Llama 3.1 405B Instruct
llama-v3p1-405b-instructPricing
List prices at Fireworks AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $3.00 | $3.00 |
What it costs a month
At Fireworks AI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$1,125
- RAG over documents2,000 requests a day, 8K in / 0.6K out$1,548
- Coding agent1,000 requests a day, 40K in / 2K out$3,780
- Overnight batch20,000 requests a day, 4K in / 0.4K out$7,920
Where to run it
4 hosts serve Llama 3.1 405B Instruct. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Fireworks AIInference llama-v3p1-405b-instruct | $3.00 / $3.00 | llama-v3p1-405b-instruct | |
Together AIInference Llama-3.1-405B-Instruct | $3.50 / $3.50 +17% vs headline | Llama-3.1-405B-Instruct | |
Vertex AICloud llama-3.1-405b-instruct-maas | $5.00 / $16.00 +158% vs headline | llama-3.1-405b-instruct-maas | |
Oracle OCICloud meta.llama-3.1-405b-instruct | $10.68 / $10.68 +256% vs headline | meta.llama-3.1-405b-instruct |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Open weights
- License: Llama Community LicenseRuntimes: Ollama, TGI, llama.cpp, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Fireworks AI.
Smaller Meta models
- 33% less
- 96% less
- 93% less
Other frontier labs
- 33% less
- 50% less
- 58% less
- 93% less
Open-weight picks
- 29% less
- 43% less
- 71% less
- 74% less
Model line
Newer and older versions, at each lab's own price.
- UndatedLlama 3.1 405B InstructLatest$3.00 / $3.00
- UndatedLlama3.1 405B Instruct$0.80 / $0.80
- UndatedLlama3 405B InstructNot listed
Call it
Using Fireworks AI's API.
from litellm import completion
response = completion(
model="fireworks_ai/llama-v3p1-405b-instruct",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Llama 3.1 405B Instruct cost?
On Fireworks AI, Llama 3.1 405B Instruct costs $3.00 per million input tokens and $3.00 per million output tokens.
Which APIs offer Llama 3.1 405B Instruct?
Llama 3.1 405B Instruct runs on 4 APIs: Fireworks AI, Together AI, Vertex AI and Oracle OCI.
What is Llama 3.1 405B Instruct's context window?
131K tokens, with up to 16K tokens in one reply.
Is Llama 3.1 405B Instruct being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of Llama 3.1 405B Instruct?
No. Llama 3.1 405B Instruct is the newest model in its line.
What are cheaper alternatives to Llama 3.1 405B Instruct?
Models that cost less and keep most of what it can do: Muse Spark 1.3 on Meta Model API (33% less), GPT-6.1 Terra on OpenAI (33% less), Gemini 3.8 Flash on Google AI Studio (50% less) and Qwen4 Max on Together AI (29% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Llama 3.1 405B Instruct's API model id?
Use llama-v3p1-405b-instruct with Fireworks AI. Other hosts use their own ids: Llama-3.1-405B-Instruct on Together AI, llama-3.1-405b-instruct-maas on Vertex AI, meta.llama-3.1-405b-instruct on Oracle OCI.
Sources
Raw catalog entry for llama-v3p1-405b-instruct on Fireworks AI
{
"input_cost_per_token": 0.000003,
"litellm_provider": "fireworks_ai",
"max_input_tokens": 131072,
"max_output_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 0.000003,
"source": "https://fireworks.ai/pricing",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
}