FriendliAI

Open-model production peer when latency/tool-calling matter. Fireworks remains depot open-model default…

Listing status · Claim or correct this listing

Open-model production peer when latency/tool-calling matter. Fireworks remains depot open-model default; dedicated GPU step-up live 2026-10-01 — size reserved endpoints on the new $/hr card. Strengths: Production open-weight inference with strong latency/tool-calling claims; Clear dedicated GPU $/hr card (post-2026-10-01 step-up); OpenRouter benchmark presence.

Overall

8.0

curated_estimate

confidence: high · as of 2026-10-01

Capability fit

8.4

Price / performance

8.0

Latency / reliability

8.4

Developer & agent DX

8.2

Privacy / data retention

8.2

Lock-in risk (higher = worse)

4.0

Maturity / track record

7.6

Lock-in risk: higher = more lock-in (worse). Overall already inverts this dimension.

Sources: FriendliAI pricing: https://friendli.ai/pricing · FriendliAI: https://friendli.ai

Open-model production peer when latency/tool-calling matter. Fireworks remains depot open-model default; dedicated GPU step-up live 2026-10-01 — size reserved endpoints on the new $/hr card.

Strengths

· Production open-weight inference with strong latency/tool-calling claims
· Clear dedicated GPU $/hr card (post-2026-10-01 step-up)
· OpenRouter benchmark presence

Weaknesses

· Model API token matrix less scrape-friendly than Fireworks/Together
· Dedicated rates stepped up 2026-10-01 (A100/H100/H200 meaningful; B200 slight)
· Smaller Western mindshare vs Fireworks/Groq

Pricing notes

As of 2026-10-01 (friendli.ai/pricing live): Dedicated Endpoints on-demand step-up **is live** — A100 **$4.0**/hr, H100 **$5.0**/hr, H200 **$7.0**/hr, B200 **$9.0**/hr, B300 $12.0/hr (was through-Sep-30: A100 $2.9, H100 $3.9, H200 $4.5, B200 $8.9, B300 $12.0). Billed per second; no idle/startup charge. Model API token examples on page (GLM/DeepSeek/MiniMax/whisper). SOC2 + HIPAA.

Regions: global, us, apLast reviewed: 2026-10-01Status: active

Sourced pricing

Contract status ambiguous · input_output_split_not_a_single_rate. Single normalized $/1M: null. Machine list: /api/pricing?provider=friendli

A100 80GB · usd_per_gpu_hour · $4 · unit_mismatch · normalized null
H100 80GB · usd_per_gpu_hour · $5 · unit_mismatch · normalized null
H200 141GB · usd_per_gpu_hour · $7 · unit_mismatch · normalized null
B200 180GB · usd_per_gpu_hour · $9 · unit_mismatch · normalized null
B300 288GB · usd_per_gpu_hour · $12 · unit_mismatch · normalized null
GLM-5.3-Flash · usd_per_million_input_tokens · $0.15 · sourced_token_price
GLM-5.3-Flash · usd_per_million_output_tokens · $0.5 · sourced_token_price
GLM-5.3-Flash · usd_per_million_cached_input_tokens · $0.03 · sourced_token_price
GLM-5.2 · usd_per_million_input_tokens · $1.4 · sourced_token_price
GLM-5.2 · usd_per_million_output_tokens · $4.4 · sourced_token_price
GLM-5.2 · usd_per_million_cached_input_tokens · $0.26 · sourced_token_price
GLM-5.1 · usd_per_million_input_tokens · $1.4 · sourced_token_price

Community signals

Insight claims only — never mutate official scores. Outside reports: 0; seed examples: 0.

0 insights

No insights yet. Submit a production claim →

All insights for this provider →