Model prices / Meta / Llama 4 Maverick 17B Instruct
Llama 4 Maverick 17B InstructOpen weights
Meta · released 2025-04-05
No price from the maker itself is on record for Llama 4 Maverick 17B Instruct. The lowest of 16 providers is Helicone: $0.15 per 1M input tokens and $0.6 per 1M output tokens (as of 2026-11-12). Context window: 1.05M tokens, up to 8.2K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
HHeliconeLowestllama-4-maverick | $0.15 | $0.6 | — | Lowest | Official docs |
NNanoGPTmeta-llama/ | $0.15 | $0.6 | $0.05 | Official docs | |
 IO.NETmeta-llama/ | $0.26875 | $0.82625 | $0.134375 | Official docs | |
 DigitalOceanllama-4-maverick | $0.25 | $0.87 | $0.05 | Official docs | |
 DevPass (LLM Gateway)llama-4-maverick-17b-instruct | $0.27 | $0.85 | — | Official docs | |
LLLM Gatewaynovita/ | $0.27 | $0.85 | — | Official docs | |
 Novita AImeta-llama/ | $0.27 | $0.85 | — | Official docs | |
 Vercel AI Gatewaymeta/ | $0.24 | $0.97 | — | Official docs | |
KKilo Gatewaymeta-llama/ | $0.35 | $1 | $0.17 | Official docs | |
 OpenRoutermeta-llama/ | $0.35 | $1 | $0.17 | Official docs | |
OOCI Generative AImeta. | $0.72 | $0.72 | — | Official docs | |
Wwatsonx.aimeta-llama/ | $0.371 | $1.484 | — | Official docs |
6 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
NNeonllama-4-maverick | $0.5 | $1.5 | — | Official docs | |
AAbacusDeprecatedmeta-llama/ | $0.14 | $0.59 | — | Deprecated | Official docs |
 Deep InfraDeprecatedmeta-llama/ | $0.2 | $0.8 | — | Deprecated | Official docs |
 Amazon BedrockDeprecatedmeta. | $0.24 | $0.97 | — | Deprecated | Official docs |
| Amazon BedrockDeprecatedus. | $0.24 | $0.97 | — | Deprecated | Official docs |
LLLM GatewayDeprecatedaws-bedrock/ | $0.24 | $0.97 | — | Deprecated | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Open multimodal Llama for strong reasoning with efficient everyday serving
Description from models.dev.
Specs
- Type
- Text
- Context
- 1.05M
- Max output
- 8.2K
- Input
- Text, Image
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2024-08
- Open weights
- Yes
- Released
- 2025-04-05
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.