deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
Deepinfra textdeepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
Input
$0.2000
per 1M input tokens
Output
$0.8000
per 1M output tokens
Cache read
n/a
per 1M cached read tokens
Cache write
n/a
per 1M cache write tokens
Context window
1,048,576
Max output
1,048,576
Effective date
Aug 28, 2026
Estimate a workload
Enter token counts to see the cost at this model's rates.
Estimated cost:
$0.00
Price history
blended $ per 1M tokens (3:1)| Effective | Input | Output | Blended |
|---|---|---|---|
| Aug 28, 2026 | $0.20 | $0.80 | $0.35 |
| Jun 15, 2026 | $0.15 | $0.60 | $0.26 |
Other Deepinfra models
deepinfra/mistralai/Mistral-Nemo-Instruct-2407
· $0.0300/Mtok out
deepinfra/google/gemma-4-E4B-it
· $0.1000/Mtok out
deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
· $0.0400/Mtok out
deepinfra/meta-llama/Llama-3.2-3B-Instruct
· $0.0200/Mtok out
deepinfra/openai/gpt-oss-20b
· $0.1400/Mtok out
deepinfra/meta-llama/Meta-Llama-3-8B-Instruct
· $0.0600/Mtok out
Source: litellm. Confirm against the provider's official pricing before relying on these figures.