📡 AI API Radar

Fireworks AI Unknown

Llama 3.3 70B Instruct — pricing & price history

Bottom line: Llama 3.3 70B Instruct costs $0.9 per 1M input tokens and $0.9 per 1M output tokens on Fireworks AI, with a 131K-token context window.

API model id: llama-v3p3-70b-instruct · Verified against the provider's pricing page as of 2026-06-22.

Input / 1M tokens
$0.9
Output / 1M tokens
$0.9
Context window
131K
Provider status
Unknown

Price history

Price history is accruing — the time-series appears here once we have ≥2 dated snapshots. Full history via the price_history API.

DateInput /1MOutput /1M
2026-06-22$0.9$0.9

Cheaper alternatives with similar context

ModelProviderInput /1MOutput /1MContext
Command R7B (12-2024) Cohere $0.04 $0.15 128K
GPT-OSS 20B Groq $0.08 $0.3 131K
DeepSeek V4 Flash DeepSeek $0.14 $0.28 1M
Llama 3.3 70B (via OpenRouter) OpenRouter $0.1 $0.32 131K
Llama 4 Scout (17Bx16E) Groq $0.11 $0.34 131K
GPT-4.1 nano OpenAI $0.1 $0.4 1M

Routing agents: call price_history("fireworks--llama-v3p3-70b-instruct") or cheapest_model(min_context=131072) over our MCP/x402 API to use this programmatically. Docs →