GLM 4.7 Flash
Z.aiReleased Jan 19, 2026Open weights · MITglm-4.7-flash
- Reasoning
- yes
- Knowledge cutoff
- January 2026
- Context
- 203K tokens
- Max output
- 128k tokens
- Input
- text
- API features
- tools, structured outputs, JSON mode, seed, logprobs
Read Oct 23, 06:00 UTC from the hosts' published offers and OpenRouter, spec sheet from Z.ai · cutoff: aiknowledgecutoff.com
The cheapest host, Venice, serves fp8 weights (maker: bf16) and serves a 125K context (maker: 198K). Cheapest at the maker's precision and context: DeepInfra, $0.46 blended. Weights and context per host
- Parameters
- 30B
- 3B active per token (MoE)
- Memory needed
- 18 GB
- in INT4 · 36 GB in INT8
- Smallest cloud setup
- RTX 3090
- 24 GB · $0.17/h, about $124 a month
- Worth it above
- 270M tokens
- a month, against the cheapest API at $0.46 per M
| Quantization | Memory | Smallest cloud GPU | Quality |
|---|---|---|---|
| INT4 (Q4) | 18 GB | RTX 3090 · $0.17/h | smallest footprint, minor quality loss |
| INT8 (Q8) | 36 GB | A100 · $1.19/h | near-lossless |
| FP16 (full) | 72 GB | A100 · $1.19/h | reference quality |
At home: in INT4 it fits a RTX 5090 (32 GB) + host PC (plus a host PC), about $3,500 once, or $0.1332/h over 3 years, electricity aside; it pays for itself after about 8B tokens against the cheapest API.
Memory ≈ parameters × bytes per parameter × 1.2 · cloud price: on-demand rate, running 24/7 · builds: GGUF, AWQ, MLX, GPTQ, Ollama · break-even calculator
| Provider | Input | Output | Cache ↑ | tok/s | First token | Uptime 24h | Checked |
|---|---|---|---|---|---|---|---|
| Venicefp8 (bf16) · 125K ctx (198K) · 16K out | $0.06 | $0.40 | $0.01 | — | — | 99.9% | Oct 19 |
| DeepInfrabf16 · 198K ctx | $0.06 | $0.40 | $0.01 | — | — | — | Sep 10 |
| Novita AIbf16 · 200K ctx · 125K out | $0.07 | $0.40 | $0.01 | — | — | — | Oct 23 |
| Cloudflareprecision not stated · 128K ctx (198K) | $0.0605 | $0.40 | — | 43 | 0.27 s | 100% | Oct 23 |
4 of 4 providers · prices per million tokens, read Oct 23, 06:00 UTC · speed: OpenRouter, median of the last 30 min, read Oct 23, 06:00 UTC · uptime: OpenRouter, last 24 h · under each host: weights precision, context and max output as served, the maker's value in brackets when the host's differs
| Provider | Weights | Context | Max output | Tools | Structured outputs | Reasoning |
|---|---|---|---|---|---|---|
| Venice | fp8 | 125K | 16K | yes | yes | yes |
| DeepInfra | bf16 | 198K | not stated by the host | — | — | — |
| Cloudflare | not stated by the host | 128K | not stated by the host | yes | yes | yes |
| Novita AI | bf16 | 200K | 125K | yes | no | yes |
Weights, context and max output: read at each host's own catalogue or docs where its terms allow, otherwise as the host declares to OpenRouter; hover a cell for its source and date · tools, structured outputs, reasoning: as declared to OpenRouter · not verified by us
GLM 4.7 Flash spec sheet, field by field, with sources
GLM 4.7 Flash spec sheetmaker-declared
What Z.ai declares about the model itself — read from its own weights repository and documentation, not from any host. What each endpoint actually serves is in the pricing above: the two can differ, and both are true.
- Context window
- 202,752 tokens
- Parameters
- 31,221,488,576≈ 31.2B
- Active experts
- 4 of 64 active per token
- Weight precision
- BF16
- License
- MIT — open weights, permissivecurated · read 2026-09-07Scope: the licence on the published weights, and nothing else. It is not the maker's acceptable-use policy, which is a separate document, and it is not the contract you sign with whichever host you call — hosts set their own terms, which this index does not read.
- Knowledge cutoff
- not published by the maker≈ January 2026 third-party estimate — not the maker's figurecurated
- Modalities
- text
- Max output (official)
- to verify
- Release date
- to verify≈ January 19, 2026 third-party catalogue — not the maker's figure
- Maker lifecycle status
- to verify
Also declared in the weights
- Architecture class
- Glm4MoeLiteForCausalLM
- Layers
- 47
- Vocabulary
- 154,880 tokens
- Weights first published
- January 19, 2026
- Weights last updated
- January 29, 2026
- Languages declared
- English · Chinese
- Paper
- arXiv:2508.06471
zai-org/GLM-4.7-Flash · config.json @ 7dd2089 · read 2026-10-08 · 6 of 10 fields published by the maker
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| Venice | $0.26 | $0.68 | $0.64 |
| DeepInfra | $0.26 | $0.68 | $0.64 |
| Cloudflare | $0.26 | $0.68 | $0.64 |
| Novita AI | $0.27 | $0.76 | $0.68 |
What each host bills for 1,000 requests of a representative job
Your own workload
Also serving GLM 4.7 Flash, without a published price
No price we can verify, so no rank.