Pricing calculator
Pick a model, set your volume, and see the bill per day, week or month — with what Fireworks, Together AI and Nebius would charge for the same work. Every rate is the committed rate card; rival figures are dated snapshots.
Save $137,500/mo
on deepseek-v4-pro vs Nebius
12%
vs Nebius
Pick the model you use most
Choose a period and volume, or type your own
What share of your tokens are input rather than output
| Model | Context | Input / 1M | Cached / 1M | Output / 1M |
|---|---|---|---|---|
| bios-adaptive | 1M | $0.44 – $1.25 | $0.14 | $1.32 – $4.00 |
| chat-latest | 266K | $5.00 | $0.50 | $30.00 |
| claude-opus-5 | 1M | $5.00 | $0.50 | $25.00 |
| claude-opus-5-5 | 1M | $4.00 | $0.20 | $20.00 |
| claude-sonnet-5 | 1M | $2.00 | $0.20 | $10.00 |
| claude-sonnet-5-5 | 1M | $2.00 | $0.20 | $10.00 |
| deepseek-v4-flash | 128K | $0.10 | $0.01 | $0.25 |
| deepseek-v4-flash-0731 | 128K | $0.10 | $0.01 | $0.25 |
| deepseek-v4-pro | 128K | $1.40 | $0.14 | $3.40 |
| deepseek-v4-pro-0813 | 128K | $1.40 | $0.14 | $3.40 |
| deepseek-v4.1-flash | 1M | $0.40 | $0.04 | $1.60 |
| glm-5.2 | 1M | $1.40 | $0.14 | $3.40 |
| glm-5.3 | 1M | $1.40 | $0.26 | $4.40 |
| glm-5.3-flash | 1M | $0.15 | $0.03 | $0.50 |
| gpt-4.1 | 1M | $2.00 | $0.50 | $8.00 |
| gpt-4.1-mini | 1M | $0.40 | $0.10 | $1.60 |
| gpt-4.1-nano | 1M | $0.10 | $0.03 | $0.40 |
| gpt-4o | 125K | $2.50 | $1.25 | $10.00 |
| gpt-4o-mini | 125K | $0.15 | $0.08 | $0.60 |
| gpt-5 | 266K | $1.25 | $0.13 | $10.00 |
| gpt-5-mini | 266K | $0.25 | $0.03 | $2.00 |
| gpt-5-nano | 266K | $0.05 | $0.01 | $0.40 |
| gpt-5.1 | 266K | $1.25 | $0.13 | $10.00 |
| gpt-5.4 | 266K | $2.50 | $0.25 | $15.00 |
| gpt-5.4-mini | 266K | $0.75 | $0.08 | $4.50 |
| gpt-5.4-nano | 266K | $0.20 | $0.02 | $1.25 |
| gpt-5.5 | 266K | $5.00 | $0.50 | $30.00 |
| gpt-5.6-luna | 266K | $0.20 | $0.02 | $1.20 |
| gpt-5.6-sol | 266K | $4.00 | $0.40 | $20.00 |
| gpt-5.6-terra | 266K | $2.00 | $0.20 | $12.00 |
| gpt-6-astra | 266K | $10.00 | $1.00 | $50.00 |
| gpt-6-luna | 266K | $0.10 | $0.01 | $0.50 |
| gpt-6-sol | 266K | $2.00 | $0.20 | $10.00 |
| kimi-k2.7-code | 128K | $0.80 | $0.08 | $3.40 |
| kimi-k3 | 1M | $3.00 | $0.30 | $15.00 |
| minimax-m3 | 128K | $0.30 | $0.03 | $1.20 |
| o3 | 195K | $2.00 | $0.50 | $8.00 |
| o3-mini | 195K | $1.10 | $0.55 | $4.40 |
| o4-mini | 195K | $1.10 | $0.28 | $4.40 |
| qwen3.5-397b-a17b | 256K | $0.50 | $0.05 | $3.40 |
| qwen3.8-2.4t-a95b | 256K | $2.00 | $0.20 | $6.00 |
Scroll inside the table to see all models. USD per 1M tokens, as of 30 September 2026. Run BiOS Adaptive shows a range because its rate follows the model each request lands on; pinned models show their floor. Prompt caching is billed separately. The exact rate for the model you are about to call is shown in the dashboard before you send a request — treat that as authoritative over this table.
Neither product can run up a debt. Both draw from one pre-paid wallet. If the balance reaches zero you get a grace warning, and a running endpoint pauses rather than accruing charges. Top up and resume.