impulse

Llama Rank

Open weightsRerank
API id Llama-Rank-V1
Input / 1M
$0.10
at Together AI
Output / 1M
$0.00
at Together AI
Context window
8K
tokens
Max output
-
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at Together AI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.10$0.00

What it costs a month

At Together AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$30.00
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$48.00
  • Coding agent1,000 requests a day, 40K in / 2K out$120
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$240
Use your own numbers

Where to run it

1 host serve Llama Rank. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Together AIInference
Llama-Rank-V1
$0.10 / $0.00

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 License
Runtimes: 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 Together AI.

Smaller Meta models

No cheaper Meta model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • Qwen3 Reranker 8B
    Alibaba Qwen · on Novita AI
    $0.05 / $0.05
    Has every key capability
    50% less

Call it

Using Together AI's API.

Python
from litellm import completion

response = completion(
    model="together_ai/Llama-Rank-V1",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Llama Rank cost?

On Together AI, Llama Rank costs $0.10 per million input tokens.

Which APIs offer Llama Rank?

Llama Rank runs on 1 API: Together AI.

What is Llama Rank's context window?

8K tokens.

Is Llama Rank being retired?

It has been retired: Together AI retired it on 6 Feb 2026.

What are cheaper alternatives to Llama Rank?

Models that cost less and keep most of what it can do: Qwen3 Reranker 8B on Novita AI (50% less).

What is Llama Rank's API model id?

Use Llama-Rank-V1 with Together AI.

Sources

Raw catalog entry for Llama-Rank-V1 on Together AI
{
  "deprecation_date": "2026-02-06",
  "deprecation_source": "https://docs.together.ai/docs/deprecations",
  "input_cost_per_token": 1e-7,
  "litellm_provider": "together_ai",
  "max_input_tokens": 8192,
  "mode": "rerank",
  "output_cost_per_token": 0,
  "source": "https://api.together.ai/v1/models"
}