Spark 4.0 Ultra
iFlytek's recommended tier and the migration target as Spark Max retires 10 Mar 2026 — but pricing is quote-based, and the WebSocket-only API is a real integration cost versus every OpenAI-compatible rival here.
Data checked 2026-09-06
Chinese AI labs
ga
4.0Ultra
- Context window
- 32.8K tokens in
- Max output
- 32.8K tokens out
- Input
- — per 1M tokens
- Output
- — per 1M tokens
A What it is for
B Capabilities
| Input modalities | text |
|---|---|
| Output modalities | text |
C Others from Chinese AI labs
| Model | Context | Max out | In $/M | Out $/M | Blended | Status |
|---|---|---|---|---|---|---|
Kimi K3
kimi-k3
|
1M | — | $2.98 | $14.90 | $5.96 | ga open |
Kimi K2.7 Code
kimi-k2.7-code
|
262.1K | — | $0.95 | $4.00 | $1.71 | ga open |
Kimi K2.7 Code Highspeed
kimi-k2.7-code-highspeed
|
262.1K | — | $1.90 | $8.00 | $3.42 | ga open |
Kimi K2.6
kimi-k2.6
|
262.1K | — | $0.97 | $4.02 | $1.73 | ga open |
GLM-5.3
glm-5.3
|
1M | 131.1K | $1.40 | $4.40 | $2.15 | ga open |
GLM-5.3-Flash
glm-5.3-flash
|
1M | 131.1K | $0.07 | $0.25 | $0.12 | ga open |
GLM-5.2
glm-5.2
|
1M | 131.1K | $1.40 | $4.40 | $2.15 | ga open |
GLM-5
glm-5
|
200K | 131.1K | $1.00 | $3.20 | $1.55 | ga open |
GLM-4.7
glm-4.7
|
200K | 131.1K | $0.60 | $2.20 | $1.00 | ga open |
GLM-4.7-FlashX
glm-4.7-flashx
|
200K | 131.1K | $0.07 | $0.40 | $0.15 | ga |
GLM-4.7-Flash
glm-4.7-flash
|
200K | 131.1K | $0.00 | $0.00 | $0.00 | ga |
GLM-4.6V
glm-4.6v
|
128K | — | $0.30 | $0.90 | $0.45 | ga |
How this model is billed. Model exists and is served: the official HTTP doc lists six language-model versions (Lite, Pro, Pro-128K, Max, Max-32K, 4.0 Ultra) with model value '4.0Ultra' on https://spark-api-open.xf-yun.com/v1/chat/completions (websocket wss://spark-api.xf-yun.com/v4.0/chat, domain=Ultra), max input 32K / max output 32K, and the Batch API doc still accepts model '4.0Ultra' (batch = 30% of realtime cost). But
D Verify before you commit
Model pricing changes without notice and this page is a snapshot. Confirm against the vendor's own page before you build a budget on it.
Source: xfyun.cn · checked 2026-09-06 · Chinese AI labs pricing · API docs