Z.ai: GLM Latest
z-ai/glm-latestThis model always redirects to the latest GLM model from Z.ai.
Modalities
In / out per 1M$0.06 / $4.40
Context1M
ReleasedAug 19, 2026
Providers
42 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.06 | $4.40 | $0.05 | 1.18s | 78 tps | 100% | |
| $0.08 | $4.80 | $0.06 | 0.78s | 110 tps | 100% | |
| $0.17 | $4.80 | $0.16 | 0.79s | 107 tps | 100% | |
| $0.19 | $4.40 | $0.19 | 1.42s | 86 tps | 100% | |
| $0.70 | $2.20 | $0.13 | 2.92s | 54 tps | 100% | |
| $1.26 | $3.96 | $0.23 | 0.90s | 104 tps | 100% | |
| $1.40 | $4.40 | $0.26 | 1.02s | 88 tps | 100% | |
| $1.40 | $4.40 | $0.26 | 3.92s | 37 tps | 100% | |
| $1.40 | $4.40 | $0.26 | 3.05s | 49 tps | 100% | |
 Baseten Fastus · fp8 | $2.10 | $6.60 | $0.21 | 0.98s | 162 tps | 100% |
| Baseten Fastfp8 | $2.10 | $6.60 | $0.21 | 0.95s | 176 tps | 100% |
| $2.80 | $8.80 | $0.56 | 1.53s | 61 tps | 100% | |
| $0.70 | $2.20 | $0.13 | 0.95s | 69 tps | 99.97% | |
| $0.84 | $2.65 | $0.19 | 0.83s | 100 tps | 99.97% | |
| $0.08 | $4.40 | $0.06 | 0.96s | 86 tps | 99.95% | |
 DigitalOcean | $0.91 | $2.86 | $0.17 | 1.11s | 86 tps | 99.95% |
| $0.55 | $2.20 | $0.18 | 0.75s | 93 tps | 99.87% | |
 Fireworks Fast | $2.10 | $6.60 | $0.39 | 1.85s | 126 tps | 99.87% |
| $0.98 | $3.08 | $0.18 | 1.63s | 42 tps | 99.79% | |
| $1.40 | $4.40 | $0.26 | 0.82s | 107 tps | 99.76% | |
| $1.40 | $4.40 | $0.26 | 0.57s | 95 tps | 99.65% | |
| $1.19 | $3.74 | $0.24 | 2.81s | 46 tps | 99.63% | |
| $1.40 | $4.40 | $0.26 | 0.83s | 92 tps | 99.62% | |
| $0.15 | $3.40 | $0.14 | 1.83s | 94 tps | 99.6% | |
| $0.15 | $3.40 | $0.14 | 1.68s | 89 tps | 99.59% | |
 SiliconFlowfp8 | $0.70 | $2.20 | $0.13 | 2.56s | 62 tps | 99.58% |
| $0.49 | $2.90 | $0.19 | 2.18s | 48 tps | 99.56% | |
| $0.84 | $2.64 | $0.16 | 3.87s | 38 tps | 99.54% | |
| Fireworks | $1.40 | $4.40 | $0.26 | 1.54s | 49 tps | 99.48% |
 Mistraleu · nvfp4 | $1.54 | $4.84 | $0.15 | 0.94s | 150 tps | 99.39% |
| Basetenus · fp4 | $1.40 | $4.40 | $0.14 | 4.00s | 43 tps | 99.38% |
| Mistralnvfp4 | $1.40 | $4.40 | $0.14 | 1.88s | 87 tps | 99.37% |
| Mistralnvfp4 | $1.40 | $4.40 | $0.14 | 0.81s | 119 tps | 99.34% |
| $0.14 | $4.20 | $0.10 | 1.15s | 47 tps | 99.03% | |
| $1.40 | $4.40 | $0.26 | 1.25s | 53 tps | 98.99% | |
| Basetenfp4 | $1.40 | $4.40 | $0.14 | 4.30s | 42 tps | 98.62% |
| $0.08 | $6.00 | $0.09 | 1.45s | 34 tps | 98.31% | |
| $1.40 | $4.40 | $0.26 | 0.77s | 90 tps | 98.31% | |
 DeepInfraus · fp4 | $0.56 | $2.50 | $0.13 | 1.12s | 77 tps | 98.25% |
| $0.14 | $4.40 | $0.10 | 0.78s | 107 tps | 96.47% | |
| $1.40 | $4.40 | $0.26 | 1.25s | 64 tps | 95.74% | |
 ModelRun [by Modular]fp4 | $2.10 | $6.60 | $0.40 | 0.25s | 125 tps | 80.26% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves GLM Latest in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what GLM Latest costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.06
per 1M tokens
Output
$4.40
per 1M tokens
Cache read
$0.06
per 1M cached tokens
Included in every pass
GLM Latest is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s20.0s40.0s60.0s80.0s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Prime Intellect Together GMICloud Alibaba Prime Cloudflare Baseten Fast (us) SiliconFlow Baseten Baidu Qianfan Makora DeepInfra (us) Sail Research Phala Fireworks AkashML Wafer Alibaba Cloud Int. inference.net Mistral NovitaAI AtlasCloud Sail Research (us) Mistral Reka AI Z.ai Baseten Fast io.net Friendli Inceptron (eu) Fireworks Fast Wafer (us) Modal Baseten (us) Venice Decart Crusoe Parasail Morph DigitalOcean Mistral (eu) ModelRun [by Modular] Relace
0 tok/s1000 tok/s2000 tok/s3000 tok/s4000 tok/s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Prime Intellect Together GMICloud Alibaba Prime Cloudflare Baseten Fast (us) SiliconFlow Baseten Baidu Qianfan Makora DeepInfra (us) Sail Research Phala Fireworks AkashML Wafer Alibaba Cloud Int. inference.net Mistral NovitaAI AtlasCloud Sail Research (us) Mistral Reka AI Z.ai Baseten Fast io.net Friendli Inceptron (eu) Fireworks Fast Wafer (us) Modal Baseten (us) Venice Decart Crusoe Parasail Morph DigitalOcean Mistral (eu) ModelRun [by Modular] Relace
Uptime
Share of requests that at least one provider served successfully.
Last 3 days
Oct 11, 2:00 PMNow
Availability over the last 24 hours
100% 98% 97% 95%
Oct 13, 2:50 PMNow
Apps
Tools that most often run GLM Latest, by tokens this week.
No apps published
This measurement has not been published for the model yet. It appears as soon as it is.
Activity
Tokens processed market-wide.
No activity published
This measurement has not been published for the model yet. It appears as soon as it is.
FAQ
Which model id do I use for GLM Latest?
~z-ai/glm-latest. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does GLM Latest hold?
1,048,576 tokens per request, of which up to 131,072 can be the response.
What can it accept and return?
Input: text. Output: text.
What does GLM Latest cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.06 per 1M input tokens and $4.40 per 1M output tokens.
Who built GLM Latest?
Z.ai, in the GLM family.
Explore
Other models your pass can call.
