router channel · LLM router

OpenRouter pricing by model

An OpenAI-compatible routing layer that offers one API across multiple language-model providers and exposes route-level pricing.

Current answer: 25 accepted observations; an example row is $0.037 / 1M input tokens, checked Aug 27, 2026. Open the evidence source before purchase.

Where this provider fits

An OpenAI-compatible routing layer that offers one API across multiple language-model providers and exposes route-level pricing.

What can change the bill

  • Provider routing can affect latency and behavior
  • Input, output, and cached-token rates must be compared separately

Who should evaluate this route

  • Broad language-model catalog
  • OpenAI-compatible interface
  • Routing and provider visibility

Compare two nearby options

Use the same model, meter, configuration, and workload when comparing channels.

Recorded price evidence

OpenRouter recorded offers · checked-source scope
ProviderModelConfigurationRecorded priceEvidence
OpenRouterrouterClaude APImodel: anthropic/claude-sonnet-5 · chat-completions · Claude Sonnet 5 standard · not-applicable · no audio$0.2 / 1M cached input tokensstaleProvider sourceChecked Aug 22, 2026
OpenRouterrouterClaude APImodel: anthropic/claude-sonnet-5 · chat-completions · Claude Sonnet 5 standard · not-applicable · no audio$2 / 1M input tokensstaleProvider sourceChecked Aug 22, 2026
OpenRouterrouterClaude APImodel: anthropic/claude-sonnet-5 · chat-completions · Claude Sonnet 5 standard · not-applicable · no audio$10 / 1M output tokensstaleProvider sourceChecked Aug 22, 2026
OpenRouterrouterGLM-5.2model: z-ai/glm-5.2 · chat-completions · standard · not-applicable · no audio$0.966 / 1M input tokensstaleProvider sourceChecked Aug 22, 2026
OpenRouterrouterGLM-5.2model: z-ai/glm-5.2 · chat-completions · standard · not-applicable · no audio$3.036 / 1M output tokensstaleProvider sourceChecked Aug 22, 2026
OpenRouterrouterGPT APImodel: openai/gpt-5.6-luna · chat-completions · standard-under-270k-context · not-applicable · no audio$0.2 / 1M input tokensstaleProvider sourceChecked Aug 22, 2026
OpenRouterrouterGPT APImodel: openai/gpt-5.6-luna · chat-completions · standard-under-270k-context · not-applicable · no audio$1.2 / 1M output tokensstaleProvider sourceChecked Aug 22, 2026
OpenRouterrouterGPT-OSS 120Bmodel: openai/gpt-oss-120b · chat-completions · standard · not-applicable · no audio$0.03 / 1M cached input tokensstaleProvider sourceChecked Aug 22, 2026
OpenRouterrouterGPT-OSS 120Bmodel: openai/gpt-oss-120b · chat-completions · standard · not-applicable · no audio$0.037 / 1M input tokensstaleProvider sourceChecked Aug 27, 2026
OpenRouterrouterGPT-OSS 120Bmodel: openai/gpt-oss-120b · chat-completions · standard · not-applicable · no audio$0.17 / 1M output tokensstaleProvider sourceChecked Aug 27, 2026
OpenRouterrouterGemini APImodel: google/gemini-3.7-flash · chat-completions · batch-route · not-applicable · no audio$0.375 / 1M input tokensstaleProvider sourceChecked Aug 22, 2026
OpenRouterrouterGemini APImodel: google/gemini-3.7-flash · chat-completions · batch-route · not-applicable · no audio$1.875 / 1M output tokensstaleProvider sourceChecked Aug 22, 2026
OpenRouterrouterGrok APImodel: x-ai/grok-4.6 · chat-completions · Grok 4.6 base below 200k prompt tokens · not-applicable · no audio · source unit: base tier below 200,000 prompt tokens$0.5 / 1M cached input tokensstaleProvider sourceChecked Aug 22, 2026
OpenRouterrouterGrok APImodel: x-ai/grok-4.6 · chat-completions · Grok 4.6 base below 200k prompt tokens · not-applicable · no audio · source unit: base tier below 200,000 prompt tokens$2 / 1M input tokensstaleProvider sourceChecked Aug 22, 2026
OpenRouterrouterGrok APImodel: x-ai/grok-4.6 · chat-completions · Grok 4.6 base below 200k prompt tokens · not-applicable · no audio · source unit: base tier below 200,000 prompt tokens$6 / 1M output tokensstaleProvider sourceChecked Aug 22, 2026
OpenRouterrouterKimi APImodel: moonshotai/kimi-k3 · chat-completions · Kimi K3 standard · not-applicable · no audio$0.3 / 1M cached input tokensstaleProvider sourceChecked Aug 22, 2026
OpenRouterrouterKimi APImodel: moonshotai/kimi-k3 · chat-completions · Kimi K3 standard · not-applicable · no audio$3 / 1M input tokensstaleProvider sourceChecked Aug 22, 2026
OpenRouterrouterKimi APImodel: moonshotai/kimi-k3 · chat-completions · Kimi K3 standard · not-applicable · no audio$15 / 1M output tokensstaleProvider sourceChecked Aug 22, 2026
OpenRouterrouterMistral Medium 3.5model: mistralai/mistral-medium-3.5-20260430 · chat-completions · standard Mistral upstream · not-applicable · no audio$1.5 / 1M input tokensstaleProvider sourceChecked Aug 23, 2026
OpenRouterrouterMistral Medium 3.5model: mistralai/mistral-medium-3.5-20260430 · chat-completions · standard Mistral upstream · not-applicable · no audio$7.5 / 1M output tokensstaleProvider sourceChecked Aug 23, 2026
OpenRouterrouterQwen APImodel: qwen/qwen3.8-2.4t-a95b · chat-completions · standard · not-applicable · no audio$2 / 1M input tokensstaleProvider sourceChecked Aug 22, 2026
OpenRouterrouterQwen APImodel: qwen/qwen3.8-2.4t-a95b · chat-completions · standard · not-applicable · no audio$6 / 1M output tokensstaleProvider sourceChecked Aug 22, 2026
OpenRouterrouterQwen APImodel: qwen/qwen3.8-max · chat-completions · Qwen3.8 Max standard · not-applicable · no audio$0.25 / 1M cached input tokensstaleProvider sourceChecked Aug 22, 2026
OpenRouterrouterQwen APImodel: qwen/qwen3.8-max · chat-completions · Qwen3.8 Max standard · not-applicable · no audio$2 / 1M input tokensstaleProvider sourceChecked Aug 22, 2026
OpenRouterrouterQwen APImodel: qwen/qwen3.8-max · chat-completions · Qwen3.8 Max standard · not-applicable · no audio$6 / 1M output tokensstaleProvider sourceChecked Aug 22, 2026

Checked evidence, not a ranking: fresh rows were checked against the linked first-party source on the shown date. APIDir does not name a cheapest provider unless exact configurations and units match. Recheck before purchasing.

Model price comparisons for this provider

Follow each model page to compare this provider route with other accepted, source-linked offers on matching billing meters.

Related provider comparisons

Use a named alternative and explicit decision dimensions instead of comparing provider brands in the abstract.

Documented integrations

These pages describe public-source setup paths. They do not claim that a project uses this provider in a private production deployment.

Editorial review

Read the evidence, tradeoffs, and unresolved buying questions in the independent APIDir review.

Read OpenRouter review →

Questions developers ask

What does APIDir verify about OpenRouter?

APIDir separates the service channel from the underlying model owner, records exact offer configuration, links the source, and exposes the check date.

Does an entry mean APIDir recommends this provider?

No. A directory record is a research starting point. Review current sources, legal terms, limits, and a workload-specific test.

Why can a displayed observation be stale?

Historical observations remain visible for audit, but stale records do not support current cheapest or savings claims.

APIDir Delta · controlled rollout

Join the source-linked pricing update waitlist.

Confirm your address to join the waitlist. Editorial delivery starts only after sender, suppression, and evidence checks are active.