Atlas / Models / Openrouter / Auto Router

Auto Router✓ Catalog verified

openrouter/auto

Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output. To see which model was used, visit Activity, or read the `model` attribute of the response. Your response will be priced at the same rate as the routed model. Learn more, including how to customize the models for routing, in our docs. Requests will be routed to the following models: - anthropic/claude-haiku-4.5 - anthropic/claude-opus-4.6 - anthropic/claude-sonnet-4.5 - anthropic/claude-sonnet-4.6 - deepseek/deepseek-r1 - google/gemini-2.5-flash-lite - google/gemini-3-flash-preview - google/gemini-3-pro-preview - google/gemini-3.1-pro-preview - meta-llama/llama-3.3-70b-instruct - minimax/minimax-m2.5 - mistralai/codestral-2508 - mistralai/mistral-7b-instruct-v0.1 - mistralai/mistral-large - mistralai/mistral-medium-3.1 - mistralai/mistral-small-3.2-24b-instruct-2506 - moonshotai/kimi-k2-thinking - moonshotai/kimi-k2.5 - openai/gpt-5 - openai/gpt-5-mini - openai/gpt-5-nano - openai/gpt-5.1 - openai/gpt-5.2 - openai/gpt-5.2-pro - openai/gpt-5.3-chat - openai/gpt-oss-120b - perplexity/sonar - qwen/qwen3-235b-a22b - x-ai/grok-3 - x-ai/grok-3-mini - x-ai/grok-4 - x-ai/grok-4.1-fast - z-ai/glm-5

Input price
$-1000000.00 /1M
Output price
$-1000000.00 /1M
Context
2M
Modalities
textimageaudiofile
Released
Nov 8, 2023
Tool calling
✓ Yes
Atlas signal
92/100
01

Overview

Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output. To see which model was used, visit Activity, or read the `model` attribute of the response. Your response will be priced at the same rate as the routed model. Learn more, including how to customize the models for routing, in our docs. Requests will be routed to the following models: - anthropic/claude-haiku-4.5 - anthropic/claude-opus-4.6 - anthropic/claude-sonnet-4.5 - anthropic/claude-sonnet-4.6 - deepseek/deepseek-r1 - google/gemini-2.5-flash-lite - google/gemini-3-flash-preview - google/gemini-3-pro-preview - google/gemini-3.1-pro-preview - meta-llama/llama-3.3-70b-instruct - minimax/minimax-m2.5 - mistralai/codestral-2508 - mistralai/mistral-7b-instruct-v0.1 - mistralai/mistral-large - mistralai/mistral-medium-3.1 - mistralai/mistral-small-3.2-24b-instruct-2506 - moonshotai/kimi-k2-thinking - moonshotai/kimi-k2.5 - openai/gpt-5 - openai/gpt-5-mini - openai/gpt-5-nano - openai/gpt-5.1 - openai/gpt-5.2 - openai/gpt-5.2-pro - openai/gpt-5.3-chat - openai/gpt-oss-120b - perplexity/sonar - qwen/qwen3-235b-a22b - x-ai/grok-3 - x-ai/grok-3-mini - x-ai/grok-4 - x-ai/grok-4.1-fast - z-ai/glm-5

Access: available through the official Openrouter API. Context window: 2M.

Pricing and metadata from the ModelsAtlas catalog.Last refreshed Aug 5, 2026
02

Specifications

API identifieropenrouter/auto
ProviderOpenrouter
Model typeMultimodal LLM
Context window2M catalog
Input modalitiestext · image · audio · file · video
Output modalitiestext · image
ReleasedNov 8, 2023
TokenizerRouter
ModeratedNo
Architecture modalitytext+image+file+audio+video->text+image
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_pweb_search_options
Source: provider documentation + catalog feedMethodology →

API defaults

Default parameters
{
  "top_p": null,
  "temperature": null,
  "frequency_penalty": null
}
03

Pricing

Live pricing components for openrouter/auto as published in the catalog.

$-1000000.00
Input /1M
$-1000000.00
Output /1M
Per request
Per image
Pricing componentRaw unit priceNormalizedUnit
Prompt tokens$-1$-1000000.00 / 1MPer input token
Completion tokens$-1$-1000000.00 / 1MPer output token
Request feeN/AN/APer request
Image feeN/AN/APer image unit
Web search feeN/AN/APer search request
Source: catalog pricing feedCompare all pricing →Cheapest models →
04

Cost calculator

Estimate monthly spend from your own token volumes.

Scale / Volume

Estimated Total Cost

$-700,000Calculated from current list pricing in the ModelsAtlas catalog.
05

Capabilities

CapabilityStatusWhat it means
Visual Understanding✓ SupportedImage and document analysis support
Audio Processing✓ SupportedSpeech and voice aligned flows
Tool Calling✓ SupportedSupports tools / function calling
Self-HostingNot advertisedDeploy outside managed APIs
Derived from catalog capability tags and supported parameters
06

Capability signals

Directional signals derived from model metadata and capability tags — not official benchmark submissions.

Auto Router
MMLU Signal (Reasoning)
95signal
Coding Signal (HumanEval proxy)
97signal
Math Signal (GSM8K proxy)
87signal
Science Signal (GPQA proxy)
87signal
Estimated from metadata — not an official benchmark runAll benchmarks →Methodology →
07

Quick start

Call Auto Router through an OpenAI-compatible client.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="openrouter/auto",
    messages=[{"role": "user", "content": "Explain quantum physics."}]
)

print(response.choices[0].message.content)
08

Alternatives

Closest models by context window from a different provider.

09

Sources & attribution

Pricing and metadata are maintained in the ModelsAtlas catalog.

Capability bars use metadata tags — directional estimates onlyHow we source and verify data →
10

Frequently asked questions

How much does Auto Router cost?

$-1000000.00 per 1M input tokens and $-1000000.00 per 1M output tokens on the official Openrouter API.

What is the context window of Auto Router?

Auto Router supports up to 2M tokens of context.

Does Auto Router support tool / function calling?

Yes, Auto Router supports tool / function calling — you can register tools and the model will emit structured tool calls.

How do I access Auto Router?

Use the official Openrouter API with the model id `openrouter/auto`. See the Quick start section above for code examples.