chore(pricing): Update fireworks-ai pricing

[siddharthsambharia-portkey]

🔄 Pricing Update: fireworks-ai

📊 Summary (complete_diff mode)

Change Type	Count
➕ Models added	17
🔄 Models updated (merged)	4

➕ New Models

• deepseek-v3p1
• deepseek-v3p2
• glm-4p7
• glm-5
• gpt-oss-120b
• gpt-oss-20b
• llama-v3p3-70b-instruct
• minimax-m2p1
• minimax-m2p5
• qwen3-8b
• qwen3-vl-30b-a3b-instruct
• qwen3-vl-30b-a3b-thinking
• flux-1-dev-fp8
• flux-1-schnell-fp8
• flux-kontext-pro
• flux-kontext-max
• qwen3-embedding-8b

🔄 Updated Models

• kimi-k2-instruct-0905
• kimi-k2-thinking
• kimi-k2p5
• mixtral-8x22b-instruct

Model → Pricing Category Mapping

Named Families (exact page values)

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

Tier-Based (text/vision)

Model ID	Tier	Input	Output
llama-v3p3-70b-instruct	>16B	$0.90	$0.90
mixtral-8x22b-instruct	MoE 56.1–176B	$1.20	$1.20
qwen3-8b	4B–16B	$0.20	$0.20

Image Generation

Model ID	Type	Pricing
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

Embeddings

Model ID	Input
qwen3-embedding-8b	$0.10/1M tokens

Skipped

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

---

Generated by Pricing Agent on 2026-03-24