impulse

Rune

Other
API id rune
Input / 1M
$0.042
at Fireworks AI
Output / 1M
$0.00
at Fireworks AI
Context window
262K
tokens
Max output
-
tokens per reply
Hosts
1
2 listings
Released
-
date not published

Pricing

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

TierInput / 1MOutput / 1M
Standard$0.042$0.00
Cached input
80% off input
$0.0084

What it costs a month

At Fireworks AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$9.58
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$12.10
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$22.18
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$101
Use your own numbers

Where to run it

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

HostIn / out per 1M
Fireworks AIInference
rune
$0.042 / $0.00
Show 1 more listings: regions, snapshots and variants
Fireworks AI
Alias
rune
$0.042 / $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

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 Independent models

No cheaper Independent model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

No cheaper open-weight match.

Call it

Using Fireworks AI's API.

Python
from litellm import completion

response = completion(
    model="fireworks_ai/rune",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Rune cost?

On Fireworks AI, Rune costs $0.042 per million input tokens. Cached input costs $0.0084 per million tokens.

Which APIs offer Rune?

Rune runs on 1 API: Fireworks AI.

What is Rune's context window?

262K tokens.

Is Rune being retired?

No retirement date is scheduled for it on any API we track.

What is Rune's API model id?

Use rune with Fireworks AI.

Sources

Raw catalog entry for rune on Fireworks AI
{
  "cache_read_input_token_cost": 8.4e-9,
  "input_cost_per_token": 4.2e-8,
  "litellm_provider": "fireworks_ai",
  "max_input_tokens": 262144,
  "mode": "evaluation",
  "output_cost_per_token": 0,
  "source": "https://docs.fireworks.ai"
}