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)	7

➕ 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-k2-thinking
• kimi-k2p5
• minimax-m2p1
• minimax-m2p5
• mixtral-8x22b-instruct

Data Sources

Model	Source	Pricing
deepseek-v3p1, deepseek-v3p2	Named family: DeepSeek V3	$0.56 input / $1.68 output
glm-4p7	Named family: GLM-4.7	$0.60 input / $2.20 output
glm-5	Named family: GLM-5	$1.00 input / $0.20 cached / $3.20 output
glm-5p1	Named family: GLM-5.1	$1.40 input / $0.26 cached / $4.40 output
gpt-oss-120b	Named family: OpenAI gpt-oss-120b	$0.15 input / $0.60 output
gpt-oss-20b	Named family: OpenAI gpt-oss-20b	$0.07 input / $0.30 output
kimi-k2-instruct-0905, kimi-k2-thinking	Named family: Kimi K2	$0.60 input / $2.50 output
kimi-k2p5	Named family: Kimi K2.5	$0.60 input / $0.10 cached / $3.00 output
llama-v3p3-70b-instruct	Tier: >16B parameters	$0.90 flat/1M
minimax-m2p1, minimax-m2p5	Named family: MiniMax M2	$0.30 input / $0.03 cached / $1.20 output
mixtral-8x22b-instruct	Tier: MoE 56.1B-176B	$1.20 flat/1M
qwen3-8b	Tier: 4B-16B parameters	$0.20 flat/1M
qwen3p6-plus	Tier: >16B parameters	$0.90 flat/1M
qwen3-vl-30b-a3b-instruct, qwen3-vl-30b-a3b-thinking	Named family: Qwen3 VL 30B A3B	$0.15 input / $0.60 output
flux-1-dev-fp8	Image: FLUX.1 [dev] per-step	$0.0005/step
flux-1-schnell-fp8	Image: FLUX.1 [schnell] per-step	$0.00035/step
flux-kontext-pro	Image: FLUX Kontext Pro per-image	$0.04/image
flux-kontext-max	Image: FLUX Kontext Max per-image	$0.08/image
qwen3-embedding-8b	Embeddings: Qwen3 8B	$0.10/1M input

Cache rule: 50% of input price for all text/vision models (unless named family specifies otherwise)
Batch rule: 50% of serverless input and output prices

Pricing source: https://fireworks.ai/pricing (RSC payload via ?_rsc=1 request, retrieved 2026-04-11)

---

Generated by Pricing Agent on 2026-04-11