Llama 4 Maverick costs $0.240/1M input tokens and $0.970/1M output tokens as of 2026-06-27. Openrouter publishes this model with a 128K tokens context window. o10 lists Llama 4 Maverick on AWS Bedrock, Together AI, and Fireworks AI at routing band C4. API slug llama-4-maverick. Verify list prices against the venue you call.
Last updated: 2026-06-27. Full catalog. Reference prices are dated snapshots. Compare total cost and measured task quality before choosing a route.
Llama 4 Maverick is a chat model from openrouter (slug: llama-4-maverick). Pick Llama 4 Maverick when you want Meta Llama on a fulfillment host (or your own GPUs) instead of a closed lab SKU. Published input pricing starts at $0.240/1M tokens. Context window: 128K tokens.
Catalog snapshot 2026-06-27.
When should you pick Llama 4 Maverick?
Pick Llama 4 Maverick when you want Meta Llama on a fulfillment host (or your own GPUs) instead of a closed lab SKU. Llama 4 Maverick is a Llama instruct checkpoint. Smaller Llama SKUs cut cost; larger ones raise quality. Prove the swap in shadow.
How does Llama 4 Maverick differ from sibling models?
Llama 4 Maverick is a Llama instruct checkpoint. Smaller Llama SKUs cut cost; larger ones raise quality. Prove the swap in shadow.
How much does Llama 4 Maverick cost per million tokens?
Llama 4 Maverick costs $0.240/1M input tokens and $0.970/1M output tokens in the gateway catalog snapshot (2026-06-27). Endpoint pricing may differ by fulfillment host.
Sourced from gateway catalog snapshot.
Where can you run Llama 4 Maverick?
Llama 4 Maverick is configured on AWS Bedrock, Together AI, and Fireworks AI. Known host IDs: meta: bedrock/us.meta.llama4-maverick-17b-instruct-v1:0; meta: together_ai/llama-4-maverick; meta: fireworks_ai/llama-4-maverick. This model is routable through o10 eval-gated routing.
What is Llama 4 Maverick's context window?
Llama 4 Maverick supports a 128K tokens context window in the gateway catalog snapshot. Context limits may vary by fulfillment host endpoint.
What o10 routing band is Llama 4 Maverick?
Llama 4 Maverick is classified at o10 routing band C4. Bands group models by cost tier and eval profile: C0 (economy), C1 (standard), C2 (capable), C3/C4 (frontier). Production routing is enabled for this slug.
Who makes Llama 4 Maverick?
Llama 4 Maverick is attributed to source provider openrouter in the o10 catalog. Fulfillment hosts (AWS Bedrock, Together AI, and Fireworks AI) supply API access; list pricing may differ by venue.
01Deep dive
Specifications
Llama 4 Maverick in the o10 unified catalog.
Llama 4 Maverick specifications
Field
Value
o10 slug
`llama-4-maverick`
Type
text
Band
C4
Routable
Yes
Source provider
openrouter
Primary host
AWS Bedrock
Gateway ID
`meta/llama-4-maverick`
Context window
128,000 tokens
Released
2025-04-05
02Deep dive
Token pricing
Gateway snapshot pricing for Llama 4 Maverick.
Llama 4 Maverick token pricing
Unit
Price
Input
$0.24/1M tokens
Output
$0.97/1M tokens
03Deep dive
Fulfillment hosts
Upstream venues configured for Llama 4 Maverick.
Llama 4 Maverick fulfillment routes
Host
Upstream model ID
meta
bedrock/us.meta.llama4-maverick-17b-instruct-v1:0
meta
together_ai/llama-4-maverick
meta
fireworks_ai/llama-4-maverick
04Deep dive
Gateway provider endpoints
Endpoint-level pricing and latency from the gateway catalog.
Llama 4 Maverick costs $0.240/1M input tokens and $0.970/1M output tokens in the gateway snapshot (2026-06-27). Verify against your provider's published pricing.
What is Llama 4 Maverick's context window?
Llama 4 Maverick supports 128K tokens in the gateway catalog snapshot. Host-specific endpoints may differ.
Which hosts serve Llama 4 Maverick?
Llama 4 Maverick (llama-4-maverick) is configured on: AWS Bedrock, Together AI, and Fireworks AI. Upstream model IDs are listed in the fulfillment routes section.
Is Llama 4 Maverick routable through o10?
Yes. Llama 4 Maverick is routable at band C4. Send model: "llama-4-maverick" or use an o10 smart routing alias.
How do I call Llama 4 Maverick via o10?
Use o10 slug "llama-4-maverick" or gateway ID "meta/llama-4-maverick" depending on your integration. Gateway-compatible endpoints accept OpenAI-style /v1 requests.
How does o10 route this model?
o10 routes Llama 4 Maverick only when per-use-case evals clear at your quality floor. Band C4 indicates cost tier. See /kyi for governance and /models/routing for smart aliases.