Fireworks AI API Pricing
🌍 GlobalAPI price snapshot
Current Fireworks AI models and token prices
ComputeUnion currently tracks 51 Fireworks AI models, with input pricing from $0.016 per 1M tokens. Each model detail page keeps this platform's quote separate from other available official or channel quotes so the official API versus relay cost gap can be checked directly.
Payment Methods
Fireworks AI is an AI API relay service. ComputeUnion tracks 57 price records for this platform (53 auto-scraped, Updated 5m ago; 4 manually maintained). Browse the categories below to compare Fireworks AI pricing across providers.
Model Pricing on Fireworks AI
Prices per 1M tokens
LLM45 models
| Model | Input | Output | Context | Updated |
|---|---|---|---|---|
| DBRX Instruct dbrx-instruct | $1.2000 | $1.2000 | 32K | Updated 5m ago |
| DeepSeek R1 deepseek-r1 | $0.2000 | $0.2000 | 125K | Updated 5m ago |
| DeepSeek R1 Distill Llama 70B deepseek-r1-distill-llama-70b | $0.9000 | $0.9000 | 125K | Updated 5m ago |
| DeepSeek R1 Distill Qwen 32B deepseek-r1-distill-qwen-32b | $0.9000 | $0.9000 | 125K | Updated 5m ago |
| DeepSeek V3 deepseek-v3 | $0.9000 | $0.9000 | 131K | Manually maintained |
| DeepSeek V4 Flash deepseek-v4-flash | $0.1400 | $0.2800 | 125K | Updated 5m ago |
| DeepSeek V4 Pro deepseek-v4-pro | $1.7400 | $3.4800 | 125K | Updated 5m ago |
| Gemma 2 9B Instruct gemma-2-9b-instruct | $0.2000 | $0.2000 | 8K | Updated 5m ago |
| Gemma 3 12B gemma-3-12b | $0.2000 | $0.2000 | 125K | Updated 5m ago |
| Gemma 3 1B gemma-3-1b | $0.1000 | $0.1000 | 32K | Updated 5m ago |
| Gemma 3 27B gemma-3-27b | $0.9000 | $0.9000 | 125K | Updated 5m ago |
| Gemma 3 4B gemma-3-4b | $0.2000 | $0.2000 | 125K | Updated 5m ago |
| GLM-5.1 glm-5-1 | $1.4000 | $4.4000 | 125K | Updated 5m ago |
| GPT Open Source gpt-open-source | $0.0700 | $0.3000 | 125K | Updated 5m ago |
| InternVL3 38B internvl3-38b | $0.9000 | $0.9000 | 8K | Updated 5m ago |
| InternVL3 78B internvl3-78b | $0.9000 | $0.9000 | 8K | Updated 5m ago |
| InternVL3 8B internvl3-8b | $0.2000 | $0.2000 | 8K | Updated 5m ago |
| Kimi K2.6 kimi-k2-6 | $0.9500 | $4.0000 | 250K | Updated 5m ago |
| Llama 3.1 405B llama-3-1-405b | $0.9000 | $0.9000 | 125K | Updated 5m ago |
| Llama 3.1 70B llama-3-1-70b | $0.9000 | $0.9000 | 125K | Updated 5m ago |
| Llama 3.1 8B llama-3-1-8b | $0.2000 | $0.2000 | 125K | Updated 5m ago |
| Llama 3.2 11B Vision llama-3-2-11b-vision | $0.2000 | $0.2000 | 125K | Updated 5m ago |
| Llama 3.2 1B llama-3-2-1b | $0.1000 | $0.1000 | 125K | Updated 5m ago |
| Llama 3.2 3B llama-3-2-3b | $0.1000 | $0.1000 | 125K | Updated 5m ago |
| Llama 3.2 90B Vision llama-3-2-90b-vision | $0.9000 | $0.9000 | 125K | Updated 5m ago |
| Llama 3.3 70B Instruct llama-3-3-70b-instruct | $0.9000 | $0.9000 | 125K | Updated 5m ago |
| Llama 4 Maverick llama-4-maverick | $1.2000 | $1.2000 | 125K | Updated 5m ago |
| Llama 4 Scout llama-4-scout | $0.5000 | $0.5000 | 125K | Updated 5m ago |
| Microsoft Phi-3 microsoft-phi-3 | $0.1000 | $0.1000 | 125K | Updated 5m ago |
| MiniMax 2.7 minimax-2-7 | $0.3000 | $1.2000 | 80K | Updated 5m ago |
| Mistral 7B mistral-7b | $0.2000 | $0.2000 | 32K | Updated 5m ago |
| Mistral Small 4 mistral-small-4 | $0.9000 | $0.9000 | 32K | Updated 5m ago |
| Mixtral 8x22B Instruct mixtral-8x22b-instruct | $1.2000 | $1.2000 | 64K | Updated 5m ago |
| Mixtral 8x7B Instruct mixtral-8x7b-instruct | $0.5000 | $0.5000 | 32K | Updated 5m ago |
| Qwen2 qwen2 | $0.2000 | $0.2000 | 125K | Updated 5m ago |
| Qwen2.5 14B Instruct qwen2-5-14b-instruct | $0.2000 | $0.2000 | 125K | Updated 5m ago |
| Qwen2.5 72B Instruct qwen2-5-72b-instruct | $0.9000 | $0.9000 | 125K | Updated 5m ago |
| Qwen2.5 7B Instruct qwen2-5-7b-instruct | $0.2000 | $0.2000 | 125K | Updated 5m ago |
| Qwen2.5 Coder 32B qwen2-5-coder-32b | $0.9000 | $0.9000 | 125K | Updated 5m ago |
| Qwen2.5 VL 72B qwen2-5-vl-72b | $0.9000 | $0.9000 | 125K | Updated 5m ago |
Showing 40 of 45 models — see the API pricing pages for the full list
Embedding6 models
| Model | Input | Output | Context | Updated |
|---|---|---|---|---|
| Qwen3 Embedding 0.6B qwen3-embedding-0-6b | $0.0160 | $0.0160 | 4K | Updated 5m ago |
| Qwen3 Embedding 4B qwen3-embedding-4b | $0.1000 | $0.1000 | 4K | Updated 5m ago |
| Qwen3 Embedding 8B qwen3-embedding-8b | $0.1000 | $0.1000 | 8K | Updated 5m ago |
| Qwen3 Reranker 0.6B qwen3-reranker-0-6b | $0.0160 | $0.0160 | 4K | Updated 5m ago |
| Qwen3 Reranker 4B qwen3-reranker-4b | $0.1000 | $0.1000 | 4K | Updated 5m ago |
| Qwen3 Reranker 8B qwen3-reranker-8b | $0.1000 | $0.1000 | 8K | Updated 5m ago |
Sources and price verification method
This page lists Fireworks AI price records by model and labels whether a record is live-API sourced or maintained. Platform identity, model availability, and pricing are separate evidence layers: official sources confirm vendor or model information, while ComputeUnion price records show currently comparable quotes. Relay model IDs, terms, refund policies, and regional availability should still be checked with the platform before purchase.
No vendor source is currently registered for automatic official-status decisions; this page only presents reviewable platform and pricing records already in the database.
FAQ
What is Fireworks AI?
Fireworks AI is an AI API relay service aggregating multi-provider access through a unified endpoint. ComputeUnion currently tracks 57 price records for this platform — 53 auto-scraped (Updated 5m ago), 4 manually maintained.
How does Fireworks AI pricing compare to official providers?
Fireworks AI quotes may differ from the official API, as may model IDs, regions, and service terms. Use the model links below to compare currently tracked quotes and verify current terms before purchase.
Is Fireworks AI accessible from China?
Fireworks AI is an international service — direct access from China mainland may be restricted.
Related pages