Llama-4-Maverick-17B-128E-Instruct-FP8 API Pricing
Llama-4-Maverick-17B-128E-Instruct-FP8 on DeepInfra costs $0.20 per 1M input tokens and $0.80 per 1M output tokens (as of ).
| Input | $0.20 / 1M tokens |
|---|---|
| Output | $0.80 / 1M tokens |
| Cached input (read) | — |
| Cache write | — |
| Batch input / output | — |
| Above 200K tokens (input / output) | — |
| Context window | 1.04858M tokens |
| Max output | 1.04858M tokens |
| Supports | tool calling |
| Deprecation date | None listed |
| API model id | meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 |
| In our records since |
What it costs for common jobs
Estimated from the list price above (no caching or batch discount).
| Job | Estimated cost |
|---|---|
| 1,000 chat replies (2,000 tokens in, 500 out each) | $0.80 |
| Summarising 100 long documents (50,000 in, 1,000 out each) | $1.08 |
| 1 million classification calls (300 in, 5 out each) | $64.00 |
Try your own numbers in the LLM API cost calculator.
Price history
- Between and : output price changed from $0.60 to $0.80 per 1M tokens.
- Between and : input price changed from $0.15 to $0.20 per 1M tokens.
Similarly priced models
| Model | Provider | Input / 1M | Output / 1M | Cached input / 1M | Context |
|---|---|---|---|---|---|
| Qwen3.5-35B-A3B | DeepInfra | $0.14 | $1.00 | $0.05 | 262K |
| Qwen3-Next-80B-A3B-Instruct | DeepInfra | $0.09 | $1.10 | — | 262K |
| Qwen2.5-72B-Instruct | DeepInfra | $0.36 | $0.40 | — | 33K |
| Qwen3-VL-235B-A22B-Instruct | DeepInfra | $0.20 | $0.88 | $0.11 | 262K |
| gpt-oss-120b-Ultra | DeepInfra | $0.20 | $0.95 | — | 131K |
| Qwen3.6-35B-A3B | DeepInfra | $0.10 | $0.95 | — | 262K |
| gemma-4-31B-it-Ultra | DeepInfra | $0.27 | $0.76 | — | 131K |
| MythoMax-L2-13b | DeepInfra | $0.40 | $0.40 | — | 4K |