# Fireworks AI GPU Pricing and Company Profile Source: https://savrn.com/ai-index/companies/fireworks-ai Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- [SAVRN Index.](https://savrn.com/ai-index) Explore the IndexCompanies Updated September 10, 2026Research capture, not yet re-verified Prices tracked 17 12 confirmed on the provider's feed or page at the last check Sources 2 Every cited page, listed below Market Fireworks AI is privately held, so there is no public market data to show. Against the market ## How Fireworks AI prices compare Fireworks AI's lowest price for each GPU beside the lowest price every other tracked provider lists for the same GPU, sold the same way. Typical is the middle provider, one price each. ### NVIDIA H100On demand [All NVIDIA H100 prices →](https://savrn.com/ai-index/pricing/gpus/h100) Fireworks AI$8.00per GPU-hour, on-demand Rank19 of 2188% above typical Typical$4.25middle of 21 providers Lowest anywhere$1.99Voltage Park Voltage Park1. H100 (single GPU, no contract) $1.99 GMI Cloud2. NVIDIA H100 $2.00 Vultr3. NVIDIA HGX H100 — Cloud GPU $2.30 Denvr Dataworks4. NVIDIA H100 SXM (8 GPUs, 208 vCPU) $2.45 Cirrascale5. 8X NVIDIA H100 (16-Node+ Clustered) $2.49 Massed Compute6. H100 (80 GB) ×1/×2/×4 $2.73 Runpod7. H100 PCIe / H100 NVL — Pods $2.89 Hyperbolic8. H100 SXM $3.19 Lambda9. NVIDIA H100 PCIe $3.29 Together AI10. H100 (80 GB), 8–256 GPUs $3.99 Fireworks AI19. H100 80 GB $8.00 Fireworks AITypical $4.2510 more providers on the [NVIDIA H100 page](https://savrn.com/ai-index/pricing/gpus/h100) ### NVIDIA H200On demand [All NVIDIA H200 prices →](https://savrn.com/ai-index/pricing/gpus/h200) Fireworks AI$8.00per GPU-hour, on-demand Rank14 of 1644% above typical Typical$5.56middle of 16 providers Lowest anywhere$2.60GMI Cloud GMI Cloud1. NVIDIA H200 $2.60 Massed Compute2. H200 NVL (141 GB) ×8 $3.62 Hyperbolic3. H200 $3.99 Crusoe Cloud4. NVIDIA H200 $4.29 Runpod5. Clusters — H200 SXM $4.31 DigitalOcean6. NVIDIA HGX H200 (141 GB) $4.47 Cirrascale7. 8X H200 $4.54 Nebius8. NVIDIA HGX H200 $5.40 Verda9. 1x H200 SXM5 141GB $5.72 Together AI10. H200 (140 GB), 256–1,000 GPUs $5.99 Fireworks AI14. H200 141 GB $8.00 Fireworks AITypical $5.565 more providers on the [NVIDIA H200 page](https://savrn.com/ai-index/pricing/gpus/h200) ### NVIDIA B200On demand [All NVIDIA B200 prices →](https://savrn.com/ai-index/pricing/gpus/b200) Fireworks AI$13.00per GPU-hour, on-demand Rank15 of 1661% above typical Typical$8.08middle of 16 providers Lowest anywhere$3.50Vultr Vultr1. NVIDIA HGX B200 — Cloud GPU $3.50 GMI Cloud2. NVIDIA B200 $4.00 Massed Compute3. B200 SXM6 ×8 $5.43 Hyperbolic4. B200 $5.99 Cirrascale5. 8X B200 $5.99 Lambda6. NVIDIA B200 SXM6 $6.69 Runpod7. B200 (180 GB, 28 vCPU) — Pods $7.99 Google Cloud8. a4-highgpu-8g (A4) $8.06 Verda9. Instant clusters, B200 SXM6 180GB $8.11 Together AI10. HGX B200 (180 GB) $8.19 Fireworks AI15. B200 180 GB $13.00 Fireworks AITypical $8.085 more providers on the [NVIDIA B200 page](https://savrn.com/ai-index/pricing/gpus/b200) ### NVIDIA B300On demand [All NVIDIA B300 prices →](https://savrn.com/ai-index/pricing/gpus/b300) Fireworks AI$15.00per GPU-hour, on-demand Rank8 of 950% above typical Typical$9.99middle of 9 providers Lowest anywhere$6.60Massed Compute Massed Compute1. B300 SXM6 ×8 (280 vCPU, 2800 GB) $6.60 TheAI Cloud2. B300 (8× B300 SXM6 · 288GB … whole node) $6.90 Nebius3. NVIDIA HGX B300 $7.85 Runpod4. B300 (288 GB HBM3e, 32 vCPU) — Pods $8.99 Together AI5. HGX B300 (270 GB) $9.99 Verda6. 1x B300 SXM6 268GB $10.38 AWS7. p6-b300.48xlarge $14.04 Fireworks AI8. B300 288 GB $15.00 Oracle OCI9. BM.GPU.B300.8 $15.00 Fireworks AITypical $9.99 ### NVIDIA GB300 NVL72On demand [All NVIDIA GB300 NVL72 prices →](https://savrn.com/ai-index/pricing/gpus/gb300) Fireworks AI$20.00per GPU-hour, on-demand Rank3 of 311% above typical Typical$18.00middle of 3 providers Lowest anywhere$11.94Verda Verda1. 1x GB300 SXM6 288GB $11.94 Oracle OCI2. BM.GPU.GB300.4 $18.00 Fireworks AI3. GB300 288 GB $20.00 Fireworks AITypical $18.00 Tracked prices ## Fireworks AI prices Every price the Index tracks for Fireworks AI, in the provider's own words beside a normalized figure, with the date it was last checked. [What AI Costs](https://savrn.com/ai-index/pricing) compares them across the market. | GPU | Offer | Terms | Published price | Per GPU-hour | Change | Checked | Source | | --- | --- | --- | --- | --- | --- | --- | --- | | [NVIDIA H100](https://savrn.com/ai-index/pricing/gpus/h100) | H100 80 GB | on-demandList | $8.00 per GPU-hour, on-demand deployments, from Sep 1 | $8.00 | +14.3% | Not foundOct 23, 2026 | [fireworks.ai ↗](https://fireworks.ai/pricing) | | [NVIDIA H200](https://savrn.com/ai-index/pricing/gpus/h200) | H200 141 GB | on-demandList | $8.00 per GPU-hour, on-demand deployments, from Sep 1 | $8.00 | +14.3% | Not foundOct 23, 2026 | [fireworks.ai ↗](https://fireworks.ai/pricing) | | [NVIDIA B200](https://savrn.com/ai-index/pricing/gpus/b200) | B200 180 GB | on-demandList | $13.00 per GPU-hour, on-demand deployments, from Sep 1 | $13.00 | +30% | Not foundOct 23, 2026 | [fireworks.ai ↗](https://fireworks.ai/pricing) | | [NVIDIA B300](https://savrn.com/ai-index/pricing/gpus/b300) | B300 288 GB | on-demandList | $15.00 per GPU-hour, on-demand deployments, from Sep 1 | $15.00 | +25% | Not foundOct 23, 2026 | [fireworks.ai ↗](https://fireworks.ai/pricing) | | [NVIDIA GB300 NVL72](https://savrn.com/ai-index/pricing/gpus/gb300) | GB300 288 GB | on-demandList | $20.00 per GPU-hour, on-demand deployments, from Sep 1 | $20.00 | +11.1% | Not foundOct 23, 2026 | [fireworks.ai ↗](https://fireworks.ai/pricing) | | Seller | Model | Input | Cached input | Output | [Revenue per GPU-hour at list](https://savrn.com/ai-index/pricing/gpus/vera-rubin#token-value) | Other published prices | Change | Checked | | --- | --- | --- | --- | --- | --- | --- | --- | --- | | Fireworks | Ember-1Batch inference is billed at 50% of serverless pricing on both input and output | $3.00 | $0.30 | $15.00 | n.a. | Priority $3.75 / $18.75 | New · Oct 5 | On pageOct 23, 2026[docs.fireworks.ai ↗](https://docs.fireworks.ai/serverless/pricing) | | Fireworks | Kimi K3Model by moonshotaiBatch inference is billed at 50% of serverless pricing on both input and output | $3.00 | $0.30 | $15.00 | n.a. | Fast $4.50 / $22.50Priority $3.75 / $18.75 | No change | On pageOct 23, 2026[docs.fireworks.ai ↗](https://docs.fireworks.ai/serverless/pricing) | | Fireworks | Qwen 3.8 MaxModel by QwenBatch inference is billed at 50% of serverless pricing on both input and output | $2.00 | $0.25 | $6.00 | n.a. | Priority $3.00 / $9.00 | No change | On pageOct 23, 2026[docs.fireworks.ai ↗](https://docs.fireworks.ai/serverless/pricing) | | Fireworks | GLM 5.3Model by zai-orgBatch inference is billed at 50% of serverless pricing on both input and output | $1.40 | $0.26 | $4.40 | n.a. | Fast $2.10 / $6.60Priority $1.75 / $5.50 | No change | On pageOct 23, 2026[docs.fireworks.ai ↗](https://docs.fireworks.ai/serverless/pricing) | | Fireworks | Muse Spark OpenModel by meta-modelsBatch inference is billed at 50% of serverless pricing on both input and output | $1.25 | $0.15 | $4.25 | n.a. | Priority $1.88 / $6.38 | New · Oct 20 | On pageOct 23, 2026[docs.fireworks.ai ↗](https://docs.fireworks.ai/serverless/pricing) | | Fireworks | NVIDIA Nemotron 3 Ultra (Preview)Model by nvidiaBatch inference is billed at 50% of serverless pricing on both input and output | $0.60 | $0.12 | $2.40 | n.a. | Priority $0.75 / $3.00 | No change | On pageOct 23, 2026[docs.fireworks.ai ↗](https://docs.fireworks.ai/serverless/pricing) | | Fireworks | DeepSeek V4.1 FlashModel by deepseek-aiBatch inference is billed at 50% of serverless pricing on both input and output | $0.30 | $0.007 | $1.20 | n.a. | Priority $0.38 / $1.50 | +81.8% | On pageOct 23, 2026[docs.fireworks.ai ↗](https://docs.fireworks.ai/serverless/pricing) | | Fireworks | DeepSeek V4.1 Flash 1017Model by deepseek-aiBatch inference is billed at 50% of serverless pricing on both input and output | $0.30 | $0.006 | $1.20 | n.a. | Priority $0.38 / $1.50 | New · Oct 19 | On pageOct 23, 2026[docs.fireworks.ai ↗](https://docs.fireworks.ai/serverless/pricing) | | Fireworks | MiniMax M3Model by MiniMaxAIBatch inference is billed at 50% of serverless pricing on both input and output | $0.30 | $0.06 | $1.20 | n.a. | Priority $0.45 / $1.80 | No change | On pageOct 23, 2026[docs.fireworks.ai ↗](https://docs.fireworks.ai/serverless/pricing) | | Fireworks | OpenAI GPT OSS 120BModel by openaiBatch inference is billed at 50% of serverless pricing on both input and output | $0.15 | $0.015 | $0.60 | n.a. | Priority $0.18 / $0.72 | No change | On pageOct 23, 2026[docs.fireworks.ai ↗](https://docs.fireworks.ai/serverless/pricing) | | Fireworks | GLM 5.3 FlashModel by zai-orgBatch inference is billed at 50% of serverless pricing on both input and output | $0.15 | $0.03 | $0.50 | n.a. | Priority $0.19 / $0.63 | No change | On pageOct 23, 2026[docs.fireworks.ai ↗](https://docs.fireworks.ai/serverless/pricing) | | Fireworks | NVIDIA Nemotron 3.5 Lightning 30B A3BModel by nvidiaBatch inference is billed at 50% of serverless pricing on both input and output | $0.05 | $0.01 | $0.20 | n.a. | Priority $0.0625 / $0.25 | No change | On pageOct 23, 2026[docs.fireworks.ai ↗](https://docs.fireworks.ai/serverless/pricing) | Revenue per GPU-hour is SAVRN's calculation, not a price any seller charges: the 6.83 million input and 0.85 million output tokens one Vera Rubin GPU handles in an hour in CoreWeave's measured test, billed at this model's list prices. It puts a token price beside a GPU rental price; it says nothing about how fast this model actually runs. Sources ## Sources for Fireworks AI Every source cited on this page, once each. - fireworks.ai[fireworks.ai](https://fireworks.ai/pricing) - docs.fireworks.ai[docs.fireworks.ai](https://docs.fireworks.ai/serverless/pricing) GPU cloud ## More in the Index [Astra Intellectus](https://savrn.com/ai-index/companies/astra-intellectus)[Baseten](https://savrn.com/ai-index/companies/baseten)[Cirrascale](https://savrn.com/ai-index/companies/cirrascale)[Dell](https://savrn.com/ai-index/companies/dell)[Denvr Dataworks](https://savrn.com/ai-index/companies/denvr-dataworks)[DigitalOcean](https://savrn.com/ai-index/companies/digitalocean)[GMI Cloud](https://savrn.com/ai-index/companies/gmi-cloud)[HPE](https://savrn.com/ai-index/companies/hpe)[Hyperbolic](https://savrn.com/ai-index/companies/hyperbolic)[Impossible Cloud](https://savrn.com/ai-index/companies/impossible-cloud)[Lightning AI](https://savrn.com/ai-index/companies/lightning-ai)[Massed Compute](https://savrn.com/ai-index/companies/massed-compute)[Runpod](https://savrn.com/ai-index/companies/runpod)[TensorWave](https://savrn.com/ai-index/companies/tensorwave)[TheAI Cloud](https://savrn.com/ai-index/companies/theai-cloud)[Vast.ai (marketplace medians)](https://savrn.com/ai-index/companies/vast-ai)[Verda](https://savrn.com/ai-index/companies/verda) Capital figures come from the [Capital Atlas](https://savrn.com/data-center-capital-atlas), refreshed every Tuesday, Thursday and Saturday. Site commitments overlap reported capital expenditure and overlap one another, so each figure appears as its source states it and none are added into a single deployment number. Informational, not investment advice. Sources The SAVRN reference set ## Seven references, one system Capital, delay, policy, water, grid, permits and scarcity are one system seen from seven sides. Each reference is primary-sourced, refreshed on a schedule, and links into the others, so a project can be followed from the money committed to the docket that stopped it. Capital Atlas Who is funding AI data centers: capital providers, named sites, financing transactions, and the blocked-and-delayed record, state by state and company by company. [Open the atlas →](https://savrn.com/data-center-capital-atlas) Delay Watchlist Project-level slippage: named projects, jurisdictional actions, utility and federal dockets, SEC disclosures, and the interconnection queue. Open the watchlist → Moratorium Tracker The policy layer: every state measure and local moratorium mapped and cited, with one page per state. Open the tracker → Water Tracker Every federal, state, local and interstate water measure that touches a data center, plus a fifty-state water ledger. Open the water tracker → Grid Operator Watchlist ERCOT, PJM, MISO, CAISO, SPP, NYISO, ISO-NE and FERC: the large-load rules, filings and queue positions that decide whether a site can energize. Open the watchlist → Permits and Power Development Data center and substation permits, large loads in the interconnection queues, and the power plants planned to serve them, refreshed hourly from public records. Open the permits tracker → SAVRN Scarcity Tracker Eleven primary-sourced indicators of AI infrastructure scarcity, one composite index, read against the token index, SAVRN's own cost basis and the frontier ceiling. Open the scarcity tracker → Have a specific address? Site Intelligence reads all seven references against one location, county, utility and grid operator included, and cites every finding. [Check an address →](https://savrn.com/site-intelligence)