Inference provider
Fireworks AI API pricing: every model, compared
We track 106 Fireworks AI prices that other providers also sell. Fireworks AI has the lowest listed price for 23 of them; for the rest, the table shows how much more you pay than at the cheapest provider.
Standard list prices in USD. Last price change Oct 21, 2026. Fireworks AI's official pricing page. How we rank.
LLMs, most widely offered first
Fireworks AI LLM prices vs the cheapest provider
| Model | Rank | Cheapest elsewhere | Input / 1M | Output / 1M | Context |
|---|---|---|---|---|---|
| gpt-oss-120b | #7 of 18 | W&B Inference (CoreWeave)you pay 304% more here | $0.15 | $0.60 | 131K |
| Llama-3.3-70B-Instruct | #12 of 13 | Nebius Token Factoryyou pay 356% more here | $0.90 | $0.90 | 131K |
| GLM-5.3 | #4 of 12 | DeepInfrayou pay 28% more here | $1.40 | $4.40 | 1M |
| GLM-5.3-Flash | #1 of 11 | Fireworks AI is cheapest | $0.15 | $0.50 | 1M |
| gpt-oss-20b | #6 of 10 | W&B Inference (CoreWeave)you pay 132% more here | $0.07 | $0.30 | 131K |
| Llama-3.1-8B-Instruct | #6 of 10 | Novita AIyou pay 264% more here | $0.10 | $0.10 | 131K |
| Kimi K3 | #3 of 9 | SiliconFlowyou pay 11% more here | $3.00 | $15.00 | 1M |
| DeepSeek-R1 | #6 of 8 | SiliconFlowyou pay 362% more here | $3.00 | $8.00 | 164K |
| DeepSeek-V3 | #6 of 8 | SiliconFlowyou pay 106% more here | $0.90 | $0.90 | 131K |
| DeepSeek-V3.2 | #6 of 8 | DeepInfrayou pay 190% more here | $0.56 | $1.68 | 164K |
| DeepSeek-V4.1-Flash | #3 of 8 | DeepInfrayou pay 150% more here | $0.30 | $1.20 | 1M |
| DeepSeek V4.1 Flash 1017 | #2 of 7 | DeepInfrayou pay 150% more here | $0.30 | $1.20 | 1M |
| DeepSeek-V3.1 | #5 of 7 | DeepInfrayou pay 98% more here | $0.56 | $1.68 | 128K |
| DeepSeek-V4-Flash | #3 of 7 | DeepInfrayou pay 56% more here | $0.14 | $0.28 | 1M |
| GLM-5.1 | #4 of 7 | DeepInfrayou pay 29% more here | $1.40 | $4.40 | 203K |
| Kimi K2.5 | #3 of 7 | DeepInfrayou pay 33% more here | $0.60 | $3.00 | 262K |
| Llama 3.2 3B Instruct | #5 of 7 | Lambdayou pay 471% more here | $0.10 | $0.10 | 131K |
| llama-3.1-70b-instruct | #6 of 7 | Nebius Token Factoryyou pay 356% more here | $0.90 | $0.90 | 131K |
| MiniMax-M3 | #3 of 7 | W&B Inference (CoreWeave)you pay 27% more here | $0.30 | $1.20 | 512K |
| Qwen3 32B | #7 of 7 | DeepInfrayou pay 592% more here | $0.90 | $0.90 | 131K |
| DeepSeek-R1-0528 | #6 of 6 | Lambdayou pay 1317% more here | $3.00 | $8.00 | 164K |
| deepseek-r1-distill-llama-70b | #6 of 6 | DeepInfrayou pay 200% more here | $0.90 | $0.90 | 131K |
| Qwen2.5-72B-Instruct | #5 of 6 | Nebius Token Factoryyou pay 356% more here | $0.90 | $0.90 | 33K |
| Qwen3 235B A22B Instruct 2507 | #4 of 6 | DeepInfrayou pay 88% more here | $0.22 | $0.88 | 262K |
| Deepseek R1 Distill Qwen 32B | #4 of 5 | Nscaleyou pay 500% more here | $0.90 | $0.90 | 131K |
| deepseek-v3-0324 | #5 of 5 | Lambdayou pay 200% more here | $0.90 | $0.90 | 164K |
| Gemma-3-27b-it | #5 of 5 | DeepInfrayou pay 800% more here | $0.90 | $0.90 | 131K |
| GLM-4.6 | #2 of 5 | DeepInfrayou pay 10% more here | $0.55 | $2.19 | 203K |
| GLM-4.7 | #2 of 5 | DeepInfrayou pay 36% more here | $0.60 | $2.20 | 203K |
| Llama 3.2 11B Vision Instruct | #3 of 5 | Lambdayou pay 1043% more here | $0.20 | $0.20 | 131K |
| Llama 3.2 1B Instruct | #4 of 5 | Novita AIyou pay 400% more here | $0.10 | $0.10 | 131K |
| Qwen2.5 Coder 32B Instruct | #4 of 5 | Lambdayou pay 1340% more here | $0.90 | $0.90 | 4K |
| Qwen3.8 2.4T A95B | #1 of 5 | Fireworks AI is cheapest | $2.00 | $6.00 | 262K |
| Qwq 32B | #5 of 5 | Nscaleyou pay 386% more here | $0.90 | $0.90 | 131K |
| DeepSeek-V3.1-Terminus | #4 of 4 | DeepInfrayou pay 86% more here | $0.56 | $1.68 | 128K |
| GLM-4.5 | #2 of 4 | DeepInfrayou pay 37% more here | $0.55 | $2.19 | 131K |
| GLM-4.5-Air | #3 of 4 | Novita AIyou pay 24% more here | $0.22 | $0.88 | 131K |
| Kimi K2 Instruct | #3 of 4 | DeepInfrayou pay 23% more here | $0.60 | $2.50 | 131K |
| Llama Guard 3 8B | #3 of 4 | Nebius Token Factoryyou pay 567% more here | $0.20 | $0.20 | 131K |
| llama-3.1-405b-instruct | #2 of 4 | Nebius Token Factoryyou pay 100% more here | $3.00 | $3.00 | 131K |
| llama3-70b-instruct | #2 of 4 | Novita AIyou pay 59% more here | $0.90 | $0.90 | 8K |
| mistral-nemo-instruct-2407 | #4 of 4 | DeepInfrayou pay 820% more here | $0.20 | $0.20 | 128K |
| Qwen2.5-7B-Instruct | #4 of 4 | SiliconFlowyou pay 300% more here | $0.20 | $0.20 | 33K |
| qwen2.5-vl-72b-instruct | #3 of 4 | Nebius Token Factoryyou pay 140% more here | $0.90 | $0.90 | 128K |
| Qwen3 VL 30B A3B Instruct | #1 of 4 | Fireworks AI is cheapest | $0.15 | $0.60 | 262K |
| Qwen3-14B | #4 of 4 | Nebius Token Factoryyou pay 67% more here | $0.20 | $0.20 | 41K |
| Qwen3-Coder-480B-A35B-Instruct | #4 of 4 | SiliconFlowyou pay 80% more here | $0.45 | $1.80 | 262K |
| qwen3-next-80b-a3b-thinking | #4 of 4 | Nebius Token Factoryyou pay 118% more here | $0.90 | $0.90 | 4K |
| Qwen3.8 Max | #2 of 4 | DeepInfrayou pay 21% more here | $2.00 | $6.00 | 262K |
| deepseek-r1-distill-qwen-14b | #3 of 3 | Nscaleyou pay 186% more here | $0.20 | $0.20 | 131K |
| GLM-4.5V | #3 of 3 | Z.aiyou pay 33% more here | $1.20 | $1.20 | 131K |
| Inkling | #2 of 3 | DeepInfrayou pay 2% more here | $1.00 | $4.05 | 1M |
| Kimi K2 Thinking | #1 of 3 | Fireworks AI is cheapest | $0.60 | $2.50 | 262K |
| llama-2-70b-chat | #1 of 3 | Fireworks AI is cheapest | $0.90 | $0.90 | 2K |
| llama-3-2-90b-vision-instruct | #1 of 3 | Fireworks AI is cheapest | $0.90 | $0.90 | 131K |
| minimax-m2 | #1 of 3 | Fireworks AI is cheapest | $0.30 | $1.20 | 197K |
| minimax-m2.1 | #1 of 3 | Fireworks AI is cheapest | $0.30 | $1.20 | 197K |
| MiniMax-M3.1-Flash | #1 of 3 | Fireworks AI is cheapest | $0.15 | $0.60 | 1M |
| mixtral-8x7b-instruct | #2 of 3 | Perplexityyou pay 308% more here | $0.50 | $0.50 | 33K |
| MythoMax L2 13B | #2 of 3 | Novita AIyou pay 122% more here | $0.20 | $0.20 | 4K |
| Qwen3 30B A3B | #3 of 3 | Nebius Token Factoryyou pay 75% more here | $0.15 | $0.60 | 131K |
| Qwen3 VL 235B A22B Instruct | #2 of 3 | DeepInfrayou pay 4% more here | $0.22 | $0.88 | 262K |
| qwen3-235b-a22b | #3 of 3 | DeepInfrayou pay 43% more here | $0.22 | $0.88 | 131K |
| qwen3-235b-a22b-thinking-2507 | #1 of 3 | Fireworks AI is cheapest | $0.22 | $0.88 | 262K |
| Qwen3-30B-A3B-Instruct-2507 | #3 of 3 | SiliconFlowyou pay 251% more here | $0.50 | $0.50 | 262K |
| Qwen3-Coder-30B-A3B-Instruct | #3 of 3 | Novita AIyou pay 119% more here | $0.15 | $0.60 | 262K |
| Qwen3-Next 80B-A3B Instruct | #3 of 3 | DeepInfrayou pay 163% more here | $0.90 | $0.90 | 4K |
| Qwen3-VL-30B-A3B-Thinking | #1 of 3 | Fireworks AI is cheapest | $0.15 | $0.60 | 262K |
| Qwen3-VL-8B-Instruct | #2 of 3 | Novita AIyou pay 8% more here | $0.20 | $0.20 | 262K |
| Qwen3.7 Plus | #2 of 3 | Together AIyou pay 25% more here | $0.40 | $1.60 | 262K |
| codellama-34b-instruct | #2 of 2 | Perplexityyou pay 47% more here | $0.90 | $0.90 | 16K |
| codellama-70b-instruct | #1 of 2 | Fireworks AI is cheapest | $0.90 | $0.90 | 4K |
| DeepSeek V4.1 Flash 1017 | #1 of 2 | Fireworks AI is cheapest | $0.30 | $1.20 | 1M |
| deepseek-r1-distill-llama-8b | #2 of 2 | Nscaleyou pay 700% more here | $0.20 | $0.20 | 131K |
| deepseek-r1-distill-qwen-1.5b | #2 of 2 | Nscaleyou pay 11% more here | $0.10 | $0.10 | 131K |
| deepseek-r1-distill-qwen-7b | #1 of 2 | Fireworks AI is cheapest | $0.20 | $0.20 | 131K |
| GLM 5.3 Fast | #1 of 2 | Fireworks AI is cheapest | $2.10 | $6.60 | 1M |
| GPT OSS Safeguard 120B | #2 of 2 | Amazon Bedrockyou pay 357% more here | $1.20 | $1.20 | 131K |
| GPT OSS Safeguard 20B | #2 of 2 | Amazon Bedrockyou pay 388% more here | $0.50 | $0.50 | 131K |
| kimi-k2-instruct-0905 | #2 of 2 | DeepInfrayou pay 23% more here | $0.60 | $2.50 | 262K |
| llama-3.1-nemotron-70b-instruct | #2 of 2 | DeepInfrayou pay 50% more here | $0.90 | $0.90 | 131K |
| llama-v2-13b | #1 of 2 | Fireworks AI is cheapest | $0.20 | $0.20 | 4K |
| llama-v2-13b-chat | #1 of 2 | Fireworks AI is cheapest | $0.20 | $0.20 | 4K |
| llama-v2-70b | #1 of 2 | Fireworks AI is cheapest | $0.10 | $0.10 | 4K |
| llama-v2-7b | #2 of 2 | Replicateyou pay 100% more here | $0.20 | $0.20 | 4K |
| llama-v2-7b-chat | #2 of 2 | Replicateyou pay 100% more here | $0.20 | $0.20 | 4K |
| llama-v3-8b | #2 of 2 | Replicateyou pay 100% more here | $0.20 | $0.20 | 8K |
| MiniMax M1 80K | #1 of 2 | Fireworks AI is cheapest | $0.10 | $0.10 | 4K |
| ministral-3-14b-instruct-2512 | #1 of 2 | Fireworks AI is cheapest | $0.20 | $0.20 | 256K |
| Mistral Small 3 | #2 of 2 | DeepInfrayou pay 1465% more here | $0.90 | $0.90 | 33K |
| mistral-7b-instruct-v0.2 | #2 of 2 | Replicateyou pay 100% more here | $0.20 | $0.20 | 33K |
| Muse Spark Open | #1 of 2 | Fireworks AI is cheapest | $1.25 | $4.25 | 1M |
| nvidia-nemotron-nano-9b-v2 | #2 of 2 | DeepInfrayou pay 186% more here | $0.20 | $0.20 | 128K |
| Qwen Max | #2 of 2 | Alibaba Cloud Model Studioyou pay 7% more here | $2.00 | $6.00 | 262K |
| qwen-v2.5-14b-instruct | #1 of 2 | Fireworks AI is cheapest | $0.20 | $0.20 | 33K |
| qwen2-vl-72b-instruct | #2 of 2 | Nebius Token Factoryyou pay 356% more here | $0.90 | $0.90 | 33K |
| qwen2-vl-7b-instruct | #2 of 2 | Nebius Token Factoryyou pay 567% more here | $0.20 | $0.20 | 33K |
| qwen2.5-32b-instruct | #2 of 2 | Nebius Token Factoryyou pay 847% more here | $0.90 | $0.90 | 33K |
| qwen2.5-coder-3b-instruct | #2 of 2 | Nscaleyou pay 567% more here | $0.10 | $0.10 | 33K |
| qwen2.5-coder-7b | #2 of 2 | Nebius Token Factoryyou pay 1233% more here | $0.20 | $0.20 | 33K |
| qwen2.5-coder-7b-instruct | #2 of 2 | Nscaleyou pay 1233% more here | $0.20 | $0.20 | 33K |
| qwen2.5-vl-32b-instruct | #2 of 2 | DeepInfrayou pay 200% more here | $0.90 | $0.90 | 128K |
| qwen3-4b | #2 of 2 | Nebius Token Factoryyou pay 67% more here | $0.20 | $0.20 | 41K |
| Qwen3-8B | #2 of 2 | SiliconFlowyou pay 233% more here | $0.20 | $0.20 | 41K |
| qwen3-vl-235b-a22b-thinking | #1 of 2 | Fireworks AI is cheapest | $0.22 | $0.88 | 262K |
| Qwen3-VL-32B-Instruct | #2 of 2 | SiliconFlowyou pay 200% more here | $0.90 | $0.90 | 4K |
Rank and difference use the blended price (3 input : 1 output tokens). Equal prices share a rank.
Ranked for your volume
gpt-oss-120b monthly cost by provider
Change the monthly tokens and the ranking updates instantly, using each provider's standard list price.
More requirements: caching, context, features, provider
| Provider | Estimated / month | Input / 1M | Output / 1M | Cached input / 1M | Context |
|---|---|---|---|---|---|
1 W&B Inference (CoreWeave)lowest for your volumePricing page | $0.64 | $0.03 | $0.17 | Not listed | 131,000 |
2 DeepInfraPricing page | $0.71 | $0.037 | $0.17 | Not listed | 131,072 |
3 Novita AIPricing page | $1.00 | $0.05 | $0.25 | Not listed | 131,072 |
4 SiliconFlowPricing page | $1.40 | $0.05 | $0.45 | Not listed | 131,000 |
5 OVHcloud AI EndpointsBilled in EUR: €0.08 input, €0.40 output per 1M tokens. USD at the ECB rate of Oct 30, 2026 (1.1172).Pricing page | $1.79 | $0.0894 | $0.4469 | Not listed | 131,000 |
6 BasetenPricing page | $2.00 | $0.10 | $0.50 | $0.10 | 128,072 |
7 Amazon BedrockPricing page | $2.70 | $0.15 | $0.60 | Not listed | 128,000 |
8 Fireworks AIPricing page | $2.70 | $0.15 | $0.60 | $0.015 | 131,072 |
9 Microsoft Azure AI FoundryPricing page | $2.70 | $0.15 | $0.60 | Not listed | 131,072 |
10 Nebius Token FactoryPricing page | $2.70 | $0.15 | $0.60 | Not listed | 131,072 |
Input volume includes the cached share, not an additional token volume. This is a list-price estimate, not a quote: cache-write charges, cache eligibility/TTL, batch discounts, long-context surcharges, regional pricing and taxes are excluded. Check the provider's terms for your workload before switching.
Ranked #1? Show it on your site
Fireworks AI has the lowest blended list price (3 input : 1 output tokens) for these models. The badge states that basis, updates daily and always shows the current rank, whatever it is; ranking is by price only.
<a href="https://aiselect.online/models/glm-5-3-flash"><img src="https://aiselect.online/badge/glm-5-3-flash/fireworks.svg" alt="GLM-5.3-Flash API price ranking on AISelect" height="20"></a>
<a href="https://aiselect.online/models/qwen3-8-2-4t-a95b"><img src="https://aiselect.online/badge/qwen3-8-2-4t-a95b/fireworks.svg" alt="Qwen3.8 2.4T A95B API price ranking on AISelect" height="20"></a>
<a href="https://aiselect.online/models/qwen3-vl-30b-a3b-instruct"><img src="https://aiselect.online/badge/qwen3-vl-30b-a3b-instruct/fireworks.svg" alt="Qwen3 VL 30B A3B Instruct API price ranking on AISelect" height="20"></a>Compare more
Other providers
Alibaba Cloud Model Studio, Amazon Bedrock, Anthropic, Baseten, Cloudflare Workers AI, Cohere, DeepInfra, DeepSeek, fal, FriendliAI, Google Cloud Vertex AI, Google Gemini API, IBM watsonx.ai, Lambda, Microsoft Azure AI Foundry, Mistral AI, Moonshot AI, Nebius Token Factory, Novita AI, Nscale, OpenAI, Oracle Cloud Generative AI, OVHcloud AI Endpoints, Perplexity, Replicate, SambaNova, Scaleway, SiliconFlow, Together AI, W&B Inference (CoreWeave), xAI, Z.ai