Create a provider API key and set the local environment variable OPENROUTER_API_KEY, then run the example below.
Request URL
https://openrouter.ai/api/v1/chat/completions
Connection settings
Base URL: https://openrouter.ai/api/v1
Catalog model: meta-llama/llama-3.3-70b-instruct
Request API model: meta-llama/llama-3.3-70b-instruct
Protocol: openai
Provider routing: coreweave/fp16
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
curl
curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
"model": "meta-llama/llama-3.3-70b-instruct",
"messages": [
{
"role": "user",
"content": "Read this support ticket and return a JSON object with \"summary\", \"urgency\" (low, medium, or high), and \"next_step\". Use null for missing details.\n\nTicket: I paid for the Pro plan yesterday, but my account still shows Free. My team needs access before tomorrow’s demo."
}
],
"provider": {
"order": [
"coreweave/fp16"
],
"only": [
"coreweave/fp16"
],
"allow_fallbacks": false,
"quantizations": [
"fp16"
]
}
}'
Prompt for your coding agent
Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "meta-llama/llama-3.3-70b-instruct". Set provider.only to ["coreweave/fp16"] and allow_fallbacks to false. Apply the recorded quantization filter. A base slug can match multiple endpoints, so confirm the served route before using the reference price. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-11-22: $0.71 / 1M input tokens, $0.71 / 1M output tokens, $0.71 / 1M cache read tokens. API integration docs: https://openrouter.ai/docs. Billing scope and conditions: Served by CoreWeave through OpenRouter, not a direct-provider contract. Published rates for route coreweave/fp16; fp16 quantization. Other fees, tier conditions and regional access must be checked before use.. Source: https://openrouter.ai/api/v1/models/meta-llama/llama-3.3-70b-instruct/endpoints.
Task test prompt
Read this support ticket and return a JSON object with "summary", "urgency" (low, medium, or high), and "next_step". Use null for missing details.
Ticket: I paid for the Pro plan yesterday, but my account still shows Free. My team needs access before tomorrow’s demo.
Price facts
Input: $0.71 / 1M tokens
Output: $0.71 / 1M tokens
Cache read: $0.71 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-11-22T09:20:21.819Z
Source: https://openrouter.ai/api/v1/models/meta-llama/llama-3.3-70b-instruct/endpoints
Source check: 2026-11-22 · valid no later than 2026-11-23 09:21 UTC
Served by CoreWeave through OpenRouter, not a direct-provider contract. Published rates for route coreweave/fp16; fp16 quantization. Other fees, tier conditions and regional access must be checked before use.
Llama 3.3 70B Instruct API pricing: official and providers: 6 current published quote records across 1 exact API IDs and 6 providers. Compare API versions, currencies, regions and billing conditions separately; prices do not prove task quality or account access.
Latest recorded source check: 2026-11-22
Recorded changes
Latest 100 recorded price and availability changes
Showing up to 100 recent events. Prices for unavailable endpoints are retained for reference. Failed source checks do not establish that a price stayed unchanged.
Open a quote’s billing details for cache reads/writes, request fees and endpoint instructions. Batch, free, promotional and off-peak tiers are selected separately. Context-tier, storage, search, tax and platform fees may be excluded.
Find lower-cost alternatives
Find lower-cost alternatives
Choose your existing model to find lower reference costs with matching declared technical constraints. Output quality remains unverified.
Loading verified quotes…
Users’ choices · Llama 3.3 70B Instruct
Describe your work to find related tasks.
Public scores by use
The same model scores differently by use. Once you pick a use, the site applies that use’s quality gate before comparing cost.
Text
Chinese12933676 votes · 2026-11-19
Classify129318775 votes · 2026-11-19
Extract fields129318775 votes · 2026-11-19
General text131854473 votes · 2026-11-19
Multi-turn13179055 votes · 2026-11-19
Summarize13148323 votes · 2026-11-19
Translate & rewrite128425223 votes · 2026-11-19
Write12858042 votes · 2026-11-19
Code & tools
Code13468729 votes · 2026-11-19
Industry
Business & finance13046623 votes · 2026-11-19
Legal & government13423154 votes · 2026-11-19
Medical & health13432728 votes · 2026-11-19
Scores come from Arena public-preference leaderboards (CC BY 4.0), latest published 2026-11-19. They describe the model, not your task’s success rate or a quantized channel. Arena ↗
Declared fields from the OpenRouter model catalog, bound to exact API IDs; not our tests, price approval or account availability.
Input
Text
Output
Text
Context
131K
Reasoning parameter
Not offered
Knowledge cutoff
2023-12-31
Open-weights clue
meta-llama/Llama-3.3-70B-Instruct
Source: https://openrouter.ai/api/v1/models, captured 2026-11-21T09:20:20.905Z, raw SHA-256: 19214ba490361282… . Unstated facts stay unknown and are not inferred from names or sibling models.
Classification sources
Source declarations for registered versions; not task quality, current account availability or price approval. Unknown versions do not inherit sibling classifications.
Snapshots and routing variants remain distinct. Choose an exact ID in the comparison before deciding; model quality and access conditions need your own review.