Skip to content

Press a switch to hold it out

Optimize utility per dollar, on every inference request.

Dispatch routes every request across frontier, open-source, bespoke and sovereign models, behind one base URL.

Example request
—
Bar
—
Model
—
Cost
—
01 / Your bar

For every bar, one model is cheapest.

Third place costs $1.34 a task and first place costs $9.15.

61 models · 10 on the frontier

Pareto frontier

Arena score against median cost per task

Chart of 61 models that publish a cost. Median cost a task runs left to right on a log scale from ten dollars down to one cent, so cost falls as you read across, and Arena's score runs bottom to top, in percentage points over the average model. 10 of them are Pareto-optimal and form the frontier, a line through Claude Fable 5.2 (Max) at $9.15 down to GPT-6 Luna (Low) at $0.01. For any bar you set, the cheapest model at or above it is the one Dispatch routes to.

  1. Claude Fable 5.2 (Max): $9.15 a task, +28.61%.
  2. Claude Opus 5.5 (Max): $5.87 a task, +18.19%.
  3. Gemini 4 Carbon (High): $1.34 a task, +16.45%.
  4. GPT-6.1 Sol (Max): $1.00 a task, +11.78%.
  5. GPT-6.1 Terra (Max): $0.88 a task, +11.34%.
  6. Gemini 4 Argon (High): $0.68 a task, +10.00%.
  7. GPT-6.1 Sol (Medium): $0.38 a task, +8.04%.
  8. GPT-6.1 Terra (Medium): $0.16 a task, +4.44%.
  9. Muse Ember (Max): $0.02 a task, +1.73%.
  10. GPT-6 Luna (Low): $0.01 a task, −7.18%.
Arena score against median cost per task, with the Pareto frontier and your bar+30%+20%+10%+0%−10%−20%$10$0.10$0.01MEDIAN COST PER TASK · USD→$1.34CLAUDE FABLE 5.2 (MAX)CLAUDE OPUS 5.5 (MAX)GEMINI 4 CARBON (HIGH)Arena score against median cost per task, with the Pareto frontier and your bar+30%+20%+10%+0%−10%−20%$10$0.10$0.01MEDIAN COST PER TASK · USD→$1.34CLAUDE FABLE 5.2 (MAX)CLAUDE OPUS 5.5 (MAX)GEMINI 4 CARBON (HIGH)GPT-6.1 SOL (MAX)GPT-6.1 SOL (MEDIUM)Arena score against median cost per task, with the Pareto frontier and your bar+30%+20%+10%+0%−10%−20%AVERAGE MODEL$10$0.50$0.10$0.02$0.01MEDIAN COST PER TASK · USD · LOG SCALECHEAPER →$1.34CLAUDE FABLE 5.2 (MAX)CLAUDE OPUS 5.5 (MAX)GEMINI 4 CARBON (HIGH)GPT-6.1 SOL (MEDIUM)GPT-6.1 TERRA (MEDIUM)MUSE EMBER (MAX)GPT-6 LUNA (LOW)BAR +16%Arena score against median cost per task, with the Pareto frontier and your bar+30%+20%+10%+0%−10%−20%AVERAGE MODEL$10$5$0.50$0.20$0.10$0.05$0.02$0.01MEDIAN COST PER TASK · USD · LOG SCALECHEAPER →$1.34CLAUDE FABLE 5.2 (MAX)CLAUDE OPUS 5.5 (MAX)GEMINI 4 CARBON (HIGH)GPT-6.1 SOL (MAX)GEMINI 4 ARGON (HIGH)GPT-6.1 SOL (MEDIUM)GPT-6.1 TERRA (MEDIUM)MUSE EMBER (MAX)GPT-6 LUNA (LOW)BAR +16%Arena score against median cost per task, with the Pareto frontier and your bar+30%+20%+10%+0%−10%−20%AVERAGE MODEL$10$0.50$0.10$0.02$0.01MEDIAN COST PER TASK · USD · LOG SCALECHEAPER →$1.34CLAUDE FABLE 5.2 (MAX)CLAUDE OPUS 5.5 (MAX)GEMINI 4 CARBON (HIGH)GPT-6.1 SOL (MAX)GEMINI 4 ARGON (HIGH)GPT-6.1 SOL (MEDIUM)GPT-6.1 TERRA (MEDIUM)MUSE EMBER (MAX)GPT-6 LUNA (LOW)BAR +16%Arena score against median cost per task, with the Pareto frontier and your bar+30%+20%+10%+0%−10%−20%AVERAGE MODEL$10$5$0.50$0.20$0.10$0.05$0.02$0.01MEDIAN COST PER TASK · USD · LOG SCALECHEAPER →$1.34CLAUDE FABLE 5.2 (MAX)CLAUDE OPUS 5.5 (MAX)GEMINI 4 CARBON (HIGH)GPT-6.1 SOL (MAX)GEMINI 4 ARGON (HIGH)GPT-6.1 SOL (MEDIUM)GPT-6.1 TERRA (MEDIUM)MUSE EMBER (MAX)GPT-6 LUNA (LOW)BAR +16%Arena score against median cost per task, with the Pareto frontier and your bar+30%+20%+10%+0%−10%−20%AVERAGE MODEL$10$5$0.50$0.20$0.10$0.05$0.02$0.01MEDIAN COST PER TASK · USD · LOG SCALECHEAPER →$1.34CLAUDE FABLE 5.2 (MAX)CLAUDE OPUS 5.5 (MAX)GEMINI 4 CARBON (HIGH)GPT-6.1 SOL (MAX)GEMINI 4 ARGON (HIGH)GPT-6.1 SOL (MEDIUM)GPT-6.1 TERRA (MEDIUM)MUSE EMBER (MAX)GPT-6 LUNA (LOW)BAR +16%
+16%
  • Frontier
  • Closed
  • Open weights
  • Routed to
  • Your bar

Pareto-optimal models

Most expensive first

  1. Claude Fable 5.2 (Max)Anthropic · Proprietary$9.15+28.61%
  2. Claude Opus 5.5 (Max)Anthropic · Proprietary$5.87+18.19%
  3. Gemini 4 Carbon (High)Google · Proprietary, preliminary$1.34+16.45%
  4. GPT-6.1 Sol (Max)OpenAI · Proprietary$1.00+11.78%
  5. GPT-6.1 Terra (Max)OpenAI · Proprietary$0.88+11.34%
  6. Gemini 4 Argon (High)Google · Proprietary$0.68+10.00%
  7. GPT-6.1 Sol (Medium)OpenAI · Proprietary$0.38+8.04%
  8. GPT-6.1 Terra (Medium)OpenAI · Proprietary$0.16+4.44%
  9. Muse Ember (Max)Meta · Proprietary$0.02+1.73%
  10. GPT-6 Luna (Low)OpenAI · Proprietary$0.01−7.18%

Routed to Gemini 4 Carbon (High) at $1.34 a task.

Source

Arena agent leaderboard, 13 Nov 2026. Public data, not a Dispatch measurement.

arena.ai/leaderboard/agent

The score

Arena’s score is each model’s improvement over the average model across Arena’s signals, in percentage points.

Coverage

2,979,271 sessions across 65 models, 61 of which publish a cost a task.

02 / How it works

One line of code, then it routes.

  1. client.pyExample
    1. 1client = OpenAI(
    2. - base_url=PROVIDER_URL,
    3. + base_url=DISPATCH_URL,
    4. 3 api_key=DISPATCH_KEY,
    5. 4)
    • 1 line changed
    • Routing
    01

    Change one line.

    Point your OpenAI or Anthropic client at Dispatch.

  2. 02

    Set your bar.

    Say how good a result has to be for each kind of work.

  3. 03

    It picks the cheapest that clears.

    When a provider fails or rate-limits, the request falls back to the next.

  4. 04

    It learns what you accept.

    The results you accept and reject improve the next route.

03 / Run it your way

Hosted by us, or inside your own walls.

  • Hosted or sovereign

    Use the endpoint we host, or run Dispatch in your own environment on your own provider keys.

  • Any model you can call

    Route across frontier and open-source models, models built for you, and models you run yourself.

  • Example

    The pool: one address in, four kinds of model behind it, and each request patched to the cheapest that clears its bar.

  • A record of every request

    See which model served each request and what it cost.

    requests.logExample
    1. 1ReconcileFrontierGPT-6.1 Sol $$$
    2. 2ExtractOpen sourceKimi K3 $  
    3. 3Mark upBespokecontracts-v2    No reply
    4. →Mark upFrontierGPT-6.1 Sol $$$Rerouted
    5. 4AnswerSovereignKimi K3.1 Pro $$ 
  • Integrity, if you want it

    Turn on Integrity and the model Dispatch picks is steered while it works.

Stop paying frontier prices for work a cheaper model does as well.

Tell us the kind of work you send and the bar it has to clear.

Get in touch