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
• qwen3p6-plus
• 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

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

Model → Pricing Category Mapping

Model ID	Category	Input $/1M	Output $/1M	Notes
deepseek-v3p1	Named: DeepSeek V3 Family	$0.56	$1.68	cache_read: $0.28
deepseek-v3p2	Named: DeepSeek V3 Family	$0.56	$1.68	cache_read: $0.28
glm-4p7	Named: GLM-4.7	$0.60	$2.20	cache_read: $0.30
glm-5	Named: GLM-5	$1.00	$3.20	cache_read: $0.20 (explicit)
glm-5p1	Named: GLM-5.1	$1.40	$4.40	cache_read: $0.26 (explicit)
gpt-oss-120b	Named: GPT-OSS-120B	$0.15	$0.60	cache_read: $0.075
gpt-oss-20b	Named: GPT-OSS-20B	$0.07	$0.30	cache_read: $0.035
kimi-k2-instruct-0905	Named: Kimi K2 Instruct	$0.60	$2.50	cache_read: $0.30
kimi-k2p5	Named: Kimi K2.5	$0.60	$3.00	cache_read: $0.10 (explicit)
kimi-k2-thinking	Named: Kimi K2 Thinking	$0.60	$2.50	cache_read: $0.30
llama-v3p3-70b-instruct	Tier: >16B	$0.90	$0.90	cache_read: $0.45
minimax-m2p1	Named family (M2.x, not explicit on page)	$0.30	$1.20	cache_read: $0.15 (50% rule)
minimax-m2p5	Named: MiniMax 2.5	$0.30	$1.20	cache_read: $0.03 (explicit)
minimax-m2p7	Named: MiniMax 2.7	$0.30	$1.20	cache_read: $0.06 (explicit)
mixtral-8x22b-instruct	Tier: MoE 56.1B–176B	$1.20	$1.20	cache_read: $0.60
qwen3-8b	Tier: 4B–16B (text model)	$0.20	$0.20	cache_read: $0.10
qwen3p6-plus	Tier: >16B (large model)	$0.90	$0.90	cache_read: $0.45
qwen3-vl-30b-a3b-instruct	Named: Qwen3 VL 30B A3B	$0.15	$0.60	cache_read: $0.075
qwen3-vl-30b-a3b-thinking	Named: Qwen3 VL 30B A3B	$0.15	$0.60	cache_read: $0.075
flux-1-dev-fp8	Image per-step (FLUX.1 dev)	—	—	$0.0005/step
flux-1-schnell-fp8	Image per-step (FLUX.1 schnell)	—	—	$0.00035/step
flux-kontext-pro	Image per-image	—	—	$0.04/image
flux-kontext-max	Image per-image	—	—	$0.08/image
qwen3-embedding-8b	Embedding (Qwen3 8B)	$0.10	—	no output price

Skipped: qwen3-reranker-8b (reranker — excluded per skill rules)

Sources: Fireworks AI Models API (25 serverless models) + https://fireworks.ai/pricing

---

Generated by Pricing Agent on 2026-04-14