Qwen3.8 2.4T A95B
fireworks-ai/accounts/fireworks/models/qwen3p8-2p4t-a95b · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$3.00
Blended $/1M (3:1)
$2
Input $/1M
$6
Output $/1M
$8.00
1M in + 1M out
$0.25 −88%
Cache read $/1M
#6259 of 8,511
Cheapest rank
- Provider
- Fireworks AI (
fireworks-ai) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 131,072 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“Qwen3.8 2.4T A95B” is offered by 19 providers — cheapest-effective first. IteraCompute is the cheapest at $2.89 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| IteraCompute | $1.95 | $5.7 | $2.89 | 1M |
| Fireworks AI (this) | $2 | $6 | $3.00 | 262k |
| Deep Infra | $2 | $6 | $3.00 | 262k |
| Vercel AI Gateway | $2 | $6 | $3.00 | 262k |
| Requesty | $2 | $6 | $3.00 | 262k |
| Novita AI | $2 | $6 | $3.00 | 1M |
| SiliconFlow | $2 | $6 | $3.00 | 1M |
| AIHubMix | $2 | $6 | $3.00 | 262k |
| Eden AI | $2 | $6 | $3.00 | 1M |
| Charm Hyper | $2 | $6 | $3.00 | 1M |
| Kilo Gateway | $2 | $6 | $3.00 | 1M |
| DevPass (LLM Gateway) | $2 | $6 | $3.00 | 1M |
| OpenRouter | $2 | $6 | $3.00 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Fireworks AI and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"accounts/fireworks/models/qwen3p8-2p4t-a95b","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):