GLM-4.7 Flash API pricing

8 providers serve GLM-4.7 Flash. GLM-4.7 Flash is an open-weight model (MIT) with 31B total parameters, 3B active per token (mixture-of-experts), up to 203K context. Prices below are per 1M tokens, cheapest input first.

Refreshed 2026-11-22 · list prices from provider APIs
Input floor $0.024/1M at Clf AI Gateway Output floor $0.160/1M at Clf AI Gateway Find your workload winner →
Provider Input $/1M Output $/1M Cache read $/1M Context
Clf AI Gateway $0.024 $0.160output floor - 131K
DeepInfra $0.060 $0.400 $0.010 203K Use
Cloudflare $0.060 $0.400 - 131K Use
OpenRouter marketplace quote $0.060 $0.400 - 200K Use
AWS Bedrock $0.070 $0.400 - 203K Use
Novita AI $0.070 $0.400 $0.010 200K Use
GMI Cloud $0.070 $0.400 - 203K Use
Kyma $0.081 $0.540 $0.013 203K

The cheapest way to run GLM-4.7 Flash

On an illustrative 70M-input / 30M-output monthly workload, today's lowest listed cost is roughly $6.48/month, at Clf AI Gateway. Input-heavy, output-heavy and cache-heavy workloads can produce different winners. Use the live mix calculator below rather than combining floors from two different providers. On output-token cost alone, a busy self-hosted deployment can work out cheaper (~$0.031/1M output on A6000). See the math below. Run your own numbers in the breakeven calculator, or read the breakeven math.

Your actual monthly cost

Uses today's list prices

Cache read uses the listed cache rate where available; otherwise it falls back to normal input price. Batch, write-cache, volume and negotiated discounts are excluded.

Or run it yourself: GLM-4.7 Flash self-hosting economics

GLM-4.7 Flash is open-weight (MIT), so the API price above competes with the GPU-hour market. 31B total parameters (MoE, ~3B active per token) needs roughly 43 GB VRAM at FP8 or 22 GB at INT4, KV-cache headroom included.

GPU that fits (FP8, single card)VRAMFrom $/hrCheapest at
A6000 48 GB $0.330community RunPod Rent
A40 48 GB $0.350community RunPod Rent
RTX PRO 6000 96 GB $0.500secure RunPod Rent
MI300X 192 GB $0.500community RunPod Rent
MI350 OAM 294 GB $0.500community RunPod Rent
H200 NVL 141 GB $0.500community RunPod Rent
Breakeven estimate: a well-batched vLLM deployment on one A6000 ($0.330/hr) at ~6000 aggregate tok/s and 50% utilization works out to roughly $0.031 per 1M output tokens, versus $0.160 via the cheapest output-token API (Clf AI Gateway). Self-hosting wins on cost if you can keep the GPU busy. Planning estimate: throughput varies with hardware, quantization, batch size and context. Tune it in the calculator.

Related models

ModelCheapest in $/1MCheapest out $/1MProviders
GLM-5.2 $0.560 $1.76 27
GLM-5.3 $0.070 $1.40 27
GLM-5.3 Flash $0.060 $0.200 26
GLM-5.1 $0.825 $3.30 15
GLM-5 $0.600 $1.92 11
GLM-4.7 $0.400 $1.75 10

FAQ

What is the cheapest API for GLM-4.7 Flash?

As of 2026-11-22, the lowest input price for GLM-4.7 Flash is Clf AI Gateway at $0.024 per 1M input tokens. The lowest output price is Clf AI Gateway at $0.160 per 1M output tokens. The cheapest provider for a real workload depends on its input/output mix. The next-lowest input price is DeepInfra at $0.060, a 150% difference.

How much VRAM do you need to self-host GLM-4.7 Flash?

GLM-4.7 Flash has 31B parameters, so plan for roughly 43 GB of VRAM at FP8 or 22 GB at INT4/AWQ, KV-cache headroom included. A single A6000 (48 GB) fits it.

← All models · GPU rental prices · Breakeven calculator · Get this data as JSON