chore(pricing): Update fireworks-ai pricing

[siddharthsambharia-portkey]

🔄 Pricing Update: fireworks-ai

📊 Summary (complete_diff mode)

Change Type	Count
➕ Models added	16
🔄 Models updated (merged)	8

➕ New Models

• deepseek-v3p1
• deepseek-v3p2
• glm-4p7
• glm-5p1
• gpt-oss-120b
• gpt-oss-20b
• llama-v3p3-70b-instruct
• qwen3-8b
• qwen3-vl-30b-a3b-instruct
• qwen3-vl-30b-a3b-thinking
• qwen3p6-plus
• qwen3-embedding-8b
• flux-1-dev-fp8
• flux-1-schnell-fp8
• flux-kontext-pro
• flux-kontext-max

🔄 Updated Models

• glm-5
• kimi-k2-instruct-0905
• kimi-k2p5
• kimi-k2-thinking
• minimax-m2p1
• minimax-m2p5
• minimax-m2p7
• mixtral-8x22b-instruct

Model → Pricing Category Mapping

Named Families (exact page values)

Model ID	Input	Cached	Output	Notes
deepseek-v3p1, deepseek-v3p2	$0.56	$0.28 (50%)	$1.68	DeepSeek V3 family
glm-4p7	$0.60	$0.30 (50%)	$2.20	GLM-4.7 named row
glm-5, glm-5p1	$1.00	$0.20 (page)	$3.20	GLM-5 named row; glm-5p1 is same family
kimi-k2-instruct-0905, kimi-k2-thinking	$0.60	$0.30 (50%)	$2.50	Kimi K2 named row
kimi-k2p5	$0.60	$0.10 (page)	$3.00	Kimi K2.5 named row
gpt-oss-120b	$0.15	$0.075 (50%)	$0.60	gpt-oss-120b named row
gpt-oss-20b	$0.07	$0.035 (50%)	$0.30	gpt-oss-20b named row
minimax-m2p1, minimax-m2p5, minimax-m2p7	$0.30	$0.03 (page)	$1.20	MiniMax M2 family named row
qwen3-vl-30b-a3b-instruct, qwen3-vl-30b-a3b-thinking	$0.15	$0.075 (50%)	$0.60	Qwen3 VL 30B A3B named row

Tier-Based (size → tier)

Model ID	Size	Tier	Input/Output
qwen3-8b	8B	4B–16B	$0.20/$0.20
qwen3p6-plus	MoE ~56B	MoE 0–56B	$0.50/$0.50
llama-v3p3-70b-instruct	70B	>16B	$0.90/$0.90
mixtral-8x22b-instruct	MoE 8x22B = 141B	MoE 56.1–176B	$1.20/$1.20

Embedding

Model ID	Price/1M tokens
qwen3-embedding-8b	$0.008

Image Generation

Model ID	Type	Price
flux-1-dev-fp8	per-step	$0.0005/step
flux-1-schnell-fp8	per-step	$0.00035/step
flux-kontext-pro	per-image	$0.04/image
flux-kontext-max	per-image	$0.08/image

Skipped

• qwen3-reranker-8b (Reranker — excluded per skill rules)

Pricing Source

All prices confirmed via binary search in current fireworks.ai/pricing HTML (April 14, 2026). Named-family prices match March 2026 citations exactly. New models (glm-5p1, minimax-m2p5, minimax-m2p7, qwen3p6-plus) assigned to same named family / tier as their siblings.

---

Generated by Pricing Agent on 2026-04-14