| title | Models |
|---|---|
| description | List and price 71 chat, image, video, music and speech models from one BlockRun API — provider rates, no margin on chat tokens, $0.001 per call. |
BlockRun provides access to models from multiple providers through a unified API.
GET https://blockrun.ai/api/v1/models
Returns a list of available models with pricing information. The response now includes extended metadata for each model.
Each model object in the response includes:
| Field | Type | Description |
|---|---|---|
id |
string | Model identifier (e.g., openai/gpt-5.5) |
object |
string | Always "model" (OpenAI-compatible envelope) |
owned_by |
string | Model maker (e.g., openai, anthropic, xai) |
name |
string | Display name (e.g., "GPT-5.5") |
description |
string | Model description |
context_window |
number | Context window size in tokens |
max_output |
number | Maximum output tokens |
categories |
string[] | Model capabilities: "chat", "reasoning", "coding", "vision" (image / video / audio rows carry "image", "video", "audio", "speech", "sound-effects") |
billing_mode |
string | "paid" (per-token), "flat" (per-request), "free", or a media mode such as "per_image" |
pricing |
object | { input, output } in USD per 1M tokens for per-token models; { flat } for flat-priced models (fee-inclusive); { per_image }, { per_second }, etc. for media |
Only models that are currently available are returned — there is no available flag to check.
{
"object": "list",
"data": [
{
"id": "openai/gpt-5.5",
"object": "model",
"created": 1700000000,
"owned_by": "openai",
"name": "GPT-5.5",
"description": "OpenAI's flagship — first fully retrained base since GPT-4.5; 1M context, 128K output, native agent + computer use",
"context_window": 1050000,
"max_output": 128000,
"categories": ["chat", "coding", "vision"],
"billing_mode": "paid",
"pricing": { "input": 5.00, "output": 30.00 }
}
]
}:::note
89 chat / LLM models are publicly listed on mainnet, plus 12 image, 8 video, 1 music, 5 text-to-speech, and 1 sound-effects model — covering chat, image, video, music, speech, and sound-effects generation from one API. Additional deprecated / superseded LLM IDs remain routable for backwards compatibility but are hidden from the catalog. Call GET /api/v1/models for the exact live list.
:::
All prices shown are provider rates — and, for per-token chat, also the billed rates: BlockRun adds no platform margin on chat tokens, only the flat $0.001/request transaction fee. Media and Live Search still carry a 5% platform fee.
Astra is the flagship; Sol (released 2026-09-22 with Luna) is the cost-efficient tier below it, and GPT-6.1 Sol (released 2026-09-29) is its refresh at the same price with a cheaper cached rate ($0.10/M against Sol's $0.20/M). All four bill a long-context tier — 2x input and cached rates, 1.5x output for the whole request once the prompt exceeds 272K tokens (mirrors OpenAI's official pricing: gpt-6-sol and gpt-6.1-sol are $4.00/M in · $15.00/M out above the threshold). Astra, Sol and Luna serve Flex at half the standard rate; GPT-6.1 Sol does not offer Flex yet.
| Model ID | Name | Input Price | Output Price | Context |
|---|---|---|---|---|
openai/gpt-6-astra |
GPT-6 Astra | $10.00/M | $50.00/M | 1M |
openai/gpt-6.1-sol |
GPT-6.1 Sol | $2.00/M | $10.00/M | 1M |
openai/gpt-6-sol |
GPT-6 Sol | $2.00/M | $10.00/M | 1M |
openai/gpt-6-luna |
GPT-6 Luna | $0.10/M | $0.50/M | 1M |
GPT-6 models accept reasoning_effort low through max and reject temperature other than 1, top_p, penalties, logprobs and stop. On plain chat the gateway lowers max to xhigh. Tool calls, which it serves through OpenAI's Responses API, run at the effort you ask for, max included, and at medium when none is sent. Higher effort spends more reasoning, which bills as output, so the per-call price scales with it: the output share of the quote is 2.5x at high, 3x at xhigh and 4.5x at max (never past max_tokens); no effort, low and medium are priced as before. none and minimal are raised to low on Astra and GPT-6.1 Sol; Sol and Luna accept none, and raise minimal to low.
Released 2026-07-09 — three fixed tiers (Sol / Terra / Luna) replacing the single-model-plus-effort-knob line. Note: on /v1/chat/completions, GPT-5.6 accepts function tools only with reasoning_effort: "none" — the BlockRun gateway sets this automatically when tools are present, so no client change is needed.
| Model ID | Name | Input Price | Output Price | Context |
|---|---|---|---|---|
openai/gpt-5.6-sol |
GPT-5.6 Sol | $4.00/M | $20.00/M | 1M |
openai/gpt-5.6-sol-pro |
GPT-5.6 Sol Pro | $4.00/M | $20.00/M | 1M |
openai/gpt-5.6-terra |
GPT-5.6 Terra | $2.00/M | $12.00/M | 1M |
openai/gpt-5.6-terra-pro |
GPT-5.6 Terra Pro | $2.00/M | $12.00/M | 1M |
openai/gpt-5.6-luna |
GPT-5.6 Luna | $0.20/M | $1.20/M | 1M |
openai/gpt-5.6-luna-pro |
GPT-5.6 Luna Pro | $0.20/M | $1.20/M | 1M |
Released 2026-04-23 — first fully retrained base since GPT-4.5.
| Model ID | Name | Input Price | Output Price | Context |
|---|---|---|---|---|
openai/gpt-5.5-pro |
GPT-5.5 Pro | $30.00/M | $180.00/M | 1M |
openai/chat-latest |
ChatGPT Instant (GPT-5.5) | $5.00/M | $30.00/M | 128K |
openai/gpt-5.5 |
GPT-5.5 | $5.00/M | $30.00/M | 1M |
| Model ID | Name | Input Price | Output Price | Context |
|---|---|---|---|---|
openai/gpt-5.4-pro |
GPT-5.4 Pro | $30.00/M | $180.00/M | 1M |
openai/gpt-5.4 |
GPT-5.4 | $2.50/M | $15.00/M | 1M |
openai/gpt-5.4-mini |
GPT-5.4 Mini | $0.75/M | $4.50/M | 400K |
openai/gpt-5.4-nano |
GPT-5.4 Nano | $0.20/M | $1.25/M | 1M |
| Model ID | Name | Input Price | Output Price | Context |
|---|---|---|---|---|
openai/gpt-5.2-pro |
GPT-5.2 Pro | $21.00/M | $168.00/M | 400K |
openai/gpt-5.2 |
GPT-5.2 | $1.75/M | $14.00/M | 400K |
openai/gpt-5.3-codex |
GPT-5.3 Codex | $1.75/M | $14.00/M | 400K |
openai/gpt-5.1 |
GPT-5.1 | $1.25/M | $10.00/M | 400K |
openai/gpt-5-mini |
GPT-5 Mini | $0.25/M | $2.00/M | 200K |
| Model ID | Name | Input Price | Output Price | Context |
|---|---|---|---|---|
openai/o1 |
o1 | $15.00/M | $60.00/M | 200K |
openai/o3 |
o3 | $2.00/M | $8.00/M | 200K |
openai/o3-mini |
o3-mini | $1.10/M | $4.40/M | 128K |
openai/o4-mini |
o4-mini | $1.10/M | $4.40/M | 128K |
| Model ID | Name | Input Price | Output Price | Context |
|---|---|---|---|---|
openai/gpt-4o |
GPT-4o | $2.50/M | $10.00/M | 128K |
openai/gpt-4.1 |
GPT-4.1 | $2.00/M | $8.00/M | 128K |
openai/gpt-4.1-mini |
GPT-4.1 Mini | $0.40/M | $1.60/M | 128K |
openai/gpt-4o-mini |
GPT-4o Mini | $0.15/M | $0.60/M | 128K |
openai/gpt-4.1-nano |
GPT-4.1 Nano | $0.10/M | $0.40/M | 128K |
| Model ID | Name | Input Price | Output Price | Context |
|---|---|---|---|---|
anthropic/claude-fable-5.1 |
Claude Fable 5.1 | $10.00/M | $50.00/M | 1M |
anthropic/claude-fable-5 |
Claude Fable 5 | $10.00/M | $50.00/M | 1M |
anthropic/claude-opus-4.5 |
Claude Opus 4.5 | $5.00/M | $25.00/M | 200K |
anthropic/claude-opus-4.7 |
Claude Opus 4.7 | $5.00/M | $25.00/M | 1M |
anthropic/claude-opus-4.8 |
Claude Opus 4.8 | $5.00/M | $25.00/M | 1M |
anthropic/claude-opus-5 |
Claude Opus 5 | $5.00/M | $25.00/M | 1M |
anthropic/claude-opus-5.5 |
Claude Opus 5.5 | $4.00/M | $20.00/M | 1M |
anthropic/claude-sonnet-4.5 |
Claude Sonnet 4.5 | $3.00/M | $15.00/M | 200K |
anthropic/claude-sonnet-4.6 |
Claude Sonnet 4.6 | $3.00/M | $15.00/M | 1M |
anthropic/claude-sonnet-5 |
Claude Sonnet 5 | $2.00/M | $10.00/M | 1M |
anthropic/claude-sonnet-5.5 |
Claude Sonnet 5.5 | $2.00/M | $10.00/M | 1M |
anthropic/claude-haiku-4.5 |
Claude Haiku 4.5 | $1.00/M | $5.00/M | 200K |
:::warning{title="Claude Opus 4.7 / 4.8 / 5 / 5.5, Fable 5 / 5.1 and Sonnet 5 / 5.5 behavior"}
These models reject all sampling parameters (temperature, top_p, top_k); the gateway drops them so calls succeed. They use adaptive thinking (built-in, not API-configurable). The model may decline a request with HTTP 200 and stop_reason: "refusal" (finish_reason: "content_filter" on the OpenAI-compatible endpoint) — check the stop reason before reading content.
Opus 5.5 and Sonnet 5.5 add three differences, all absorbed by the gateway so a request that works on Opus 5 still works here:
- Forced tool choice. Both — and Fable 5.1 — reject
tool_choice: "required"/ a named tool (Anthropicany/tool). The gateway serves it asauto; name the tool in your prompt if the call must happen. - Turning thinking off. Opus 5.5 cannot turn thinking off at all — a
{"type": "disabled"}block is dropped and the model thinks adaptively; use a lowoutput_config.effortto keep it short. Sonnet 5.5 calls "off"between_tools; the gateway translatesdisabledfor you and caps effort athigh, the most that mode allows. - Cache reads on Opus 5.5 are $0.20/M — 0.05x input, where other Claude models read at 0.1x. :::
| Model ID | Name | Input Price | Output Price | Context |
|---|---|---|---|---|
google/gemini-4-argon |
Gemini 4 Argon | $2.00/M | $10.00/M | 1M |
google/gemini-3.1-pro |
Gemini 3.1 Pro | $2.00/M | $12.00/M | 1M |
google/gemini-2.5-pro |
Gemini 2.5 Pro | $1.25/M | $10.00/M | 1M |
google/gemini-3.5-flash |
Gemini 3.5 Flash | $1.50/M | $9.00/M | 1M |
google/gemini-3.8-flash |
Gemini 3.8 Flash | $0.75/M | $3.75/M | 1M |
google/gemini-3.6-flash |
Gemini 3.6 Flash | $0.75/M | $3.75/M | 1M |
google/gemini-3-flash-preview |
Gemini 3 Flash Preview | $0.50/M | $3.00/M | 1M |
google/gemini-2.5-flash |
Gemini 2.5 Flash | $0.30/M | $2.50/M | 1M |
google/gemini-3.5-flash-lite |
Gemini 3.5 Flash Lite | $0.30/M | $2.50/M | 1M |
google/gemini-3.1-flash-lite |
Gemini 3.1 Flash Lite | $0.25/M | $1.50/M | 1M |
google/gemini-2.5-flash-lite |
Gemini 2.5 Flash Lite | $0.10/M | $0.40/M | 1M |
Gemini Pro models (gemini-2.5-pro, gemini-3.1-pro) bill a long-context tier — 2x input, 1.5x output above 200K prompt tokens (mirrors Google's official pricing: gemini-2.5-pro is $2.50/M in · $15.00/M out, gemini-3.1-pro is $4.00/M in · $18.00/M out above the threshold). Flash / Flash-Lite are flat-priced.
| Model ID | Name | Input Price | Output Price | Context |
|---|---|---|---|---|
xai/grok-4.7 |
Grok 4.7 | $2.00/M | $6.00/M | 500K |
xai/grok-4.6 |
Grok 4.6 | $2.00/M | $6.00/M | 500K |
xai/grok-4.5 |
Grok 4.5 | $2.00/M | $6.00/M | 500K |
xai/grok-4.3 |
Grok 4.3 | $1.25/M | $2.50/M | 1M |
xai/grok-build-0.1 |
Grok Build 0.1 | $1.00/M | $2.00/M | 256K |
Grok bills a long-context tier at 2x the rates above once a request's prompt reaches 200K tokens (mirrors xAI's official pricing — e.g. Grok 4.7 is $4.00/M in · $12.00/M out above the threshold). Live Search adds one flat surcharge per call: $0.30 on Grok 4.5 / 4.6 / 4.7 / 4.20, $0.12 on Grok 4.3 and below. Grok Imagine image/video SKUs are listed under Image / Video Generation below.
| Model ID | Name | Input Price | Output Price | Context |
|---|---|---|---|---|
deepseek/deepseek-v4-pro |
DeepSeek V4 Pro | $1.32/M | $3.96/M | 1M |
deepseek/deepseek-v4-flash-vision-exp |
DeepSeek V4 Flash Vision (image input) | $0.30/M | $1.20/M | 1M |
deepseek/deepseek-v4.1-flash |
DeepSeek V4.1 Flash (non-thinking) | $0.14/M | $0.28/M | 1M |
deepseek/deepseek-chat |
DeepSeek Chat (V4.1 Flash) — compatibility id, same model as deepseek/deepseek-v4.1-flash |
$0.14/M | $0.28/M | 1M |
deepseek/deepseek-reasoner |
DeepSeek Reasoner (V4.1 Flash) — same model with thinking on | $0.14/M | $0.28/M | 1M |
| Model ID | Name | Input Price | Output Price | Context |
|---|---|---|---|---|
zai/glm-5.1 |
GLM-5.1 | $1.40/M | $4.40/M | 200K |
zai/glm-5.2 |
GLM-5.2 | $1.40/M | $4.40/M | 1M |
zai/glm-5.3 |
GLM-5.3 | $1.40/M | $4.40/M | 1M |
zai/glm-5-turbo |
GLM-5 Turbo | $1.20/M | $4.00/M | 200K |
zai/glm-5 |
GLM-5 | $1.00/M | $3.20/M | 200K |
zai/glm-5.3-flash |
GLM-5.3 Flash | $0.15/M | $0.50/M | 1M |
| Model ID | Name | Input Price | Output Price | Context |
|---|---|---|---|---|
moonshot/kimi-k3.1-pro |
Kimi K3.1 Pro | $2.00/M | $10.00/M | 1M |
K3.1 Pro is the current flagship — Moonshot's post-trained successor to K3, built for long-horizon coding and agents, with a 1M-token context window, image + text input, and reasoning_content on completions. Cached input is $0.20/M. K3 ($3.00/$15.00) remains routable but superseded. K2.7 (256K, adds video input) remains routable but superseded; K2.6 and K2.5 are earlier multi-modal generations, still routable.
| Model ID | Name | Input Price | Output Price | Context |
|---|---|---|---|---|
minimax/minimax-m2.7 |
MiniMax M2.7 | $0.30/M | $1.20/M | 200K |
minimax/minimax-m3 |
MiniMax M3 | $0.30/M | $1.20/M | 1M |
| Model ID | Name | Input Price | Output Price | Context |
|---|---|---|---|---|
qwen/qwen3.8-max |
Qwen3.8 Max (flagship) | $2.00/M | $6.00/M | 1M |
qwen/qwen3.7-max |
Qwen3.7 Max | $1.475/M | $4.425/M | 1M |
qwen/qwen3.7-plus |
Qwen3.7 Plus | $0.32/M | $1.28/M | 1M |
qwen/qwen3.7-flash |
Qwen3.7 Flash | $0.03/M | $0.13/M | 1M |
qwen/qwen3.8-flash |
Qwen3.8 Flash (image input) | $0.15/M | $0.47/M | 1M |
| Model ID | Name | Input Price | Output Price | Context |
|---|---|---|---|---|
tencent/hy4-preview |
Tencent Hy4 Preview (770B MoE, reasoning) | $0.834/M | $2.501/M | 1M |
tencent/hy3 |
Tencent Hy3 | $0.132/M | $0.528/M | 256K |
| Model ID | Name | Input Price | Output Price | Context |
|---|---|---|---|---|
poolside/laguna-s-2.1 |
Laguna S 2.1 (coding) | $0.09/M | $0.18/M | 1M |
| Model ID | Name | Input Price | Output Price | Context |
|---|---|---|---|---|
mistral/mistral-large-4 |
Mistral Large 4 (reasoning, image input) | $1.36/M | $4.18/M | 512K |
| Model ID | Name | Input Price | Output Price | Context |
|---|---|---|---|---|
xiaomi/mimo-v2.5 |
Xiaomi MiMo-V2.5 (multimodal) | $0.14/M | $0.28/M | 1M |
xiaomi/mimo-v2.5-pro |
Xiaomi MiMo-V2.5 Pro | $0.435/M | $0.87/M | 1M |
Open-weight models billed at a flat per-request price instead of per token — the request is the unit, whatever its length.
| Model ID | Name | Price | Context |
|---|---|---|---|
openai/gpt-oss-120b |
GPT-OSS 120B | $0.002/request | 128K |
openai/gpt-oss-20b |
GPT-OSS 20B | $0.001/request | 128K |
Open-weight models served free of charge (no x402 payment), subject to a small per-IP rate limit. The free tier auto-routes around any temporarily unavailable model, so the live set is best read from GET /api/v1/models (filter on billing_mode: "free"). There are 8 free models listed on mainnet.
| Model ID | Name | Input Price | Output Price |
|---|---|---|---|
nvidia/nemotron-3-ultra-550b |
Nemotron 3 Ultra 550B (1M ctx) | FREE | FREE |
nvidia/nemotron-3.5-lightning |
Nemotron 3.5 Lightning (1M ctx) | FREE | FREE |
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning |
Nemotron 3 Nano Omni (vision) | FREE | FREE |
nvidia/llama-3.2-11b-vision |
Llama 3.2 11B Vision | FREE | FREE |
cohere/north-mini-code |
Cohere North Mini Code (coding) | FREE | FREE |
poolside/laguna-xs-2.1 |
Poolside Laguna XS 2.1 (coding) | FREE | FREE |
nvidia/muse-glimmer-30b |
Muse Glimmer 30B (Meta, reasoning) | FREE | FREE |
Media prices below include the 5% media margin; the flat $0.001 transaction fee is added per call.
| Model ID | Name | Price |
|---|---|---|
openai/gpt-image-1 |
GPT Image 1 | $0.021-0.042/image |
openai/gpt-image-2 |
ChatGPT Images 2.0 | $0.063-0.126/image |
google/nano-banana |
Nano Banana | $0.0525/image |
google/nano-banana-2 |
Nano Banana 2 | $0.0945/image |
google/nano-banana-pro |
Nano Banana Pro | $0.105-0.1575/image |
xai/grok-imagine-image |
Grok Imagine | $0.021/image |
xai/grok-imagine-image-2.0 |
Grok Imagine 2.0 | $0.042/image |
xai/grok-imagine-image-pro |
Grok Imagine Pro | $0.0525/image |
zai/cogview-4 |
CogView-4 | $0.01575-0.021/image |
bytedance/seedream-5-pro |
Seedream 5.0 Pro | $0.047-0.095/image (async, ~2 min) |
Seedance defaults to 720p with synced audio for text-to-video; pass resolution / generate_audio to override. See Video Generation API.
| Model ID | Name | Price (5s 720p default) | Max duration |
|---|---|---|---|
xai/grok-imagine-video |
Grok Imagine Video | $0.05/sec @480p default · $0.07/sec @720p, + $0.001/generation (8s 480p = $0.401) | 15s |
xai/grok-imagine-video-1.5 |
Grok Imagine Video 1.5 | $0.08/sec @480p default · $0.14/sec @720p · $0.25/sec @1080p, + $0.001/generation (8s 480p = $0.641) | 15s |
bytedance/seedance-1.5-pro |
Seedance 1.5 Pro | ~$0.070/sec ($0.35 / 5s clip) | 12s |
bytedance/seedance-2.0-mini |
Seedance 2.0 Mini | ~$0.080/sec ($0.40 / 5s clip) | 15s |
bytedance/seedance-2.0-fast |
Seedance 2.0 Fast | ~$0.165/sec ($0.83 / 5s clip) | 15s |
bytedance/seedance-2.0 |
Seedance 2.0 Pro | ~$0.227/sec ($1.14 / 5s clip) | 15s |
bytedance/seedance-2.5 |
Seedance 2.5 | ~$0.315/sec ($1.58 / 5s clip) | 30s |
azure/sora-2 |
Sora 2 | $0.10/sec (4s = $0.42) | 12s |
For character consistency across multiple Seedance videos, enroll a Virtual Portrait ($0.011 one-time, no government ID) for AI characters, or a RealFace ($0.011 one-time, no government ID, requires brief on-phone liveness check) for real people. Pass the returned ta_xxx as real_face_asset_id.
Each model includes a categories array in the API response. Categories indicate model capabilities:
- chat - General conversation
- reasoning - Complex problem-solving
- coding - Code generation and analysis
- vision - Image understanding
Filter models by category:
models = client.list_models()
reasoning_models = [m for m in models if "reasoning" in m.get("categories", [])]Prices are per 1 million tokens. Your actual cost depends on:
- Input tokens - Length of your prompt and context
- Output tokens - Length of the model's response
- Transaction fee - a flat $0.001 per request; chat tokens carry no platform margin (media and Live Search carry 5%)
The SDK calculates the exact price before each request.
Want to save 84% automatically? ClawRouter routes each request to the cheapest model that can handle it.
::::tabs
:::tab{label="Python"}
from blockrun_llm import LLMClient
client = LLMClient()
models = client.list_models()
for model in models:
pricing = model.get("pricing", {})
print(f"{model['id']}: ${pricing.get('input')}/M input, context: {model['context_window']}")
print(f" Categories: {', '.join(model.get('categories', []))}"):::
:::tab{label="TypeScript"}
import { LLMClient } from '@blockrun/llm';
const client = new LLMClient({ privateKey: '0x...' });
const models = await client.listModels();
for (const model of models) {
console.log(`${model.id}: $${model.inputPrice}/M input, context: ${model.contextWindow}`);
console.log(` Categories: ${model.categories.join(', ')}`);
}:::
::::
::::cards
:::card{title="Chat Completions" href="chat-completions.md" icon="Brain"} Call any model ID from this catalog through the OpenAI-compatible endpoint. :::
:::card{title="Image Generation" href="image-generation.md" icon="Image"} Generate images with the GPT Image, Nano Banana, and CogView model family. :::
:::card{title="Save 84% with ClawRouter" href="../products/routing/clawrouter.md" icon="Route"} Route each prompt to the cheapest model that can handle it, automatically. :::
::::