BlockRun
Get started

Available Models

Every call priced in dollars before it runs. No account needed.

Mainnet models
New · October 2026GPT-6.1 SolMistral Large 4

GPT-6.1 Sol — the refreshed GPT-6 Sol, at the same price.

Chat: OpenAI openai/gpt-6.1-sol is $2.00 in / $10.00 out per 1M, the same as openai/gpt-6-sol at $2.00 / $10.00, with knowledge through April 2026, 1M context (a prompt over 272K tokens bills the whole request at the long-context rate, as OpenAI does), 128K output and vision. Tool calls go through the usual /v1/chat/completions; the gateway serves them where the model accepts them, at the reasoning effort you asked for. Mistral's flagship mistral/mistral-large-4 — 512K context, reasoning, image input — is $0.68 / $2.09 at Mistral's launch rate. Every call is quoted in dollars before it runs.

Still recent: claude-opus-5.5, claude-sonnet-5.5, xAI grok-4.7, gpt-6-sol · luna, zai/glm-5.3-flash (natively multimodal, 1M context), ByteDance seedance-2.5 (30s clips with synced audio), xAI grok-imagine-video-1.5 and gpt-5.6-sol · terra · luna — see the changelog for dates and prices. For consistent characters across clips, enroll a Seedance Virtual Portrait ($0.011, AI character) or Seedance RealFace ($0.011, real person + 1-min on-phone liveness check, no government ID). Generated assets are mirrored to BlockRun's storage so URLs don't expire.

115 models

How pricing works on BlockRun

Every model above is billed per request, in USDC, settled on-chain through the x402 protocol. There is no subscription, no monthly minimum, and no API key to provision — a request arrives unpaid, the gateway answers with a signed price quote, your client signs it, and the retry returns the completion. Chat models are priced per million input and output tokens; image, video, music and speech models are priced per image, per second, per track, and per thousand characters respectively.

Token prices track each upstream lab's public list price with no markup on chat tokens — only a $0.001 per-request fee that covers on-chain settlement (media models carry a 5% margin). Because you pay per call, an agent that makes ten requests a day costs cents a month, and one that makes ten thousand pays exactly ten thousand times the per-call price — the unit economics do not change with volume, and nothing expires unused.

Choosing a model

The catalog spans 88 chat and reasoning models alongside image, video, music and speech generation, for 115 in total. Use the Reasoning filter for long-horizon planning and hard analytical work, Coding for repository-scale edits and agentic tool use, and Vision when requests carry images. The Free filter lists models that need no payment header at all — useful for prototyping an integration before you fund a wallet.

Every model is reachable through the same OpenAI-compatible /v1/chat/completions endpoint, so switching between them is a one-line change to the model field. See the documentation for request shapes and the pricing page for a full per-model rate card.