Total 12 models
Lowest Price
Nemotron 3.5 Lightning (BF16)GLM-5.3-FlashMiniMax-M3.1-FlashDeepSeek V4.1 Flash 1017 (max)DeepSeek V4.1 Flash (non-reasoning)Blended price (per 1M tokens)
Total 12 models
Fireworks offers 12 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 DeepSeek V4.1 Flash 1017 (max) (45), Kimi K3 (max) (44), and MiniMax-M3.1-Flash (43).
- For output speed, the fastest models are DeepSeek V4.1 Flash (non-reasoning) (424 t/s), Nemotron 3.5 Lightning (BF16) (388 t/s), and DeepSeek V4.1 Flash 1017 (max) (206 t/s). Speed varies significantly across models, with a 139% difference between the fastest and slowest.
- For latency, DeepSeek V4.1 Flash (non-reasoning) (0.77s), Nemotron 3.5 Lightning (BF16) (5.62s), and DeepSeek V4.1 Flash 1017 (max) (10.84s) offer the lowest time to first answer token.
- For pricing, Nemotron 3.5 Lightning (BF16) ($0.04), GLM-5.3-Flash ($0.10), and MiniMax-M3.1-Flash ($0.10) offer the lowest blended prices per 1M tokens. Prices vary up to 5.0x across models.
- For context window size, Kimi K3 (max) (1M), GLM-5.3-Flash (1M), and Muse Spark Open (xhigh) (1M) support the largest context windows on Fireworks.
Intelligence Evaluations
Artificial Analysis Intelligence Index
Evaluations
Agentic knowledge work, Elo
Knowledge
1 - hallucination rate
Agentic SaaS workflows
Agentic real-world work tasks, Elo
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
Kubernetes incident root-cause analysis
Medical long context reasoning
Visual reasoning
Rich, varied, well-crafted language
Well-structured, scannable, answer-first
Truthful, acknowledges uncertainty, non-sycophantic
Use of filler and generic language
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 | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
DeepSeek V4.1 Flash 1017 (max) | 1M | Open | 45 | $0.24 | 155 | 1.20 | 17.29 | 12.88 | |||
Kimi K3 (max) | 1.05M | Open | 44 | $1.91 | 115 | 0.97 | 22.77 | 17.44 | |||
GLM-5.3-Flash | 1.05M | Open | 42 | $0.37 | 175 | 2.84 | 17.12 | 11.42 | |||
Qwen3.8 2.4T A95B | 262k | Open | 40 | $1.87 | 175 | 0.99 | 15.26 | 11.42 | |||
 Muse Spark Open (xhigh) | 1.05M | Open | 39 | $0.84 | 88 | 0.81 | 29.09 | 22.63 | |||
DeepSeek V4 Flash 0731 (max) | 1.05M | Open | 34 | $0.09 | -- | -- | -- | -- | |||
GLM-5.2 (max) | 1M | Open | 34 | $2.94 | -- | -- | -- | -- | |||
Kimi K3 (low) | 1.05M | Open | 30 | $0.92 | 115 | 0.98 | 22.73 | 17.41 | |||
MiniMax-M3 | 524k | Open | 29 | $0.50 | 179 | 0.93 | 14.93 | 11.20 | |||
GLM-5 | 203k | Open | 28* | -- | -- | -- | -- | -- | |||
Kimi K2.6 | 262k | Open | 27 | $0.52 | -- | -- | -- | -- | |||
Inkling (xhigh) | 1.05M | Open | 25 | $0.63 | 196 | 0.51 | 13.25 | 10.20 | |||
Kimi K2.6 (non-reasoning) | 262k | Open | 24* | -- | -- | -- | -- | -- | |||
Nemotron 3 Ultra | 262k | Open | 23 | $0.32 | 128 | 0.75 | 22.40 | 17.75 | |||
GLM-5 (non-reasoning) | 203k | Open | 22* | -- | -- | -- | -- | -- | |||
DeepSeek V3.2 | 164k | Open | 21* | -- | -- | -- | -- | -- | |||
DeepSeek V3.2 (non-reasoning) | 164k | Open | 16* | -- | -- | -- | -- | -- | |||
DeepSeek V3.1 (non-reasoning) | 164k | Open | 14* | -- | -- | -- | -- | -- | |||
Nemotron 3.5 Lightning (BF16) | 262k | Open | 13 | $0.02 | 410 | 0.48 | 6.57 | 4.87 | |||
Qwen3 VL 235B A22B | 262k | Open | 10* | -- | -- | -- | -- | -- | |||
Qwen3 VL 30B A3B | 262k | Open | 9* | -- | -- | -- | -- | -- | |||
Qwen3 VL 30B A3B | 262k | Open | 8* | -- | -- | -- | -- | -- | |||
Qwen3 30B | 262k | Open | 8* | -- | -- | -- | -- | -- | |||
Qwen3 8B (non-reasoning) | 41k | Open | 6* | -- | -- | -- | -- | -- | |||
Key definitions
Frequently Asked Questions
Common questions about Fireworks
Fireworks offers 12 models that we track: DeepSeek V4.1 Flash 1017 (max), Kimi K3 (max), MiniMax-M3.1-Flash, GLM-5.3-Flash, Qwen3.8 2.4T A95B, Muse Spark Open (xhigh), Kimi K3 (low), MiniMax-M3, Inkling (xhigh), DeepSeek V4.1 Flash (non-reasoning), Nemotron 3 Ultra, and Nemotron 3.5 Lightning (BF16).
The most intelligent model available on Fireworks is DeepSeek V4.1 Flash 1017 (max) with an Intelligence Index score of 45.
The fastest model on Fireworks by output speed is DeepSeek V4.1 Flash (non-reasoning) at 424.5 tokens per second.
The model with the lowest time to first answer token on Fireworks is DeepSeek V4.1 Flash (non-reasoning) at 0.77s. Lower latency means faster initial response time.
The most affordable model on Fireworks by blended price is Nemotron 3.5 Lightning (BF16) at $0.04 per 1M tokens (7:2:1 cache hit/input/output ratio).
Prices on Fireworks vary up to 62x across models, from $0.04 per 1M tokens for Nemotron 3.5 Lightning (BF16) to $2.31 per 1M tokens for Kimi K3 (low).
Yes, Fireworks offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
Yes, all 12 models on Fireworks support JSON mode for structured output.
Yes, all 12 models on Fireworks support function calling (tool use).
Yes, Fireworks offers 11 reasoning models: DeepSeek V4.1 Flash 1017 (max), Kimi K3 (max), MiniMax-M3.1-Flash, GLM-5.3-Flash, Qwen3.8 2.4T A95B, Muse Spark Open (xhigh), Kimi K3 (low), MiniMax-M3, Inkling (xhigh), Nemotron 3 Ultra, and Nemotron 3.5 Lightning (BF16). Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, 11 of 12 models on Fireworks are open weight models: DeepSeek V4.1 Flash 1017 (max), Kimi K3 (max), GLM-5.3-Flash, Qwen3.8 2.4T A95B, Muse Spark Open (xhigh), Kimi K3 (low), MiniMax-M3, Inkling (xhigh), DeepSeek V4.1 Flash (non-reasoning), Nemotron 3 Ultra, and Nemotron 3.5 Lightning (BF16).
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.