Get started in seconds with per token pricing, zero setup and no cold starts
Customize open models with your own data with minimal setup
Pay per GPU second for faster speeds, higher rate limits, and lower costs at scale
| Base model | $ / 1M tokens |
|---|---|
| Less than 4B parameters | $0.10 |
| 4B - 16B parameters | $0.20 |
| More than 16B parameters | $0.90 |
| MoE 0B - 56B parameters (e.g. Mixtral 8x7B) | $0.50 |
| MoE 56.1B - 176B parameters (e.g. DBRX, Mixtral 8x22B) | $1.20 |
| DeepSeek V3 | $0.90 |
| DeepSeek R1 (Fast) | $3.00 input, $8.00 output |
| DeepSeek R1 0528 (Fast) | $3.00 input, $8.00 output |
| GLM-4.5 and DeepSeek R1 (Basic) | $0.55 input, $2.19 output |
| Meta Llama 3.1 405B | $3.00 |
| Meta Llama 4 Maverick (Basic) | $0.22 input, $0.88 output |
| Meta Llama 4 Scout (Basic) | $0.15 input, $0.60 output |
| Qwen3 235B Family and GLM-4.5 Air | $0.22 input, $0.88 output |
| Qwen3 30B and Qwen Coder Flash | $0.15 input, $0.60 output |
| Kimi K2 Instruct | $0.60 input, $2.50 output |
| Qwen3 Coder 480B | $0.45 input, $1.80 output |
| OpenAI gpt OSS 120b | $0.15 input, $0.60 output |
| OpenAI gpt OSS 20b | $0.07 input, $0.30 output |
Discounts for prompt caching are available for enterprise deployments. Contact us to learn more.
Batch inference is priced at 50% of our serverless pricing for both input and output tokens. Learn more here.
Pay per second of audio input
| Model | $ / audio minute (billed per second) |
|---|---|
| Whisper-v3-large | $0.0015 |
| Whisper-v3-large-turbo | $0.0009 |
| Streaming transcription service | $0.0032 |
| Image model name | $ / step | Approx $ / image |
|---|---|---|
| All Non-Flux Models (SDXL, Playground, etc) | $0.00013 per step ($0.0039 per 30 step image) | $0.0002 per step ($0.006 per 30 step image) |
| FLUX.1 [dev] | $0.0005 per step ($0.014 per 28 step image) | N/A on serverless |
| FLUX.1 [schnell] | $0.00035 per step ($0.0014 per 4 step image) | N/A on serverless |
| FLUX.1 Kontext Pro | $0.04 per image | N/A |
| FLUX.1 Kontext Max | $0.08 per image | N/A |
All models besides the Flux Kontext models are charged by the number of inference steps (denoising iterations). The Flux Kontext models are charged a flat rate per generated image.
| Base model parameter count | $ / 1M input tokens |
|---|---|
| up to 150M | $0.008 |
| 150M - 350M | $0.016 |
| Base Model | $ / 1M training tokens |
|---|---|
| Models up to 16B parameters | $0.50 |
| Models 16.1B - 80B | $3.00 |
| Models 80B - 300B (e.g. Qwen3-235B, gpt-oss-120B) | $6.00 |
| Models >300B (e.g. DeepSeek V3, Kimi K2) | $10.00 |
Fine-tuning with images (VLM supervised fine-tuning) is billed per token as well. See this FAQ on calculating image tokens.
There is no additional cost for storing LoRA fine-tunes up to the quota for an account.
| GPU Type | $ / hour (billed per second) |
|---|---|
| A100 80 GB GPU | $2.90 |
| H100 80 GB GPU | $5.80 |
| H200 141 GB GPU | $6.99 |
| B200 180 GB GPU | $11.99 |
| AMD MI300X | $4.99 |
For estimates of per-token prices, see this blog. Results vary by use case, but we often observe improvements like ~250% higher throughput and 50% faster speed on Fireworks compared to open source inference engines.
